initial project version!

.gitignore

@@ -0,0 +1,72 @@
+# Repo-specific GitIgnore ----------------------------------------------------------------------------------------------
+*.jpg
+*.jpeg
+*.png
+*.bmp
+*.tif
+*.tiff
+*.heic
+*.JPG
+*.JPEG
+*.PNG
+*.BMP
+*.TIF
+*.TIFF
+*.HEIC
+*.mp4
+*.mov
+*.MOV
+*.avi
+*.data
+*.json
+*.cfg
+
+*.rar
+*.pkl
+*.npy
+*.csv
+
+
+
+# for tracking ---------------------------------------------------------------
+tracking/.git
+tracking/bakeup
+tracking/.gitignore
+tracking/result/**/*.mp4
+tracking/result/**/*.png
+tracking/data/boxes_imgs/*
+tracking/data/trackfeats/*
+tracking/data/tracks/*
+tracking/data/handlocal/*
+ckpts/*
+doc
+
+
+
+
+# Datasets -------------------------------------------------------------------------------------------------------------
+coco/
+coco128/
+VOC/
+
+
+
+# Neural Network weights -----------------------------------------------------------------------------------------------
+*.weights
+*.pt
+*.pb
+*.onnx
+*.engine
+*.mlmodel
+*.torchscript
+*.tflite
+*.h5
+*.caffemodel
+*_saved_model/
+*_web_model/
+*_openvino_model/
+*_paddle_model/
+
+
+
+

README.en.md

@@ -0,0 +1,36 @@
+# YoloV5_track
+
+#### Description
+{**When you're done, you can delete the content in this README and update the file with details for others getting started with your repository**}
+
+#### Software Architecture
+Software architecture description
+
+#### Installation
+
+1.  xxxx
+2.  xxxx
+3.  xxxx
+
+#### Instructions
+
+1.  xxxx
+2.  xxxx
+3.  xxxx
+
+#### Contribution
+
+1.  Fork the repository
+2.  Create Feat_xxx branch
+3.  Commit your code
+4.  Create Pull Request
+
+
+#### Gitee Feature
+
+1.  You can use Readme\_XXX.md to support different languages, such as Readme\_en.md, Readme\_zh.md
+2.  Gitee blog [blog.gitee.com](https://blog.gitee.com)
+3.  Explore open source project [https://gitee.com/explore](https://gitee.com/explore)
+4.  The most valuable open source project [GVP](https://gitee.com/gvp)
+5.  The manual of Gitee [https://gitee.com/help](https://gitee.com/help)
+6.  The most popular members  [https://gitee.com/gitee-stars/](https://gitee.com/gitee-stars/)

README.md

@@ -0,0 +1,7 @@
+说明：
+    该代码仓库是yolov5_track文件夹下代码的备份，这里的yolov5代码来至：https://github.com/ultralytics/yolov5
+    gitee地址为：https://gitee.com/nanjing-yimao-information/dettrack
+核心模块：
+    track_reid.py实现：
+        1. yolov5检测
+        2. Bot-SORT用于目标跟踪

bakeup/track_reid_20240515.py

@@ -0,0 +1,629 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+"""
+Run YOLOv5 detection inference on images, videos, directories, globs, YouTube, webcam, streams, etc.
+
+Usage - sources:
+    $ python detect.py --weights yolov5s.pt --source 0                               # webcam
+                                                     img.jpg                         # image
+                                                     vid.mp4                         # video
+                                                     screen                          # screenshot
+                                                     path/                           # directory
+                                                     list.txt                        # list of images
+                                                     list.streams                    # list of streams
+                                                     'path/*.jpg'                    # glob
+                                                     'https://youtu.be/Zgi9g1ksQHc'  # YouTube
+                                                     'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream
+
+Usage - formats:
+    $ python detect.py --weights yolov5s.pt                 # PyTorch
+                                 yolov5s.torchscript        # TorchScript
+                                 yolov5s.onnx               # ONNX Runtime or OpenCV DNN with --dnn
+                                 yolov5s_openvino_model     # OpenVINO
+                                 yolov5s.engine             # TensorRT
+                                 yolov5s.mlmodel            # CoreML (macOS-only)
+                                 yolov5s_saved_model        # TensorFlow SavedModel
+                                 yolov5s.pb                 # TensorFlow GraphDef
+                                 yolov5s.tflite             # TensorFlow Lite
+                                 yolov5s_edgetpu.tflite     # TensorFlow Edge TPU
+                                 yolov5s_paddle_model       # PaddlePaddle
+"""
+
+import argparse
+import csv
+import os
+import platform
+import sys
+from pathlib import Path
+import glob
+import numpy as np
+import pickle
+import torch
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[0]  # YOLOv5 root directory
+if str(ROOT) not in sys.path:
+    sys.path.append(str(ROOT))  # add ROOT to PATH
+ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative
+
+from models.common import DetectMultiBackend
+from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadScreenshots, LoadStreams
+from utils.general import (LOGGER, Profile, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2,
+                           increment_path, non_max_suppression, print_args, scale_boxes, strip_optimizer, xyxy2xywh)
+from utils.torch_utils import select_device, smart_inference_mode
+
+'''集成跟踪模块，输出跟踪结果文件 .npy'''
+# from ultralytics.engine.results import Boxes    # Results
+# from ultralytics.utils import IterableSimpleNamespace, yaml_load
+from tracking.utils.plotting import Annotator, colors
+from tracking.utils import Boxes, IterableSimpleNamespace, yaml_load, boxes_add_fid
+from tracking.trackers import BOTSORT, BYTETracker
+from tracking.utils.showtrack import drawtracks
+from hands.hand_inference import hand_pose
+
+# =============================================================================
+# from tracking.trackers.reid.reid_interface import ReIDInterface 
+# from tracking.trackers.reid.config import config as ReIDConfig
+# ReIDEncoder = ReIDInterface(ReIDConfig)
+# =============================================================================
+
+# tracker_yaml = r"./tracking/trackers/cfg/botsort.yaml"
+
+def init_trackers(tracker_yaml = None, bs=1):
+    """
+    Initialize trackers for object tracking during prediction.
+    """      
+    # tracker_yaml = r"./tracking/trackers/cfg/botsort.yaml"
+    
+    TRACKER_MAP = {'bytetrack': BYTETracker, 'botsort': BOTSORT}
+    
+    cfg = IterableSimpleNamespace(**yaml_load(tracker_yaml))
+    trackers = []
+    for _ in range(bs):
+        tracker = TRACKER_MAP[cfg.tracker_type](args=cfg, frame_rate=30)
+        trackers.append(tracker)
+    
+    return trackers
+
+
+@smart_inference_mode()
+def run(
+        weights=ROOT / 'yolov5s.pt',  # model path or triton URL
+        source=ROOT / 'data/images',  # file/dir/URL/glob/screen/0(webcam)
+        
+        project=ROOT / 'runs/detect',  # save results to project/name
+        name='exp',  # save results to project/name
+        
+        tracker_yaml = "./tracking/trackers/cfg/botsort.yaml",
+        imgsz=(640, 640),  # inference size (height, width)
+        conf_thres=0.25,  # confidence threshold
+        iou_thres=0.45,  # NMS IOU threshold
+        max_det=1000,  # maximum detections per image
+        device='',  # cuda device, i.e. 0 or 0,1,2,3 or cpu
+        view_img=False,  # show results
+        save_txt=False,  # save results to *.txt
+        save_csv=False,  # save results in CSV format
+        save_conf=False,  # save confidences in --save-txt labels
+        save_crop=False,  # save cropped prediction boxes
+        nosave=False,  # do not save images/videos
+        classes=None,  # filter by class: --class 0, or --class 0 2 3
+        agnostic_nms=False,  # class-agnostic NMS
+        augment=False,  # augmented inference
+        visualize=False,  # visualize features
+        update=False,  # update all models
+        exist_ok=False,  # existing project/name ok, do not increment
+        line_thickness=3,  # bounding box thickness (pixels)
+        hide_labels=False,  # hide labels
+        hide_conf=False,  # hide confidencesL
+        half=False,  # use FP16 half-precision inference
+        dnn=False,  # use OpenCV DNN for ONNX inference
+        vid_stride=1,  # video frame-rate stride
+        data=ROOT / 'data/coco128.yaml',  # dataset.yaml path
+):
+    source = str(source)
+    # filename = os.path.split(source)[-1]
+    
+    save_img = not nosave and not source.endswith('.txt')  # save inference images
+    is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
+    is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
+    webcam = source.isnumeric() or source.endswith('.streams') or (is_url and not is_file)
+    screenshot = source.lower().startswith('screen')
+    if is_url and is_file:
+        source = check_file(source)  # download
+    
+    save_dir = Path(project) / Path(source).stem
+    if save_dir.exists():
+        print(Path(source).stem)
+        # return
+        
+        save_dir = increment_path(Path(project) / name, exist_ok=exist_ok)  # increment run
+        (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir
+    else:
+        save_dir.mkdir(parents=True, exist_ok=True) 
+        
+    # Load model
+    device = select_device(device)
+    model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
+    stride, names, pt = model.stride, model.names, model.pt
+    imgsz = check_img_size(imgsz, s=stride)  # check image size
+     
+    # Dataloader
+    bs = 1  # batch_size
+    
+    dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride)    
+    vid_path, vid_writer = [None] * bs, [None] * bs
+   
+    
+    # Run inference
+    model.warmup(imgsz=(1 if pt or model.triton else bs, 3, *imgsz))  # warmup
+    seen, dt = 0, (Profile(), Profile(), Profile())
+    
+    tracker = init_trackers(tracker_yaml, bs)[0]
+    
+    handpose = hand_pose()
+    handlocals_dict = {}
+    
+    boxes_and_imgs = []
+    track_boxes = np.empty((0, 9), dtype = np.float32)
+    det_boxes = np.empty((0, 9), dtype = np.float32)
+    
+    
+    features_dict = {}    
+    for path, im, im0s, vid_cap, s in dataset:
+        if save_img and 'imgshow' not in locals().keys():
+            imgshow = im0s.copy() 
+        
+        ## ============================= tracking 功能只处理视频，writed by WQG
+        if dataset.mode == 'image':
+            continue
+
+        with dt[0]:
+            im = torch.from_numpy(im).to(model.device)
+            im = im.half() if model.fp16 else im.float()  # uint8 to fp16/32
+            im /= 255  # 0 - 255 to 0.0 - 1.0
+            if len(im.shape) == 3:
+                im = im[None]  # expand for batch dim
+
+        # Inference
+        with dt[1]:
+            visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
+            pred = model(im, augment=augment, visualize=visualize)
+
+        # NMS
+        with dt[2]:
+            pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
+
+        # Second-stage classifier (optional)
+        # pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)
+
+        # Define the path for the CSV file
+        # csv_path = save_dir / 'predictions.csv'
+
+        # Create or append to the CSV file
+        # def write_to_csv(image_name, prediction, confidence):
+        #     data = {'Image Name': image_name, 'Prediction': prediction, 'Confidence': confidence}
+        #     with open(csv_path, mode='a', newline='') as f:
+        #         writer = csv.DictWriter(f, fieldnames=data.keys())
+        #         if not csv_path.is_file():
+        #             writer.writeheader()
+        #         writer.writerow(data)
+
+        # Process predictions
+        for i, det in enumerate(pred):  # per image
+            seen += 1
+            if webcam:  # batch_size >= 1
+                p, im0, frame = path[i], im0s[i].copy(), dataset.count
+                s += f'{i}: '
+            else:
+                p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0)
+            
+            im0_ant = im0.copy()
+            
+            p = Path(p)  # to Path
+            save_path = str(save_dir / p.name)  # im.jpg
+            s += '%gx%g ' % im.shape[2:]  # print string
+            
+            annotator = Annotator(im0_ant, line_width=line_thickness, example=str(names))
+            
+            nd = len(det)
+            if nd: 
+                # Rescale boxes from img_size to im0 size
+                det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], im0.shape).round()
+                
+                det = det.cpu().numpy()
+                det = np.concatenate([det[:, :4], np.arange(nd).reshape(-1, 1), det[:, 4:]], axis=-1) 
+                
+                '''FeatFlag为相对于上一帧boxes，当前boxes是否为静止的标志。'''
+                # def static_estimate(box1, box2, TH1=8, TH2=12):
+                #     dij_abs = max(np.abs(box1 - box2))
+                #     dij_euc = max([np.linalg.norm((box1[:2] - box2[:2])), 
+                #                    np.linalg.norm((box1[2:4] - box2[2:4]))
+                #                    ])
+                #     if dij_abs < TH1 and dij_euc < TH2:
+                #         return True
+                #     else:
+                #         return False
+
+                # FeatFlag = [-1] * nd  
+                # if len(boxes_and_imgs):
+                #     detj = boxes_and_imgs[-1][0]
+                #     frmj = boxes_and_imgs[-1][-1]  
+                #     for ii in range(nd):
+                #         ## flag 中保存的是box索引
+                #         condt1 = frame-frmj==1
+                #         flag = [idx for jj, idx in enumerate(detj[:, 4]) if condt1 and static_estimate(det[ii, :4], detj[jj, :4])]
+                #         if len(flag) == 1:
+                #             FeatFlag[ii] = flag[0]
+                            
+
+                boxes_and_imgs.append((det, im0, frame)) 
+
+                ## ================================================================ writed by WQG
+                '''tracks: [x1, y1, x2, y2, track_id, score, cls, frame_index, box_index]
+                   这里，frame_index 也可以用视频的 帧ID 代替, box_index 保持不变
+                '''
+
+                det_tracking = Boxes(det, im0.shape).cpu().numpy()
+                tracks = tracker.update(det_tracking, im0)
+                
+                # detbox = [tlwh2tlbr(x._tlwh).tolist() + [x.track_id, x.score, x.cls, x.frame_id, x.idx] 
+                #           for x in tracker.tracked_stracks if x.is_activated]
+                if len(tracks):
+                    '''
+                    tracks: [x1, y1, x2, y2, track_id, score, cls, frame_index, box_index] 
+                            0   1   2   3      4        5     6       7           8     
+                    '''
+                    tracks[:, 7] = dataset.frame
+                    
+                
+                    '''================== 1. 提取手势位置 ==================='''
+                    # idx_0 = tracks[:, 6].astype(np.int_) == 0
+                    # hn = 0
+                    # for j, index in enumerate(idx_0):
+                    #     if index:        
+                    #         track = tracks[j, :]
+                    #         hand_local, imgshow = handpose.get_hand_local(track, im0)
+                    #         handlocals_dict.update({int(track[7]): {int(track[8]): hand_local}})
+                            
+                    #         # '''yoloV5和手势检测的召回率并不一直，用hand_local代替tracks中手部的(x1, y1, x2, y2)，会使得两种坐标方式混淆'''
+                    #         # if hand_local: tracks[j, :4] = hand_local
+                            
+                    #         hn += 1 
+                    #         cv2.imwrite(f"D:\DeepLearning\yolov5\hands\images\{Path(source).stem}_{int(track[7])}_{hn}.png", imgshow)
+
+
+                    '''================== 2. 存储轨迹信息 ==================='''    
+                    track_boxes = np.concatenate([track_boxes, tracks], axis=0)
+
+                    # det_boxes = np.concatenate([det_boxes, detbox], axis=0)
+                    '''================== 3. 存储轨迹 REID 特征 ============='''
+                    
+                    def crop_img(track, image):                                                
+                        tlbr = track.tlwh_to_tlbr(track._tlwh).astype(np.int_)
+
+                        H, W = image.shape[:2]
+                        tlbr[0] = max(0, tlbr[0])
+                        tlbr[1] = max(0, tlbr[1])
+                        tlbr[2] = min(W - 1, tlbr[2])
+                        tlbr[3] = min(H - 1, tlbr[3])
+                        
+                        img = image[tlbr[1]:tlbr[3], tlbr[0]:tlbr[2], :]
+                        # cv2.imwrite(f"./runs/imgs/{int(track.idx)}.png", img)
+                        return img
+                    
+                    feat_dict_1 = {f'{int(x.idx)}_img': crop_img(x, im0) for x in tracker.tracked_stracks if x.is_activated} 
+                    feat_dict = {int(x.idx): x.curr_feat for x in tracker.tracked_stracks if x.is_activated}
+                    feat_dict.update(feat_dict_1)
+
+                    features_dict.update({int(dataset.frame): feat_dict})
+                    
+                #     det_anno = tracks.copy()
+                # else:
+                #     idmark = -1 * np.ones([det.shape[0], 1])
+                #     det_anno = np.concatenate([det[:,:4], idmark, det[:, 4:]], axis=1)
+                    
+
+
+
+                for *xyxy, id, conf, cls, fid, bid in reversed(tracks):
+                    name = ('' if id==-1 else f'id:{int(id)} ') + names[int(cls)]                   
+                    label = None if hide_labels else (name if hide_conf else f'{name} {conf:.2f}')
+                    
+                    if id >=0 and cls==0:
+                        color = colors(int(cls), True)
+                    elif id >=0 and cls!=0:
+                        color = colors(int(id), True)
+                    else:
+                        color = colors(19, True)     # 19为调色板的最后一个元素
+           
+                    annotator.box_label(xyxy, label, color=color)
+
+            # Save results (image and video with tracking)
+            im0 = annotator.result()
+            save_path_img, ext = os.path.splitext(save_path)
+            if save_img:
+                if dataset.mode == 'image':
+                    imgpath = save_path_img + f"_{dataset}.png"
+                else:
+                    imgpath = save_path_img + f"_{dataset.frame}.png"
+                    
+                cv2.imwrite(Path(imgpath), im0)
+                
+                if vid_path[i] != save_path:  # new video
+                    vid_path[i] = save_path
+                    if isinstance(vid_writer[i], cv2.VideoWriter):
+                        vid_writer[i].release()  # release previous video writer
+                    if vid_cap:  # video
+                        fps = vid_cap.get(cv2.CAP_PROP_FPS)
+                        w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+                        h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+                    else:  # stream
+                        fps, w, h = 30, im0.shape[1], im0.shape[0]
+                    save_path = str(Path(save_path).with_suffix('.mp4'))  # force *.mp4 suffix on results videos
+                    vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
+                vid_writer[i].write(im0)
+
+        # Print time (inference-only)
+        LOGGER.info(f"{s}{'' if len(det) else '(no detections), '}{dt[1].dt * 1E3:.1f}ms")
+
+    
+    ## ======================================================================== written by WQG
+    ## track_boxes: Array, [x1, y1, x2, y2, track_id, score, cls, frame_index, box_id]
+    
+    '''上面保存了检测结果是视频和图像，以下还保存五种类型的数据'''
+    filename = os.path.split(save_path_img)[-1]
+    # file, ext = os.path.splitext(filename)
+# =============================================================================
+#     fileElements = filename.split('_')
+#     if len(fileElements) == 6 and len(fileElements[3])==1:
+#         barcode = fileElements[1]
+#         camera = fileElements[3]
+#     elif len(fileElements) == 7 and len(fileElements[3])==1:
+#         barcode = fileElements[2]
+#         camera = fileElements[4]
+#     else:
+#         barcode = ''
+#         camera = ''
+# =============================================================================
+
+    
+    '''======================== 1. save in './run/detect/' ===================='''
+    if source.find("front") >= 0:
+        carttemp = cv2.imread("./tracking/shopcart/cart_tempt/board_ftmp_line.png")
+    else:
+        carttemp = cv2.imread("./tracking/shopcart/cart_tempt/edgeline.png")
+        
+    
+    imgshow = drawtracks(track_boxes, carttemp)    
+    showpath_1 = save_path_img + "_show.png"
+    cv2.imwrite(Path(showpath_1), imgshow)
+
+
+    '''======================== 2. save boxes and raw images =================='''
+    # boxes_imgs_dir = Path('./tracking/data/boxes_imgs/')
+    # if not boxes_imgs_dir.exists():
+    #     boxes_imgs_dir.mkdir(parents=True, exist_ok=True)
+    # boxes_imgs_path = boxes_imgs_dir.joinpath(f'{filename}.pkl')
+    # with open(boxes_imgs_path, 'wb') as file:
+    #     pickle.dump(boxes_and_imgs, file)
+    
+    '''======================== 3. save tracks data ==========================='''
+    tracks_dir = Path('./tracking/data/tracks/')
+    if not tracks_dir.exists():
+        tracks_dir.mkdir(parents=True, exist_ok=True)
+    tracks_path = tracks_dir.joinpath(filename + "_track.npy") 
+    np.save(tracks_path, track_boxes)
+    
+    detect_path = tracks_dir.joinpath(filename + "_detect.npy") 
+    np.save(detect_path, det_boxes)
+ 
+    '''======================== 4. save reid features data ===================='''
+    feats_dir = Path('./tracking/data/trackfeats/')
+    if not feats_dir.exists():
+        feats_dir.mkdir(parents=True, exist_ok=True)
+    feats_path = feats_dir.joinpath(f'{filename}.pkl')
+    with open(feats_path, 'wb') as file:
+        pickle.dump(features_dict, file)
+        
+    '''======================== 5. save hand_local data =================='''
+    # handlocal_dir = Path('./tracking/data/handlocal/')
+    # if not handlocal_dir.exists():
+    #     handlocal_dir.mkdir(parents=True, exist_ok=True)
+    # handlocal_path = handlocal_dir.joinpath(f'{filename}.pkl')
+    # with open(handlocal_path, 'wb') as file:
+    #     pickle.dump(handlocals_dict, file)
+        
+
+
+    
+    # Print results
+    t = tuple(x.t / seen * 1E3 for x in dt)  # speeds per image
+    LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t)
+    if save_txt or save_img:
+        s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
+        LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
+    if update:
+        strip_optimizer(weights[0])  # update model (to fix SourceChangeWarning)
+
+
+def parse_opt():
+    modelpath = ROOT / 'ckpts/best_yolov5m_250000.pt'       # 'ckpts/best_15000_0908.pt',  'ckpts/yolov5s.pt', 'ckpts/best_20000_cls30.pt'
+    
+    '''datapath为视频文件目录或视频文件'''
+    datapath = r"D:/datasets/ym/videos/标记视频/"   # ROOT/'data/videos',  ROOT/'data/images'   images    
+    # datapath = r"D:\datasets\ym\highvalue\videos"
+    # datapath = r"D:/dcheng/videos/"
+    # modelpath = ROOT / 'ckpts/yolov5s.pt' 
+    
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--weights', nargs='+', type=str, default=modelpath, help='model path or triton URL')   # 'yolov5s.pt', best_15000_0908.pt
+    parser.add_argument('--source', type=str, default=datapath, help='file/dir/URL/glob/screen/0(webcam)')    # images, videos
+    parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='(optional) dataset.yaml path')
+    parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')
+    parser.add_argument('--conf-thres', type=float, default=0.25, help='confidence threshold')
+    parser.add_argument('--iou-thres', type=float, default=0.45, help='NMS IoU threshold')
+    parser.add_argument('--max-det', type=int, default=1000, help='maximum detections per image')
+    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    parser.add_argument('--view-img', action='store_true', help='show results')
+    parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
+    parser.add_argument('--save-csv', action='store_true', help='save results in CSV format')
+    parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
+    parser.add_argument('--save-crop', action='store_true', help='save cropped prediction boxes')
+    parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
+    parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --classes 0, or --classes 0 2 3')
+    parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
+    parser.add_argument('--augment', action='store_true', help='augmented inference')
+    parser.add_argument('--visualize', action='store_true', help='visualize features')
+    parser.add_argument('--update', action='store_true', help='update all models')
+    parser.add_argument('--project', default=ROOT / 'runs/detect', help='save results to project/name')
+    parser.add_argument('--name', default='exp', help='save results to project/name')
+    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
+    parser.add_argument('--line-thickness', default=3, type=int, help='bounding box thickness (pixels)')
+    parser.add_argument('--hide-labels', default=False, action='store_true', help='hide labels')
+    parser.add_argument('--hide-conf', default=False, action='store_true', help='hide confidences')
+    parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')
+    parser.add_argument('--dnn', action='store_true', help='use OpenCV DNN for ONNX inference')
+    parser.add_argument('--vid-stride', type=int, default=1, help='video frame-rate stride')
+    opt = parser.parse_args()
+    opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1  # expand
+    print_args(vars(opt))
+    return opt
+
+def main_loop_folders(opt):
+    check_requirements(ROOT / 'requirements.txt', exclude=('tensorboard', 'thop'))
+    
+    # path1 = r"D:\datasets\ym\videos\标记视频" 
+    
+    path2 = r"D:\datasets\ym\永辉双摄视频\加购_前摄\videos_front"
+    # path3 = r"D:\datasets\ym\永辉双摄视频\加购_后摄\videos_back"
+    # path4 = r"D:\datasets\ym\永辉双摄视频\退购_前摄\videos_front"
+    # path5 = r"D:\datasets\ym\永辉双摄视频\退购_后摄\videos_back"
+    
+    path6 = r"D:\datasets\ym\测试数据20240328\front"
+    path7 = r"D:\datasets\ym\测试数据20240328\back"
+
+    '''列表paths内的元素为视频文件夹，该文件夹下元素为视频文件'''
+    paths = [path2, path7]   # [path1, path2, path3, path4, path5]
+
+    optdict = vars(opt)
+    k1, k2 = 0, 0
+    for p in paths:
+        files = []
+        if os.path.isdir(p):
+            files.extend(sorted(glob.glob(os.path.join(p, '*.*'))))
+            for file in files:
+                file = r"D:\datasets\ym\测试数据20240328\front\112954521-7dd5ddad-922a-427b-b59e-a593e95e6ff4_front.mp4"
+                
+                optdict["source"] = file
+                run(**optdict)
+                
+                k2 += 1
+                if k2 == 1:
+                    break
+                
+        elif os.path.isfile(p):
+            run(**optdict)
+        
+        k1 += 1
+        if k1 == 1:
+            break
+        
+def find_files_in_nested_dirs(root_dir):
+    all_files = []
+    extensions = ['.mp4']
+    for dirpath, dirnames, filenames in os.walk(root_dir):
+        for filename in filenames:
+            file, ext = os.path.splitext(filename)
+            if ext in extensions:
+                all_files.append(os.path.join(dirpath, filename))
+    return all_files
+            
+print('=======')
+
+def main(opt):
+    check_requirements(ROOT / 'requirements.txt', exclude=('tensorboard', 'thop'))
+       
+    p = r"D:\datasets\ym\永辉测试数据_202404\20240402"
+    optdict = vars(opt)
+    files = []
+    k = 0
+    
+    all_files = find_files_in_nested_dirs(p)
+    
+    if os.path.isdir(p):
+        files.extend(sorted(glob.glob(os.path.join(p, '*.*'))))   
+        for file in files:
+            optdict["source"] = file
+            run(**optdict)
+            
+            k += 1
+            if k == 2:
+                break         
+    elif os.path.isfile(p):
+        run(**vars(opt))
+        
+def main_loop(opt):
+    check_requirements(ROOT / 'requirements.txt', exclude=('tensorboard', 'thop'))
+    
+    optdict = vars(opt)   
+    
+    # p = r"D:\datasets\ym\永辉测试数据_比对" 
+    p = r"D:\datasets\ym\广告板遮挡测试\8"
+    # p = r"D:\datasets\ym\videos\标记视频"
+    # p = r"D:\datasets\ym\实验室测试"
+    
+    k = 0
+    if os.path.isdir(p):
+        files = find_files_in_nested_dirs(p)
+        
+        files = [r"D:\datasets\ym\videos\标记视频\test_20240402-173935_6920152400975_back_174037372.mp4",
+                  r"D:\datasets\ym\videos\标记视频\test_20240402-173935_6920152400975_front_174037379.mp4"
+                ]
+        
+        files = [r"D:\datasets\ym\广告板遮挡测试\8\2500441577966_20240508-175946_front_addGood_70f75407b7ae_155_17788571404.mp4"]
+        for file in files:
+            optdict["source"] = file
+            run(**optdict)
+            
+            k += 1
+            if k == 2:
+                break
+    elif os.path.isfile(p):
+        optdict["source"] = p
+        run(**vars(opt))
+
+
+
+
+if __name__ == '__main__':
+    opt = parse_opt()
+    
+    # main_loop_folders(opt)
+    # main(opt)
+    main_loop(opt)
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    

benchmarks.py

@@ -0,0 +1,174 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+"""
+Run YOLOv5 benchmarks on all supported export formats
+
+Format                      | `export.py --include`         | Model
+---                         | ---                           | ---
+PyTorch                     | -                             | yolov5s.pt
+TorchScript                 | `torchscript`                 | yolov5s.torchscript
+ONNX                        | `onnx`                        | yolov5s.onnx
+OpenVINO                    | `openvino`                    | yolov5s_openvino_model/
+TensorRT                    | `engine`                      | yolov5s.engine
+CoreML                      | `coreml`                      | yolov5s.mlmodel
+TensorFlow SavedModel       | `saved_model`                 | yolov5s_saved_model/
+TensorFlow GraphDef         | `pb`                          | yolov5s.pb
+TensorFlow Lite             | `tflite`                      | yolov5s.tflite
+TensorFlow Edge TPU         | `edgetpu`                     | yolov5s_edgetpu.tflite
+TensorFlow.js               | `tfjs`                        | yolov5s_web_model/
+
+Requirements:
+    $ pip install -r requirements.txt coremltools onnx onnx-simplifier onnxruntime openvino-dev tensorflow-cpu  # CPU
+    $ pip install -r requirements.txt coremltools onnx onnx-simplifier onnxruntime-gpu openvino-dev tensorflow  # GPU
+    $ pip install -U nvidia-tensorrt --index-url https://pypi.ngc.nvidia.com  # TensorRT
+
+Usage:
+    $ python benchmarks.py --weights yolov5s.pt --img 640
+"""
+
+import argparse
+import platform
+import sys
+import time
+from pathlib import Path
+
+import pandas as pd
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[0]  # YOLOv5 root directory
+if str(ROOT) not in sys.path:
+    sys.path.append(str(ROOT))  # add ROOT to PATH
+# ROOT = ROOT.relative_to(Path.cwd())  # relative
+
+import export
+from models.experimental import attempt_load
+from models.yolo import SegmentationModel
+from segment.val import run as val_seg
+from utils import notebook_init
+from utils.general import LOGGER, check_yaml, file_size, print_args
+from utils.torch_utils import select_device
+from val import run as val_det
+
+
+def run(
+        weights=ROOT / 'yolov5s.pt',  # weights path
+        imgsz=640,  # inference size (pixels)
+        batch_size=1,  # batch size
+        data=ROOT / 'data/coco128.yaml',  # dataset.yaml path
+        device='',  # cuda device, i.e. 0 or 0,1,2,3 or cpu
+        half=False,  # use FP16 half-precision inference
+        test=False,  # test exports only
+        pt_only=False,  # test PyTorch only
+        hard_fail=False,  # throw error on benchmark failure
+):
+    y, t = [], time.time()
+    device = select_device(device)
+    model_type = type(attempt_load(weights, fuse=False))  # DetectionModel, SegmentationModel, etc.
+    for i, (name, f, suffix, cpu, gpu) in export.export_formats().iterrows():  # index, (name, file, suffix, CPU, GPU)
+        try:
+            assert i not in (9, 10), 'inference not supported'  # Edge TPU and TF.js are unsupported
+            assert i != 5 or platform.system() == 'Darwin', 'inference only supported on macOS>=10.13'  # CoreML
+            if 'cpu' in device.type:
+                assert cpu, 'inference not supported on CPU'
+            if 'cuda' in device.type:
+                assert gpu, 'inference not supported on GPU'
+
+            # Export
+            if f == '-':
+                w = weights  # PyTorch format
+            else:
+                w = export.run(weights=weights,
+                               imgsz=[imgsz],
+                               include=[f],
+                               batch_size=batch_size,
+                               device=device,
+                               half=half)[-1]  # all others
+            assert suffix in str(w), 'export failed'
+
+            # Validate
+            if model_type == SegmentationModel:
+                result = val_seg(data, w, batch_size, imgsz, plots=False, device=device, task='speed', half=half)
+                metric = result[0][7]  # (box(p, r, map50, map), mask(p, r, map50, map), *loss(box, obj, cls))
+            else:  # DetectionModel:
+                result = val_det(data, w, batch_size, imgsz, plots=False, device=device, task='speed', half=half)
+                metric = result[0][3]  # (p, r, map50, map, *loss(box, obj, cls))
+            speed = result[2][1]  # times (preprocess, inference, postprocess)
+            y.append([name, round(file_size(w), 1), round(metric, 4), round(speed, 2)])  # MB, mAP, t_inference
+        except Exception as e:
+            if hard_fail:
+                assert type(e) is AssertionError, f'Benchmark --hard-fail for {name}: {e}'
+            LOGGER.warning(f'WARNING ⚠️ Benchmark failure for {name}: {e}')
+            y.append([name, None, None, None])  # mAP, t_inference
+        if pt_only and i == 0:
+            break  # break after PyTorch
+
+    # Print results
+    LOGGER.info('\n')
+    parse_opt()
+    notebook_init()  # print system info
+    c = ['Format', 'Size (MB)', 'mAP50-95', 'Inference time (ms)'] if map else ['Format', 'Export', '', '']
+    py = pd.DataFrame(y, columns=c)
+    LOGGER.info(f'\nBenchmarks complete ({time.time() - t:.2f}s)')
+    LOGGER.info(str(py if map else py.iloc[:, :2]))
+    if hard_fail and isinstance(hard_fail, str):
+        metrics = py['mAP50-95'].array  # values to compare to floor
+        floor = eval(hard_fail)  # minimum metric floor to pass, i.e. = 0.29 mAP for YOLOv5n
+        assert all(x > floor for x in metrics if pd.notna(x)), f'HARD FAIL: mAP50-95 < floor {floor}'
+    return py
+
+
+def test(
+        weights=ROOT / 'yolov5s.pt',  # weights path
+        imgsz=640,  # inference size (pixels)
+        batch_size=1,  # batch size
+        data=ROOT / 'data/coco128.yaml',  # dataset.yaml path
+        device='',  # cuda device, i.e. 0 or 0,1,2,3 or cpu
+        half=False,  # use FP16 half-precision inference
+        test=False,  # test exports only
+        pt_only=False,  # test PyTorch only
+        hard_fail=False,  # throw error on benchmark failure
+):
+    y, t = [], time.time()
+    device = select_device(device)
+    for i, (name, f, suffix, gpu) in export.export_formats().iterrows():  # index, (name, file, suffix, gpu-capable)
+        try:
+            w = weights if f == '-' else \
+                export.run(weights=weights, imgsz=[imgsz], include=[f], device=device, half=half)[-1]  # weights
+            assert suffix in str(w), 'export failed'
+            y.append([name, True])
+        except Exception:
+            y.append([name, False])  # mAP, t_inference
+
+    # Print results
+    LOGGER.info('\n')
+    parse_opt()
+    notebook_init()  # print system info
+    py = pd.DataFrame(y, columns=['Format', 'Export'])
+    LOGGER.info(f'\nExports complete ({time.time() - t:.2f}s)')
+    LOGGER.info(str(py))
+    return py
+
+
+def parse_opt():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.pt', help='weights path')
+    parser.add_argument('--imgsz', '--img', '--img-size', type=int, default=640, help='inference size (pixels)')
+    parser.add_argument('--batch-size', type=int, default=1, help='batch size')
+    parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='dataset.yaml path')
+    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')
+    parser.add_argument('--test', action='store_true', help='test exports only')
+    parser.add_argument('--pt-only', action='store_true', help='test PyTorch only')
+    parser.add_argument('--hard-fail', nargs='?', const=True, default=False, help='Exception on error or < min metric')
+    opt = parser.parse_args()
+    opt.data = check_yaml(opt.data)  # check YAML
+    print_args(vars(opt))
+    return opt
+
+
+def main(opt):
+    test(**vars(opt)) if opt.test else run(**vars(opt))
+
+
+if __name__ == '__main__':
+    opt = parse_opt()
+    main(opt)

detect.py

@@ -0,0 +1,308 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+"""
+Run YOLOv5 detection inference on images, videos, directories, globs, YouTube, webcam, streams, etc.
+
+Usage - sources:
+    $ python detect.py --weights yolov5s.pt --source 0                               # webcam
+                                                     img.jpg                         # image
+                                                     vid.mp4                         # video
+                                                     screen                          # screenshot
+                                                     path/                           # directory
+                                                     list.txt                        # list of images
+                                                     list.streams                    # list of streams
+                                                     'path/*.jpg'                    # glob
+                                                     'https://youtu.be/Zgi9g1ksQHc'  # YouTube
+                                                     'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream
+
+Usage - formats:
+    $ python detect.py --weights yolov5s.pt                 # PyTorch
+                                 yolov5s.torchscript        # TorchScript
+                                 yolov5s.onnx               # ONNX Runtime or OpenCV DNN with --dnn
+                                 yolov5s_openvino_model     # OpenVINO
+                                 yolov5s.engine             # TensorRT
+                                 yolov5s.mlmodel            # CoreML (macOS-only)
+                                 yolov5s_saved_model        # TensorFlow SavedModel
+                                 yolov5s.pb                 # TensorFlow GraphDef
+                                 yolov5s.tflite             # TensorFlow Lite
+                                 yolov5s_edgetpu.tflite     # TensorFlow Edge TPU
+                                 yolov5s_paddle_model       # PaddlePaddle
+"""
+
+import argparse
+import csv
+import os
+import platform
+import sys
+from pathlib import Path
+
+import torch
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[0]  # YOLOv5 root directory
+if str(ROOT) not in sys.path:
+    sys.path.append(str(ROOT))  # add ROOT to PATH
+ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative
+
+from ultralytics.utils.plotting import Annotator, colors, save_one_box
+
+
+from models.common import DetectMultiBackend
+from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadScreenshots, LoadStreams
+from utils.general import (LOGGER, Profile, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2,
+                           increment_path, non_max_suppression, print_args, scale_boxes, strip_optimizer, xyxy2xywh)
+from utils.torch_utils import select_device, smart_inference_mode
+
+
+
+@smart_inference_mode()
+def run(
+        weights=ROOT / 'yolov5s.pt',  # model path or triton URL
+        source=ROOT / 'data/images',  # file/dir/URL/glob/screen/0(webcam)
+        data=ROOT / 'data/coco128.yaml',  # dataset.yaml path
+        imgsz=(640, 640),  # inference size (height, width)
+        conf_thres=0.25,  # confidence threshold
+        iou_thres=0.45,  # NMS IOU threshold
+        max_det=1000,  # maximum detections per image
+        device='',  # cuda device, i.e. 0 or 0,1,2,3 or cpu
+        view_img=False,  # show results
+        save_txt=False,  # save results to *.txt
+        save_csv=False,  # save results in CSV format
+        save_conf=False,  # save confidences in --save-txt labels
+        save_crop=False,  # save cropped prediction boxes
+        nosave=False,  # do not save images/videos
+        classes=None,  # filter by class: --class 0, or --class 0 2 3
+        agnostic_nms=False,  # class-agnostic NMS
+        augment=False,  # augmented inference
+        visualize=False,  # visualize features
+        update=False,  # update all models
+        project=ROOT / 'runs/detect',  # save results to project/name
+        name='exp',  # save results to project/name
+        exist_ok=False,  # existing project/name ok, do not increment
+        line_thickness=3,  # bounding box thickness (pixels)
+        hide_labels=False,  # hide labels
+        hide_conf=False,  # hide confidences
+        half=False,  # use FP16 half-precision inference
+        dnn=False,  # use OpenCV DNN for ONNX inference
+        vid_stride=1,  # video frame-rate stride
+):
+    source = str(source)
+    save_img = not nosave and not source.endswith('.txt')  # save inference images
+    is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
+    is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
+    webcam = source.isnumeric() or source.endswith('.streams') or (is_url and not is_file)
+    screenshot = source.lower().startswith('screen')
+    if is_url and is_file:
+        source = check_file(source)  # download
+
+    # Directories
+    save_dir = increment_path(Path(project) / name, exist_ok=exist_ok)  # increment run
+    (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir
+
+    # Load model
+    device = select_device(device)
+    model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
+    stride, names, pt = model.stride, model.names, model.pt
+    imgsz = check_img_size(imgsz, s=stride)  # check image size
+
+    # Dataloader
+    bs = 1  # batch_size
+    if webcam:
+        view_img = check_imshow(warn=True)
+        dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride)
+        bs = len(dataset)
+    elif screenshot:
+        dataset = LoadScreenshots(source, img_size=imgsz, stride=stride, auto=pt)
+    else:
+        dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride)
+    vid_path, vid_writer = [None] * bs, [None] * bs
+   
+    
+    # Run inference
+    model.warmup(imgsz=(1 if pt or model.triton else bs, 3, *imgsz))  # warmup
+    seen, windows, dt = 0, [], (Profile(), Profile(), Profile())
+    
+    
+    for path, im, im0s, vid_cap, s in dataset:
+        ## ============================= tracking 功能只处理视频，writed by WQG
+        if dataset.mode == 'image':
+            continue
+        
+        
+        with dt[0]:
+            im = torch.from_numpy(im).to(model.device)
+            im = im.half() if model.fp16 else im.float()  # uint8 to fp16/32
+            im /= 255  # 0 - 255 to 0.0 - 1.0
+            if len(im.shape) == 3:
+                im = im[None]  # expand for batch dim
+
+        # Inference
+        with dt[1]:
+            visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
+            pred = model(im, augment=augment, visualize=visualize)
+
+        # NMS
+        with dt[2]:
+            pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
+
+        # Second-stage classifier (optional)
+        # pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)
+
+        # Define the path for the CSV file
+        csv_path = save_dir / 'predictions.csv'
+
+        # Create or append to the CSV file
+        def write_to_csv(image_name, prediction, confidence):
+            data = {'Image Name': image_name, 'Prediction': prediction, 'Confidence': confidence}
+            with open(csv_path, mode='a', newline='') as f:
+                writer = csv.DictWriter(f, fieldnames=data.keys())
+                if not csv_path.is_file():
+                    writer.writeheader()
+                writer.writerow(data)
+        
+
+
+        # Process predictions
+        for i, det in enumerate(pred):  # per image
+            seen += 1
+            if webcam:  # batch_size >= 1
+                p, im0, frame = path[i], im0s[i].copy(), dataset.count
+                s += f'{i}: '
+            else:
+                p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0)
+
+            p = Path(p)  # to Path
+            save_path = str(save_dir / p.name)  # im.jpg
+            txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}')  # im.txt
+            s += '%gx%g ' % im.shape[2:]  # print string
+            gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]  # normalization gain whwh
+            imc = im0.copy() if save_crop else im0  # for save_crop
+            
+            annotator = Annotator(im0, line_width=line_thickness, example=str(names))
+            
+            ## ================================================================================== writed by WQG
+            annotator_track = Annotator(im0, line_width=line_thickness, example=str(names))
+            if len(det):
+                # Rescale boxes from img_size to im0 size
+                det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], im0.shape).round()
+            
+                
+                # Print results
+                for c in det[:, 5].unique():
+                    n = (det[:, 5] == c).sum()  # detections per class
+                    s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string
+
+                # Write results
+                for *xyxy, conf, cls in reversed(det):
+                    c = int(cls)  # integer class
+                    label = names[c] if hide_conf else f'{names[c]}'
+                    confidence = float(conf)
+                    confidence_str = f'{confidence:.2f}'
+
+                    if save_csv:
+                        write_to_csv(p.name, label, confidence_str)
+
+                    if save_txt:  # Write to file
+                        xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
+                        line = (cls, *xywh, conf) if save_conf else (cls, *xywh)  # label format
+                        with open(f'{txt_path}.txt', 'a') as f:
+                            f.write(('%g ' * len(line)).rstrip() % line + '\n')
+
+                    if save_img or save_crop or view_img:  # Add bbox to image
+                        c = int(cls)  # integer class
+                        label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')
+                        annotator.box_label(xyxy, label, color=colors(c, True))
+                    if save_crop:
+                        save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)
+
+
+            # Stream results
+            im0 = annotator.result()
+            if view_img:
+                if platform.system() == 'Linux' and p not in windows:
+                    windows.append(p)
+                    cv2.namedWindow(str(p), cv2.WINDOW_NORMAL | cv2.WINDOW_KEEPRATIO)  # allow window resize (Linux)
+                    cv2.resizeWindow(str(p), im0.shape[1], im0.shape[0])
+                cv2.imshow(str(p), im0)
+                cv2.waitKey(1)  # 1 millisecond
+
+            # Save results (image with detections)
+            if save_img:
+                if dataset.mode == 'image':
+                    cv2.imwrite(save_path, im0)
+                else:  # 'video' or 'stream'
+                    if vid_path[i] != save_path:  # new video
+                        vid_path[i] = save_path
+                        if isinstance(vid_writer[i], cv2.VideoWriter):
+                            vid_writer[i].release()  # release previous video writer
+                        if vid_cap:  # video
+                            fps = vid_cap.get(cv2.CAP_PROP_FPS)
+                            w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+                            h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+                        else:  # stream
+                            fps, w, h = 30, im0.shape[1], im0.shape[0]
+                        save_path = str(Path(save_path).with_suffix('.mp4'))  # force *.mp4 suffix on results videos
+                        vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
+                    vid_writer[i].write(im0)
+
+        # Print time (inference-only)
+        LOGGER.info(f"{s}{'' if len(det) else '(no detections), '}{dt[1].dt * 1E3:.1f}ms")
+ 
+        
+
+    # Print results
+    t = tuple(x.t / seen * 1E3 for x in dt)  # speeds per image
+    LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t)
+    if save_txt or save_img:
+        s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
+        LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
+    if update:
+        strip_optimizer(weights[0])  # update model (to fix SourceChangeWarning)
+
+
+def parse_opt():
+    modelpath = ROOT / 'ckpts/best_15000_0908.pt'       # ROOT/'ckpts/best_15000_0908.pt',  ROOT/'ckpts/yolov5s.pt'
+    datapath = r"D:/datasets/ym/videos/标记视频"   # ROOT/'data/videos',  ROOT/'data/images'   images
+     
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--weights', nargs='+', type=str, default=modelpath, help='model path or triton URL')   # 'yolov5s.pt', best_15000_0908.pt
+    parser.add_argument('--source', type=str, default=datapath, help='file/dir/URL/glob/screen/0(webcam)')    # images, videos
+    parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='(optional) dataset.yaml path')
+    parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')
+    parser.add_argument('--conf-thres', type=float, default=0.25, help='confidence threshold')
+    parser.add_argument('--iou-thres', type=float, default=0.45, help='NMS IoU threshold')
+    parser.add_argument('--max-det', type=int, default=1000, help='maximum detections per image')
+    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    parser.add_argument('--view-img', action='store_true', help='show results')
+    parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
+    parser.add_argument('--save-csv', action='store_true', help='save results in CSV format')
+    parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
+    parser.add_argument('--save-crop', action='store_true', help='save cropped prediction boxes')
+    parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
+    parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --classes 0, or --classes 0 2 3')
+    parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
+    parser.add_argument('--augment', action='store_true', help='augmented inference')
+    parser.add_argument('--visualize', action='store_true', help='visualize features')
+    parser.add_argument('--update', action='store_true', help='update all models')
+    parser.add_argument('--project', default=ROOT / 'runs/detect', help='save results to project/name')
+    parser.add_argument('--name', default='exp', help='save results to project/name')
+    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
+    parser.add_argument('--line-thickness', default=3, type=int, help='bounding box thickness (pixels)')
+    parser.add_argument('--hide-labels', default=False, action='store_true', help='hide labels')
+    parser.add_argument('--hide-conf', default=False, action='store_true', help='hide confidences')
+    parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')
+    parser.add_argument('--dnn', action='store_true', help='use OpenCV DNN for ONNX inference')
+    parser.add_argument('--vid-stride', type=int, default=1, help='video frame-rate stride')
+    opt = parser.parse_args()
+    opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1  # expand
+    print_args(vars(opt))
+    return opt
+
+
+def main(opt):
+    check_requirements(ROOT / 'requirements.txt', exclude=('tensorboard', 'thop'))
+    run(**vars(opt))
+
+
+if __name__ == '__main__':
+    opt = parse_opt()
+    main(opt)

export.py

@@ -0,0 +1,863 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+"""
+Export a YOLOv5 PyTorch model to other formats. TensorFlow exports authored by https://github.com/zldrobit
+
+Format                      | `export.py --include`         | Model
+---                         | ---                           | ---
+PyTorch                     | -                             | yolov5s.pt
+TorchScript                 | `torchscript`                 | yolov5s.torchscript
+ONNX                        | `onnx`                        | yolov5s.onnx
+OpenVINO                    | `openvino`                    | yolov5s_openvino_model/
+TensorRT                    | `engine`                      | yolov5s.engine
+CoreML                      | `coreml`                      | yolov5s.mlmodel
+TensorFlow SavedModel       | `saved_model`                 | yolov5s_saved_model/
+TensorFlow GraphDef         | `pb`                          | yolov5s.pb
+TensorFlow Lite             | `tflite`                      | yolov5s.tflite
+TensorFlow Edge TPU         | `edgetpu`                     | yolov5s_edgetpu.tflite
+TensorFlow.js               | `tfjs`                        | yolov5s_web_model/
+PaddlePaddle                | `paddle`                      | yolov5s_paddle_model/
+
+Requirements:
+    $ pip install -r requirements.txt coremltools onnx onnx-simplifier onnxruntime openvino-dev tensorflow-cpu  # CPU
+    $ pip install -r requirements.txt coremltools onnx onnx-simplifier onnxruntime-gpu openvino-dev tensorflow  # GPU
+
+Usage:
+    $ python export.py --weights yolov5s.pt --include torchscript onnx openvino engine coreml tflite ...
+
+Inference:
+    $ python detect.py --weights yolov5s.pt                 # PyTorch
+                                 yolov5s.torchscript        # TorchScript
+                                 yolov5s.onnx               # ONNX Runtime or OpenCV DNN with --dnn
+                                 yolov5s_openvino_model     # OpenVINO
+                                 yolov5s.engine             # TensorRT
+                                 yolov5s.mlmodel            # CoreML (macOS-only)
+                                 yolov5s_saved_model        # TensorFlow SavedModel
+                                 yolov5s.pb                 # TensorFlow GraphDef
+                                 yolov5s.tflite             # TensorFlow Lite
+                                 yolov5s_edgetpu.tflite     # TensorFlow Edge TPU
+                                 yolov5s_paddle_model       # PaddlePaddle
+
+TensorFlow.js:
+    $ cd .. && git clone https://github.com/zldrobit/tfjs-yolov5-example.git && cd tfjs-yolov5-example
+    $ npm install
+    $ ln -s ../../yolov5/yolov5s_web_model public/yolov5s_web_model
+    $ npm start
+"""
+
+import argparse
+import contextlib
+import json
+import os
+import platform
+import re
+import subprocess
+import sys
+import time
+import warnings
+from pathlib import Path
+
+import pandas as pd
+import torch
+from torch.utils.mobile_optimizer import optimize_for_mobile
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[0]  # YOLOv5 root directory
+if str(ROOT) not in sys.path:
+    sys.path.append(str(ROOT))  # add ROOT to PATH
+if platform.system() != 'Windows':
+    ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative
+
+from models.experimental import attempt_load
+from models.yolo import ClassificationModel, Detect, DetectionModel, SegmentationModel
+from utils.dataloaders import LoadImages
+from utils.general import (LOGGER, Profile, check_dataset, check_img_size, check_requirements, check_version,
+                           check_yaml, colorstr, file_size, get_default_args, print_args, url2file, yaml_save)
+from utils.torch_utils import select_device, smart_inference_mode
+
+MACOS = platform.system() == 'Darwin'  # macOS environment
+
+
+class iOSModel(torch.nn.Module):
+
+    def __init__(self, model, im):
+        super().__init__()
+        b, c, h, w = im.shape  # batch, channel, height, width
+        self.model = model
+        self.nc = model.nc  # number of classes
+        if w == h:
+            self.normalize = 1. / w
+        else:
+            self.normalize = torch.tensor([1. / w, 1. / h, 1. / w, 1. / h])  # broadcast (slower, smaller)
+            # np = model(im)[0].shape[1]  # number of points
+            # self.normalize = torch.tensor([1. / w, 1. / h, 1. / w, 1. / h]).expand(np, 4)  # explicit (faster, larger)
+
+    def forward(self, x):
+        xywh, conf, cls = self.model(x)[0].squeeze().split((4, 1, self.nc), 1)
+        return cls * conf, xywh * self.normalize  # confidence (3780, 80), coordinates (3780, 4)
+
+
+def export_formats():
+    # YOLOv5 export formats
+    x = [
+        ['PyTorch', '-', '.pt', True, True],
+        ['TorchScript', 'torchscript', '.torchscript', True, True],
+        ['ONNX', 'onnx', '.onnx', True, True],
+        ['OpenVINO', 'openvino', '_openvino_model', True, False],
+        ['TensorRT', 'engine', '.engine', False, True],
+        ['CoreML', 'coreml', '.mlmodel', True, False],
+        ['TensorFlow SavedModel', 'saved_model', '_saved_model', True, True],
+        ['TensorFlow GraphDef', 'pb', '.pb', True, True],
+        ['TensorFlow Lite', 'tflite', '.tflite', True, False],
+        ['TensorFlow Edge TPU', 'edgetpu', '_edgetpu.tflite', False, False],
+        ['TensorFlow.js', 'tfjs', '_web_model', False, False],
+        ['PaddlePaddle', 'paddle', '_paddle_model', True, True], ]
+    return pd.DataFrame(x, columns=['Format', 'Argument', 'Suffix', 'CPU', 'GPU'])
+
+
+def try_export(inner_func):
+    # YOLOv5 export decorator, i..e @try_export
+    inner_args = get_default_args(inner_func)
+
+    def outer_func(*args, **kwargs):
+        prefix = inner_args['prefix']
+        try:
+            with Profile() as dt:
+                f, model = inner_func(*args, **kwargs)
+            LOGGER.info(f'{prefix} export success ✅ {dt.t:.1f}s, saved as {f} ({file_size(f):.1f} MB)')
+            return f, model
+        except Exception as e:
+            LOGGER.info(f'{prefix} export failure ❌ {dt.t:.1f}s: {e}')
+            return None, None
+
+    return outer_func
+
+
+@try_export
+def export_torchscript(model, im, file, optimize, prefix=colorstr('TorchScript:')):
+    # YOLOv5 TorchScript model export
+    LOGGER.info(f'\n{prefix} starting export with torch {torch.__version__}...')
+    f = file.with_suffix('.torchscript')
+
+    ts = torch.jit.trace(model, im, strict=False)
+    d = {'shape': im.shape, 'stride': int(max(model.stride)), 'names': model.names}
+    extra_files = {'config.txt': json.dumps(d)}  # torch._C.ExtraFilesMap()
+    if optimize:  # https://pytorch.org/tutorials/recipes/mobile_interpreter.html
+        optimize_for_mobile(ts)._save_for_lite_interpreter(str(f), _extra_files=extra_files)
+    else:
+        ts.save(str(f), _extra_files=extra_files)
+    return f, None
+
+
+@try_export
+def export_onnx(model, im, file, opset, dynamic, simplify, prefix=colorstr('ONNX:')):
+    # YOLOv5 ONNX export
+    check_requirements('onnx>=1.12.0')
+    import onnx
+
+    LOGGER.info(f'\n{prefix} starting export with onnx {onnx.__version__}...')
+    f = file.with_suffix('.onnx')
+
+    output_names = ['output0', 'output1'] if isinstance(model, SegmentationModel) else ['output0']
+    if dynamic:
+        dynamic = {'images': {0: 'batch', 2: 'height', 3: 'width'}}  # shape(1,3,640,640)
+        if isinstance(model, SegmentationModel):
+            dynamic['output0'] = {0: 'batch', 1: 'anchors'}  # shape(1,25200,85)
+            dynamic['output1'] = {0: 'batch', 2: 'mask_height', 3: 'mask_width'}  # shape(1,32,160,160)
+        elif isinstance(model, DetectionModel):
+            dynamic['output0'] = {0: 'batch', 1: 'anchors'}  # shape(1,25200,85)
+
+    torch.onnx.export(
+        model.cpu() if dynamic else model,  # --dynamic only compatible with cpu
+        im.cpu() if dynamic else im,
+        f,
+        verbose=False,
+        opset_version=opset,
+        do_constant_folding=True,  # WARNING: DNN inference with torch>=1.12 may require do_constant_folding=False
+        input_names=['images'],
+        output_names=output_names,
+        dynamic_axes=dynamic or None)
+
+    # Checks
+    model_onnx = onnx.load(f)  # load onnx model
+    onnx.checker.check_model(model_onnx)  # check onnx model
+
+    # Metadata
+    d = {'stride': int(max(model.stride)), 'names': model.names}
+    for k, v in d.items():
+        meta = model_onnx.metadata_props.add()
+        meta.key, meta.value = k, str(v)
+    onnx.save(model_onnx, f)
+
+    # Simplify
+    if simplify:
+        try:
+            cuda = torch.cuda.is_available()
+            check_requirements(('onnxruntime-gpu' if cuda else 'onnxruntime', 'onnx-simplifier>=0.4.1'))
+            import onnxsim
+
+            LOGGER.info(f'{prefix} simplifying with onnx-simplifier {onnxsim.__version__}...')
+            model_onnx, check = onnxsim.simplify(model_onnx)
+            assert check, 'assert check failed'
+            onnx.save(model_onnx, f)
+        except Exception as e:
+            LOGGER.info(f'{prefix} simplifier failure: {e}')
+    return f, model_onnx
+
+
+@try_export
+def export_openvino(file, metadata, half, int8, data, prefix=colorstr('OpenVINO:')):
+    # YOLOv5 OpenVINO export
+    check_requirements('openvino-dev>=2023.0')  # requires openvino-dev: https://pypi.org/project/openvino-dev/
+    import openvino.runtime as ov  # noqa
+    from openvino.tools import mo  # noqa
+
+    LOGGER.info(f'\n{prefix} starting export with openvino {ov.__version__}...')
+    f = str(file).replace(file.suffix, f'_openvino_model{os.sep}')
+    f_onnx = file.with_suffix('.onnx')
+    f_ov = str(Path(f) / file.with_suffix('.xml').name)
+    if int8:
+        check_requirements('nncf>=2.4.0')  # requires at least version 2.4.0 to use the post-training quantization
+        import nncf
+        import numpy as np
+        from openvino.runtime import Core
+
+        from utils.dataloaders import create_dataloader
+        core = Core()
+        onnx_model = core.read_model(f_onnx)  # export
+
+        def prepare_input_tensor(image: np.ndarray):
+            input_tensor = image.astype(np.float32)  # uint8 to fp16/32
+            input_tensor /= 255.0  # 0 - 255 to 0.0 - 1.0
+
+            if input_tensor.ndim == 3:
+                input_tensor = np.expand_dims(input_tensor, 0)
+            return input_tensor
+
+        def gen_dataloader(yaml_path, task='train', imgsz=640, workers=4):
+            data_yaml = check_yaml(yaml_path)
+            data = check_dataset(data_yaml)
+            dataloader = create_dataloader(data[task],
+                                           imgsz=imgsz,
+                                           batch_size=1,
+                                           stride=32,
+                                           pad=0.5,
+                                           single_cls=False,
+                                           rect=False,
+                                           workers=workers)[0]
+            return dataloader
+
+        # noqa: F811
+
+        def transform_fn(data_item):
+            """
+            Quantization transform function. Extracts and preprocess input data from dataloader item for quantization.
+            Parameters:
+               data_item: Tuple with data item produced by DataLoader during iteration
+            Returns:
+                input_tensor: Input data for quantization
+            """
+            img = data_item[0].numpy()
+            input_tensor = prepare_input_tensor(img)
+            return input_tensor
+
+        ds = gen_dataloader(data)
+        quantization_dataset = nncf.Dataset(ds, transform_fn)
+        ov_model = nncf.quantize(onnx_model, quantization_dataset, preset=nncf.QuantizationPreset.MIXED)
+    else:
+        ov_model = mo.convert_model(f_onnx, model_name=file.stem, framework='onnx', compress_to_fp16=half)  # export
+
+    ov.serialize(ov_model, f_ov)  # save
+    yaml_save(Path(f) / file.with_suffix('.yaml').name, metadata)  # add metadata.yaml
+    return f, None
+
+
+@try_export
+def export_paddle(model, im, file, metadata, prefix=colorstr('PaddlePaddle:')):
+    # YOLOv5 Paddle export
+    check_requirements(('paddlepaddle', 'x2paddle'))
+    import x2paddle
+    from x2paddle.convert import pytorch2paddle
+
+    LOGGER.info(f'\n{prefix} starting export with X2Paddle {x2paddle.__version__}...')
+    f = str(file).replace('.pt', f'_paddle_model{os.sep}')
+
+    pytorch2paddle(module=model, save_dir=f, jit_type='trace', input_examples=[im])  # export
+    yaml_save(Path(f) / file.with_suffix('.yaml').name, metadata)  # add metadata.yaml
+    return f, None
+
+
+@try_export
+def export_coreml(model, im, file, int8, half, nms, prefix=colorstr('CoreML:')):
+    # YOLOv5 CoreML export
+    check_requirements('coremltools')
+    import coremltools as ct
+
+    LOGGER.info(f'\n{prefix} starting export with coremltools {ct.__version__}...')
+    f = file.with_suffix('.mlmodel')
+
+    if nms:
+        model = iOSModel(model, im)
+    ts = torch.jit.trace(model, im, strict=False)  # TorchScript model
+    ct_model = ct.convert(ts, inputs=[ct.ImageType('image', shape=im.shape, scale=1 / 255, bias=[0, 0, 0])])
+    bits, mode = (8, 'kmeans_lut') if int8 else (16, 'linear') if half else (32, None)
+    if bits < 32:
+        if MACOS:  # quantization only supported on macOS
+            with warnings.catch_warnings():
+                warnings.filterwarnings('ignore', category=DeprecationWarning)  # suppress numpy==1.20 float warning
+                ct_model = ct.models.neural_network.quantization_utils.quantize_weights(ct_model, bits, mode)
+        else:
+            print(f'{prefix} quantization only supported on macOS, skipping...')
+    ct_model.save(f)
+    return f, ct_model
+
+
+@try_export
+def export_engine(model, im, file, half, dynamic, simplify, workspace=4, verbose=False, prefix=colorstr('TensorRT:')):
+    # YOLOv5 TensorRT export https://developer.nvidia.com/tensorrt
+    assert im.device.type != 'cpu', 'export running on CPU but must be on GPU, i.e. `python export.py --device 0`'
+    try:
+        import tensorrt as trt
+    except Exception:
+        if platform.system() == 'Linux':
+            check_requirements('nvidia-tensorrt', cmds='-U --index-url https://pypi.ngc.nvidia.com')
+        import tensorrt as trt
+
+    if trt.__version__[0] == '7':  # TensorRT 7 handling https://github.com/ultralytics/yolov5/issues/6012
+        grid = model.model[-1].anchor_grid
+        model.model[-1].anchor_grid = [a[..., :1, :1, :] for a in grid]
+        export_onnx(model, im, file, 12, dynamic, simplify)  # opset 12
+        model.model[-1].anchor_grid = grid
+    else:  # TensorRT >= 8
+        check_version(trt.__version__, '8.0.0', hard=True)  # require tensorrt>=8.0.0
+        export_onnx(model, im, file, 12, dynamic, simplify)  # opset 12
+    onnx = file.with_suffix('.onnx')
+
+    LOGGER.info(f'\n{prefix} starting export with TensorRT {trt.__version__}...')
+    assert onnx.exists(), f'failed to export ONNX file: {onnx}'
+    f = file.with_suffix('.engine')  # TensorRT engine file
+    logger = trt.Logger(trt.Logger.INFO)
+    if verbose:
+        logger.min_severity = trt.Logger.Severity.VERBOSE
+
+    builder = trt.Builder(logger)
+    config = builder.create_builder_config()
+    config.max_workspace_size = workspace * 1 << 30
+    # config.set_memory_pool_limit(trt.MemoryPoolType.WORKSPACE, workspace << 30)  # fix TRT 8.4 deprecation notice
+
+    flag = (1 << int(trt.NetworkDefinitionCreationFlag.EXPLICIT_BATCH))
+    network = builder.create_network(flag)
+    parser = trt.OnnxParser(network, logger)
+    if not parser.parse_from_file(str(onnx)):
+        raise RuntimeError(f'failed to load ONNX file: {onnx}')
+
+    inputs = [network.get_input(i) for i in range(network.num_inputs)]
+    outputs = [network.get_output(i) for i in range(network.num_outputs)]
+    for inp in inputs:
+        LOGGER.info(f'{prefix} input "{inp.name}" with shape{inp.shape} {inp.dtype}')
+    for out in outputs:
+        LOGGER.info(f'{prefix} output "{out.name}" with shape{out.shape} {out.dtype}')
+
+    if dynamic:
+        if im.shape[0] <= 1:
+            LOGGER.warning(f'{prefix} WARNING ⚠️ --dynamic model requires maximum --batch-size argument')
+        profile = builder.create_optimization_profile()
+        for inp in inputs:
+            profile.set_shape(inp.name, (1, *im.shape[1:]), (max(1, im.shape[0] // 2), *im.shape[1:]), im.shape)
+        config.add_optimization_profile(profile)
+
+    LOGGER.info(f'{prefix} building FP{16 if builder.platform_has_fast_fp16 and half else 32} engine as {f}')
+    if builder.platform_has_fast_fp16 and half:
+        config.set_flag(trt.BuilderFlag.FP16)
+    with builder.build_engine(network, config) as engine, open(f, 'wb') as t:
+        t.write(engine.serialize())
+    return f, None
+
+
+@try_export
+def export_saved_model(model,
+                       im,
+                       file,
+                       dynamic,
+                       tf_nms=False,
+                       agnostic_nms=False,
+                       topk_per_class=100,
+                       topk_all=100,
+                       iou_thres=0.45,
+                       conf_thres=0.25,
+                       keras=False,
+                       prefix=colorstr('TensorFlow SavedModel:')):
+    # YOLOv5 TensorFlow SavedModel export
+    try:
+        import tensorflow as tf
+    except Exception:
+        check_requirements(f"tensorflow{'' if torch.cuda.is_available() else '-macos' if MACOS else '-cpu'}")
+        import tensorflow as tf
+    from tensorflow.python.framework.convert_to_constants import convert_variables_to_constants_v2
+
+    from models.tf import TFModel
+
+    LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...')
+    f = str(file).replace('.pt', '_saved_model')
+    batch_size, ch, *imgsz = list(im.shape)  # BCHW
+
+    tf_model = TFModel(cfg=model.yaml, model=model, nc=model.nc, imgsz=imgsz)
+    im = tf.zeros((batch_size, *imgsz, ch))  # BHWC order for TensorFlow
+    _ = tf_model.predict(im, tf_nms, agnostic_nms, topk_per_class, topk_all, iou_thres, conf_thres)
+    inputs = tf.keras.Input(shape=(*imgsz, ch), batch_size=None if dynamic else batch_size)
+    outputs = tf_model.predict(inputs, tf_nms, agnostic_nms, topk_per_class, topk_all, iou_thres, conf_thres)
+    keras_model = tf.keras.Model(inputs=inputs, outputs=outputs)
+    keras_model.trainable = False
+    keras_model.summary()
+    if keras:
+        keras_model.save(f, save_format='tf')
+    else:
+        spec = tf.TensorSpec(keras_model.inputs[0].shape, keras_model.inputs[0].dtype)
+        m = tf.function(lambda x: keras_model(x))  # full model
+        m = m.get_concrete_function(spec)
+        frozen_func = convert_variables_to_constants_v2(m)
+        tfm = tf.Module()
+        tfm.__call__ = tf.function(lambda x: frozen_func(x)[:4] if tf_nms else frozen_func(x), [spec])
+        tfm.__call__(im)
+        tf.saved_model.save(tfm,
+                            f,
+                            options=tf.saved_model.SaveOptions(experimental_custom_gradients=False) if check_version(
+                                tf.__version__, '2.6') else tf.saved_model.SaveOptions())
+    return f, keras_model
+
+
+@try_export
+def export_pb(keras_model, file, prefix=colorstr('TensorFlow GraphDef:')):
+    # YOLOv5 TensorFlow GraphDef *.pb export https://github.com/leimao/Frozen_Graph_TensorFlow
+    import tensorflow as tf
+    from tensorflow.python.framework.convert_to_constants import convert_variables_to_constants_v2
+
+    LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...')
+    f = file.with_suffix('.pb')
+
+    m = tf.function(lambda x: keras_model(x))  # full model
+    m = m.get_concrete_function(tf.TensorSpec(keras_model.inputs[0].shape, keras_model.inputs[0].dtype))
+    frozen_func = convert_variables_to_constants_v2(m)
+    frozen_func.graph.as_graph_def()
+    tf.io.write_graph(graph_or_graph_def=frozen_func.graph, logdir=str(f.parent), name=f.name, as_text=False)
+    return f, None
+
+
+@try_export
+def export_tflite(keras_model, im, file, int8, data, nms, agnostic_nms, prefix=colorstr('TensorFlow Lite:')):
+    # YOLOv5 TensorFlow Lite export
+    import tensorflow as tf
+
+    LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...')
+    batch_size, ch, *imgsz = list(im.shape)  # BCHW
+    f = str(file).replace('.pt', '-fp16.tflite')
+
+    converter = tf.lite.TFLiteConverter.from_keras_model(keras_model)
+    converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS]
+    converter.target_spec.supported_types = [tf.float16]
+    converter.optimizations = [tf.lite.Optimize.DEFAULT]
+    if int8:
+        from models.tf import representative_dataset_gen
+        dataset = LoadImages(check_dataset(check_yaml(data))['train'], img_size=imgsz, auto=False)
+        converter.representative_dataset = lambda: representative_dataset_gen(dataset, ncalib=100)
+        converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS_INT8]
+        converter.target_spec.supported_types = []
+        converter.inference_input_type = tf.uint8  # or tf.int8
+        converter.inference_output_type = tf.uint8  # or tf.int8
+        converter.experimental_new_quantizer = True
+        f = str(file).replace('.pt', '-int8.tflite')
+    if nms or agnostic_nms:
+        converter.target_spec.supported_ops.append(tf.lite.OpsSet.SELECT_TF_OPS)
+
+    tflite_model = converter.convert()
+    open(f, 'wb').write(tflite_model)
+    return f, None
+
+
+@try_export
+def export_edgetpu(file, prefix=colorstr('Edge TPU:')):
+    # YOLOv5 Edge TPU export https://coral.ai/docs/edgetpu/models-intro/
+    cmd = 'edgetpu_compiler --version'
+    help_url = 'https://coral.ai/docs/edgetpu/compiler/'
+    assert platform.system() == 'Linux', f'export only supported on Linux. See {help_url}'
+    if subprocess.run(f'{cmd} > /dev/null 2>&1', shell=True).returncode != 0:
+        LOGGER.info(f'\n{prefix} export requires Edge TPU compiler. Attempting install from {help_url}')
+        sudo = subprocess.run('sudo --version >/dev/null', shell=True).returncode == 0  # sudo installed on system
+        for c in (
+                'curl https://packages.cloud.google.com/apt/doc/apt-key.gpg | sudo apt-key add -',
+                'echo "deb https://packages.cloud.google.com/apt coral-edgetpu-stable main" | sudo tee /etc/apt/sources.list.d/coral-edgetpu.list',
+                'sudo apt-get update', 'sudo apt-get install edgetpu-compiler'):
+            subprocess.run(c if sudo else c.replace('sudo ', ''), shell=True, check=True)
+    ver = subprocess.run(cmd, shell=True, capture_output=True, check=True).stdout.decode().split()[-1]
+
+    LOGGER.info(f'\n{prefix} starting export with Edge TPU compiler {ver}...')
+    f = str(file).replace('.pt', '-int8_edgetpu.tflite')  # Edge TPU model
+    f_tfl = str(file).replace('.pt', '-int8.tflite')  # TFLite model
+
+    subprocess.run([
+        'edgetpu_compiler',
+        '-s',
+        '-d',
+        '-k',
+        '10',
+        '--out_dir',
+        str(file.parent),
+        f_tfl, ], check=True)
+    return f, None
+
+
+@try_export
+def export_tfjs(file, int8, prefix=colorstr('TensorFlow.js:')):
+    # YOLOv5 TensorFlow.js export
+    check_requirements('tensorflowjs')
+    import tensorflowjs as tfjs
+
+    LOGGER.info(f'\n{prefix} starting export with tensorflowjs {tfjs.__version__}...')
+    f = str(file).replace('.pt', '_web_model')  # js dir
+    f_pb = file.with_suffix('.pb')  # *.pb path
+    f_json = f'{f}/model.json'  # *.json path
+
+    args = [
+        'tensorflowjs_converter',
+        '--input_format=tf_frozen_model',
+        '--quantize_uint8' if int8 else '',
+        '--output_node_names=Identity,Identity_1,Identity_2,Identity_3',
+        str(f_pb),
+        str(f), ]
+    subprocess.run([arg for arg in args if arg], check=True)
+
+    json = Path(f_json).read_text()
+    with open(f_json, 'w') as j:  # sort JSON Identity_* in ascending order
+        subst = re.sub(
+            r'{"outputs": {"Identity.?.?": {"name": "Identity.?.?"}, '
+            r'"Identity.?.?": {"name": "Identity.?.?"}, '
+            r'"Identity.?.?": {"name": "Identity.?.?"}, '
+            r'"Identity.?.?": {"name": "Identity.?.?"}}}', r'{"outputs": {"Identity": {"name": "Identity"}, '
+            r'"Identity_1": {"name": "Identity_1"}, '
+            r'"Identity_2": {"name": "Identity_2"}, '
+            r'"Identity_3": {"name": "Identity_3"}}}', json)
+        j.write(subst)
+    return f, None
+
+
+def add_tflite_metadata(file, metadata, num_outputs):
+    # Add metadata to *.tflite models per https://www.tensorflow.org/lite/models/convert/metadata
+    with contextlib.suppress(ImportError):
+        # check_requirements('tflite_support')
+        from tflite_support import flatbuffers
+        from tflite_support import metadata as _metadata
+        from tflite_support import metadata_schema_py_generated as _metadata_fb
+
+        tmp_file = Path('/tmp/meta.txt')
+        with open(tmp_file, 'w') as meta_f:
+            meta_f.write(str(metadata))
+
+        model_meta = _metadata_fb.ModelMetadataT()
+        label_file = _metadata_fb.AssociatedFileT()
+        label_file.name = tmp_file.name
+        model_meta.associatedFiles = [label_file]
+
+        subgraph = _metadata_fb.SubGraphMetadataT()
+        subgraph.inputTensorMetadata = [_metadata_fb.TensorMetadataT()]
+        subgraph.outputTensorMetadata = [_metadata_fb.TensorMetadataT()] * num_outputs
+        model_meta.subgraphMetadata = [subgraph]
+
+        b = flatbuffers.Builder(0)
+        b.Finish(model_meta.Pack(b), _metadata.MetadataPopulator.METADATA_FILE_IDENTIFIER)
+        metadata_buf = b.Output()
+
+        populator = _metadata.MetadataPopulator.with_model_file(file)
+        populator.load_metadata_buffer(metadata_buf)
+        populator.load_associated_files([str(tmp_file)])
+        populator.populate()
+        tmp_file.unlink()
+
+
+def pipeline_coreml(model, im, file, names, y, prefix=colorstr('CoreML Pipeline:')):
+    # YOLOv5 CoreML pipeline
+    import coremltools as ct
+    from PIL import Image
+
+    print(f'{prefix} starting pipeline with coremltools {ct.__version__}...')
+    batch_size, ch, h, w = list(im.shape)  # BCHW
+    t = time.time()
+
+    # YOLOv5 Output shapes
+    spec = model.get_spec()
+    out0, out1 = iter(spec.description.output)
+    if platform.system() == 'Darwin':
+        img = Image.new('RGB', (w, h))  # img(192 width, 320 height)
+        # img = torch.zeros((*opt.img_size, 3)).numpy()  # img size(320,192,3) iDetection
+        out = model.predict({'image': img})
+        out0_shape, out1_shape = out[out0.name].shape, out[out1.name].shape
+    else:  # linux and windows can not run model.predict(), get sizes from pytorch output y
+        s = tuple(y[0].shape)
+        out0_shape, out1_shape = (s[1], s[2] - 5), (s[1], 4)  # (3780, 80), (3780, 4)
+
+    # Checks
+    nx, ny = spec.description.input[0].type.imageType.width, spec.description.input[0].type.imageType.height
+    na, nc = out0_shape
+    # na, nc = out0.type.multiArrayType.shape  # number anchors, classes
+    assert len(names) == nc, f'{len(names)} names found for nc={nc}'  # check
+
+    # Define output shapes (missing)
+    out0.type.multiArrayType.shape[:] = out0_shape  # (3780, 80)
+    out1.type.multiArrayType.shape[:] = out1_shape  # (3780, 4)
+    # spec.neuralNetwork.preprocessing[0].featureName = '0'
+
+    # Flexible input shapes
+    # from coremltools.models.neural_network import flexible_shape_utils
+    # s = [] # shapes
+    # s.append(flexible_shape_utils.NeuralNetworkImageSize(320, 192))
+    # s.append(flexible_shape_utils.NeuralNetworkImageSize(640, 384))  # (height, width)
+    # flexible_shape_utils.add_enumerated_image_sizes(spec, feature_name='image', sizes=s)
+    # r = flexible_shape_utils.NeuralNetworkImageSizeRange()  # shape ranges
+    # r.add_height_range((192, 640))
+    # r.add_width_range((192, 640))
+    # flexible_shape_utils.update_image_size_range(spec, feature_name='image', size_range=r)
+
+    # Print
+    print(spec.description)
+
+    # Model from spec
+    model = ct.models.MLModel(spec)
+
+    # 3. Create NMS protobuf
+    nms_spec = ct.proto.Model_pb2.Model()
+    nms_spec.specificationVersion = 5
+    for i in range(2):
+        decoder_output = model._spec.description.output[i].SerializeToString()
+        nms_spec.description.input.add()
+        nms_spec.description.input[i].ParseFromString(decoder_output)
+        nms_spec.description.output.add()
+        nms_spec.description.output[i].ParseFromString(decoder_output)
+
+    nms_spec.description.output[0].name = 'confidence'
+    nms_spec.description.output[1].name = 'coordinates'
+
+    output_sizes = [nc, 4]
+    for i in range(2):
+        ma_type = nms_spec.description.output[i].type.multiArrayType
+        ma_type.shapeRange.sizeRanges.add()
+        ma_type.shapeRange.sizeRanges[0].lowerBound = 0
+        ma_type.shapeRange.sizeRanges[0].upperBound = -1
+        ma_type.shapeRange.sizeRanges.add()
+        ma_type.shapeRange.sizeRanges[1].lowerBound = output_sizes[i]
+        ma_type.shapeRange.sizeRanges[1].upperBound = output_sizes[i]
+        del ma_type.shape[:]
+
+    nms = nms_spec.nonMaximumSuppression
+    nms.confidenceInputFeatureName = out0.name  # 1x507x80
+    nms.coordinatesInputFeatureName = out1.name  # 1x507x4
+    nms.confidenceOutputFeatureName = 'confidence'
+    nms.coordinatesOutputFeatureName = 'coordinates'
+    nms.iouThresholdInputFeatureName = 'iouThreshold'
+    nms.confidenceThresholdInputFeatureName = 'confidenceThreshold'
+    nms.iouThreshold = 0.45
+    nms.confidenceThreshold = 0.25
+    nms.pickTop.perClass = True
+    nms.stringClassLabels.vector.extend(names.values())
+    nms_model = ct.models.MLModel(nms_spec)
+
+    # 4. Pipeline models together
+    pipeline = ct.models.pipeline.Pipeline(input_features=[('image', ct.models.datatypes.Array(3, ny, nx)),
+                                                           ('iouThreshold', ct.models.datatypes.Double()),
+                                                           ('confidenceThreshold', ct.models.datatypes.Double())],
+                                           output_features=['confidence', 'coordinates'])
+    pipeline.add_model(model)
+    pipeline.add_model(nms_model)
+
+    # Correct datatypes
+    pipeline.spec.description.input[0].ParseFromString(model._spec.description.input[0].SerializeToString())
+    pipeline.spec.description.output[0].ParseFromString(nms_model._spec.description.output[0].SerializeToString())
+    pipeline.spec.description.output[1].ParseFromString(nms_model._spec.description.output[1].SerializeToString())
+
+    # Update metadata
+    pipeline.spec.specificationVersion = 5
+    pipeline.spec.description.metadata.versionString = 'https://github.com/ultralytics/yolov5'
+    pipeline.spec.description.metadata.shortDescription = 'https://github.com/ultralytics/yolov5'
+    pipeline.spec.description.metadata.author = 'glenn.jocher@ultralytics.com'
+    pipeline.spec.description.metadata.license = 'https://github.com/ultralytics/yolov5/blob/master/LICENSE'
+    pipeline.spec.description.metadata.userDefined.update({
+        'classes': ','.join(names.values()),
+        'iou_threshold': str(nms.iouThreshold),
+        'confidence_threshold': str(nms.confidenceThreshold)})
+
+    # Save the model
+    f = file.with_suffix('.mlmodel')  # filename
+    model = ct.models.MLModel(pipeline.spec)
+    model.input_description['image'] = 'Input image'
+    model.input_description['iouThreshold'] = f'(optional) IOU Threshold override (default: {nms.iouThreshold})'
+    model.input_description['confidenceThreshold'] = \
+        f'(optional) Confidence Threshold override (default: {nms.confidenceThreshold})'
+    model.output_description['confidence'] = 'Boxes × Class confidence (see user-defined metadata "classes")'
+    model.output_description['coordinates'] = 'Boxes × [x, y, width, height] (relative to image size)'
+    model.save(f)  # pipelined
+    print(f'{prefix} pipeline success ({time.time() - t:.2f}s), saved as {f} ({file_size(f):.1f} MB)')
+
+
+@smart_inference_mode()
+def run(
+        data=ROOT / 'data/coco128.yaml',  # 'dataset.yaml path'
+        weights=ROOT / 'yolov5s.pt',  # weights path
+        imgsz=(640, 640),  # image (height, width)
+        batch_size=1,  # batch size
+        device='cpu',  # cuda device, i.e. 0 or 0,1,2,3 or cpu
+        include=('torchscript', 'onnx'),  # include formats
+        half=False,  # FP16 half-precision export
+        inplace=False,  # set YOLOv5 Detect() inplace=True
+        keras=False,  # use Keras
+        optimize=False,  # TorchScript: optimize for mobile
+        int8=False,  # CoreML/TF INT8 quantization
+        dynamic=False,  # ONNX/TF/TensorRT: dynamic axes
+        simplify=False,  # ONNX: simplify model
+        opset=12,  # ONNX: opset version
+        verbose=False,  # TensorRT: verbose log
+        workspace=4,  # TensorRT: workspace size (GB)
+        nms=False,  # TF: add NMS to model
+        agnostic_nms=False,  # TF: add agnostic NMS to model
+        topk_per_class=100,  # TF.js NMS: topk per class to keep
+        topk_all=100,  # TF.js NMS: topk for all classes to keep
+        iou_thres=0.45,  # TF.js NMS: IoU threshold
+        conf_thres=0.25,  # TF.js NMS: confidence threshold
+):
+    t = time.time()
+    include = [x.lower() for x in include]  # to lowercase
+    fmts = tuple(export_formats()['Argument'][1:])  # --include arguments
+    flags = [x in include for x in fmts]
+    assert sum(flags) == len(include), f'ERROR: Invalid --include {include}, valid --include arguments are {fmts}'
+    jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, paddle = flags  # export booleans
+    file = Path(url2file(weights) if str(weights).startswith(('http:/', 'https:/')) else weights)  # PyTorch weights
+
+    # Load PyTorch model
+    device = select_device(device)
+    if half:
+        assert device.type != 'cpu' or coreml, '--half only compatible with GPU export, i.e. use --device 0'
+        assert not dynamic, '--half not compatible with --dynamic, i.e. use either --half or --dynamic but not both'
+    model = attempt_load(weights, device=device, inplace=True, fuse=True)  # load FP32 model
+
+    # Checks
+    imgsz *= 2 if len(imgsz) == 1 else 1  # expand
+    if optimize:
+        assert device.type == 'cpu', '--optimize not compatible with cuda devices, i.e. use --device cpu'
+
+    # Input
+    gs = int(max(model.stride))  # grid size (max stride)
+    imgsz = [check_img_size(x, gs) for x in imgsz]  # verify img_size are gs-multiples
+    im = torch.zeros(batch_size, 3, *imgsz).to(device)  # image size(1,3,320,192) BCHW iDetection
+
+    # Update model
+    model.eval()
+    for k, m in model.named_modules():
+        if isinstance(m, Detect):
+            m.inplace = inplace
+            m.dynamic = dynamic
+            m.export = True
+
+    for _ in range(2):
+        y = model(im)  # dry runs
+    if half and not coreml:
+        im, model = im.half(), model.half()  # to FP16
+    shape = tuple((y[0] if isinstance(y, tuple) else y).shape)  # model output shape
+    metadata = {'stride': int(max(model.stride)), 'names': model.names}  # model metadata
+    LOGGER.info(f"\n{colorstr('PyTorch:')} starting from {file} with output shape {shape} ({file_size(file):.1f} MB)")
+
+    # Exports
+    f = [''] * len(fmts)  # exported filenames
+    warnings.filterwarnings(action='ignore', category=torch.jit.TracerWarning)  # suppress TracerWarning
+    if jit:  # TorchScript
+        f[0], _ = export_torchscript(model, im, file, optimize)
+    if engine:  # TensorRT required before ONNX
+        f[1], _ = export_engine(model, im, file, half, dynamic, simplify, workspace, verbose)
+    if onnx or xml:  # OpenVINO requires ONNX
+        f[2], _ = export_onnx(model, im, file, opset, dynamic, simplify)
+    if xml:  # OpenVINO
+        f[3], _ = export_openvino(file, metadata, half, int8, data)
+    if coreml:  # CoreML
+        f[4], ct_model = export_coreml(model, im, file, int8, half, nms)
+        if nms:
+            pipeline_coreml(ct_model, im, file, model.names, y)
+    if any((saved_model, pb, tflite, edgetpu, tfjs)):  # TensorFlow formats
+        assert not tflite or not tfjs, 'TFLite and TF.js models must be exported separately, please pass only one type.'
+        assert not isinstance(model, ClassificationModel), 'ClassificationModel export to TF formats not yet supported.'
+        f[5], s_model = export_saved_model(model.cpu(),
+                                           im,
+                                           file,
+                                           dynamic,
+                                           tf_nms=nms or agnostic_nms or tfjs,
+                                           agnostic_nms=agnostic_nms or tfjs,
+                                           topk_per_class=topk_per_class,
+                                           topk_all=topk_all,
+                                           iou_thres=iou_thres,
+                                           conf_thres=conf_thres,
+                                           keras=keras)
+        if pb or tfjs:  # pb prerequisite to tfjs
+            f[6], _ = export_pb(s_model, file)
+        if tflite or edgetpu:
+            f[7], _ = export_tflite(s_model, im, file, int8 or edgetpu, data=data, nms=nms, agnostic_nms=agnostic_nms)
+            if edgetpu:
+                f[8], _ = export_edgetpu(file)
+            add_tflite_metadata(f[8] or f[7], metadata, num_outputs=len(s_model.outputs))
+        if tfjs:
+            f[9], _ = export_tfjs(file, int8)
+    if paddle:  # PaddlePaddle
+        f[10], _ = export_paddle(model, im, file, metadata)
+
+    # Finish
+    f = [str(x) for x in f if x]  # filter out '' and None
+    if any(f):
+        cls, det, seg = (isinstance(model, x) for x in (ClassificationModel, DetectionModel, SegmentationModel))  # type
+        det &= not seg  # segmentation models inherit from SegmentationModel(DetectionModel)
+        dir = Path('segment' if seg else 'classify' if cls else '')
+        h = '--half' if half else ''  # --half FP16 inference arg
+        s = '# WARNING ⚠️ ClassificationModel not yet supported for PyTorch Hub AutoShape inference' if cls else \
+            '# WARNING ⚠️ SegmentationModel not yet supported for PyTorch Hub AutoShape inference' if seg else ''
+        LOGGER.info(f'\nExport complete ({time.time() - t:.1f}s)'
+                    f"\nResults saved to {colorstr('bold', file.parent.resolve())}"
+                    f"\nDetect:          python {dir / ('detect.py' if det else 'predict.py')} --weights {f[-1]} {h}"
+                    f"\nValidate:        python {dir / 'val.py'} --weights {f[-1]} {h}"
+                    f"\nPyTorch Hub:     model = torch.hub.load('ultralytics/yolov5', 'custom', '{f[-1]}')  {s}"
+                    f'\nVisualize:       https://netron.app')
+    return f  # return list of exported files/dirs
+
+
+def parse_opt(known=False):
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='dataset.yaml path')
+    parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'yolov5s.pt', help='model.pt path(s)')
+    parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640, 640], help='image (h, w)')
+    parser.add_argument('--batch-size', type=int, default=1, help='batch size')
+    parser.add_argument('--device', default='cpu', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    parser.add_argument('--half', action='store_true', help='FP16 half-precision export')
+    parser.add_argument('--inplace', action='store_true', help='set YOLOv5 Detect() inplace=True')
+    parser.add_argument('--keras', action='store_true', help='TF: use Keras')
+    parser.add_argument('--optimize', action='store_true', help='TorchScript: optimize for mobile')
+    parser.add_argument('--int8', action='store_true', help='CoreML/TF/OpenVINO INT8 quantization')
+    parser.add_argument('--dynamic', action='store_true', help='ONNX/TF/TensorRT: dynamic axes')
+    parser.add_argument('--simplify', action='store_true', help='ONNX: simplify model')
+    parser.add_argument('--opset', type=int, default=17, help='ONNX: opset version')
+    parser.add_argument('--verbose', action='store_true', help='TensorRT: verbose log')
+    parser.add_argument('--workspace', type=int, default=4, help='TensorRT: workspace size (GB)')
+    parser.add_argument('--nms', action='store_true', help='TF: add NMS to model')
+    parser.add_argument('--agnostic-nms', action='store_true', help='TF: add agnostic NMS to model')
+    parser.add_argument('--topk-per-class', type=int, default=100, help='TF.js NMS: topk per class to keep')
+    parser.add_argument('--topk-all', type=int, default=100, help='TF.js NMS: topk for all classes to keep')
+    parser.add_argument('--iou-thres', type=float, default=0.45, help='TF.js NMS: IoU threshold')
+    parser.add_argument('--conf-thres', type=float, default=0.25, help='TF.js NMS: confidence threshold')
+    parser.add_argument(
+        '--include',
+        nargs='+',
+        default=['torchscript'],
+        help='torchscript, onnx, openvino, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, paddle')
+    opt = parser.parse_known_args()[0] if known else parser.parse_args()
+    print_args(vars(opt))
+    return opt
+
+
+def main(opt):
+    for opt.weights in (opt.weights if isinstance(opt.weights, list) else [opt.weights]):
+        run(**vars(opt))
+
+
+if __name__ == '__main__':
+    opt = parse_opt()
+    main(opt)

hands/hand_inference.py

@@ -0,0 +1,107 @@
+import cv2
+import os
+import numpy as np
+import mediapipe as mp
+
+class hand_pose:
+    def __init__(self, min_dc=0.45, min_tc=0.45, max_nh=1):
+        self.mp_drawing = mp.solutions.drawing_utils
+        self.mp_hands = mp.solutions.hands
+        self.hands = self.mp_hands.Hands(
+            static_image_mode=False,
+            max_num_hands=max_nh,
+            min_detection_confidence=min_dc,
+            min_tracking_confidence=min_tc
+        )
+
+    @staticmethod
+    def img_show(img):
+        cv2.imshow('MediaPipe Hands', img)
+        cv2.waitKey(1)
+
+    def draw(self, img):
+        hand_locals = []
+        h_re = self.hands.process(img)
+        if h_re.multi_hand_landmarks:
+            
+            for hand in h_re.multi_handedness:
+                hand_position = 'Left' if hand.classification[0].label == "Left" else 'Right'
+            
+            hand_local = []
+            for hand_landmarks in h_re.multi_hand_landmarks:
+                self.mp_drawing.draw_landmarks(img,
+                                               hand_landmarks,
+                                               self.mp_hands.HAND_CONNECTIONS)
+                imgshow = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
+                # self.img_show(imgshow)
+                cv2.imwrite(f"./images/{k}.png", imgshow)
+
+                '''获取手部关键点坐标'''
+                for i in range(21):
+                    x = hand_landmarks.landmark[i].x * img.shape[1]
+                    y = hand_landmarks.landmark[i].y * img.shape[0]
+                    hand_local.append((x, y))
+            
+            hand_locals.append(hand_local)
+        return hand_locals
+    
+    def get_hand_local(self, track, image):
+        '''tracks: [x1, y1, x2, y2, track_id, score, cls, frame_index, box_index]'''
+        H, W, _ = np.shape(image)
+        tlbr = track[:4].astype(np.int_)
+        x1 = max(0, tlbr[0]-50)
+        y1 = max(0, tlbr[1]-50)
+        x2 = min(W - 1, tlbr[2]+50)
+        y2 = min(H - 1, tlbr[3]+50)
+        img = image[y1:y2, x1:x2, :]
+        imgshow = img.copy()
+        
+        # hand_local = np.empty((0,2), dtype = np.int_)
+        min_x, max_x = W-1, 0
+        min_y, max_y = H-1, 0
+        
+        img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+        h_re = self.hands.process(img)
+        if h_re.multi_hand_landmarks:
+            for hand_landmarks in h_re.multi_hand_landmarks:
+                for i in range(21):
+                    x = hand_landmarks.landmark[i].x * img.shape[1]
+                    y = hand_landmarks.landmark[i].y * img.shape[0]
+                    # hand_local = np.concatenate([hand_local, np.array([[x1+x, y1+y]]).astype(np.int_)], axis=0)
+                    
+                    if min_x>x1+x: min_x=x1+x
+                    if max_x<x1+x: max_x=x1+x
+                    if min_y>y1+y: min_y=y1+y
+                    if max_y<y1+y: max_y=y1+y
+                    
+                    
+                self.mp_drawing.draw_landmarks(img, hand_landmarks, self.mp_hands.HAND_CONNECTIONS)
+                imgshow = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
+        if min_x < max_x and min_y < max_y:
+            hand_local = (min_x, min_y, max_x, max_y)
+        else:
+            hand_local = None       
+        
+        return hand_local, imgshow
+    
+    
+    
+
+if __name__ == "__main__":
+    handpose = hand_pose()
+    file = r"D:\datasets\ym\videos\标记视频\加购_双手放入_1.mp4"
+    cap = cv2.VideoCapture(file)
+    k = 0
+    while cap.isOpened():
+        ret, frame = cap.read()
+        if ret is False:
+            break
+        frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+        hand_local = handpose.draw(frame)
+        k += 1
+    
+    cap.release()
+    # cv2.destroyAllWindows()
+        
+        
+        

hands/hand_inference_origin.py

@@ -0,0 +1,44 @@
+import cv2
+import os
+import mediapipe as mp
+
+class hand_pose:
+    def __init__(self, min_dc=0.45, min_tc=0.45, max_nh=1):
+        self.mp_drawing = mp.solutions.drawing_utils
+        self.mp_hands = mp.solutions.hands
+        self.hands = self.mp_hands.Hands(
+            static_image_mode=False,
+            max_num_hands=max_nh,
+            min_detection_confidence=min_dc,
+            min_tracking_confidence=min_tc
+        )
+
+    @staticmethod
+    def img_show(img):
+        cv2.imshow('MediaPipe Hands', img)
+        cv2.waitKey(1)
+
+    def draw(self, img):
+        hand_local = []
+        h_re = self.hands.process(img)
+        if h_re.multi_hand_landmarks:
+            for hand_landmarks in h_re.multi_hand_landmarks:
+                self.mp_drawing.draw_landmarks(img,
+                                               hand_landmarks,
+                                               self.mp_hands.HAND_CONNECTIONS)
+                self.img_show(img)
+
+            '''获取手部关键点坐标'''
+            for i in range(21):
+                x = hand_landmarks.landmark[i].x * img.shape[1]
+                y = hand_landmarks.landmark[i].y * img.shape[0]
+                hand_local.append((x, y))
+        return hand_local
+
+if __name__ == "__main__":
+    handpose = hand_pose()
+    cap = cv2.VideoCapture(0)
+    while True:
+        ret, frame = cap.read()
+        frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+        handpose.draw(frame)

models/common.py

@@ -0,0 +1,883 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+"""
+Common modules
+"""
+
+import ast
+import contextlib
+import json
+import math
+import platform
+import warnings
+import zipfile
+from collections import OrderedDict, namedtuple
+from copy import copy
+from pathlib import Path
+from urllib.parse import urlparse
+
+import cv2
+import numpy as np
+import pandas as pd
+import requests
+import torch
+import torch.nn as nn
+from PIL import Image
+from torch.cuda import amp
+
+# Import 'ultralytics' package or install if if missing
+try:
+    import ultralytics
+
+    assert hasattr(ultralytics, '__version__')  # verify package is not directory
+except (ImportError, AssertionError):
+    import os
+
+    os.system('pip install -U ultralytics')
+    import ultralytics
+
+from ultralytics.utils.plotting import Annotator, colors, save_one_box
+
+from utils import TryExcept
+from utils.dataloaders import exif_transpose, letterbox
+from utils.general import (LOGGER, ROOT, Profile, check_requirements, check_suffix, check_version, colorstr,
+                           increment_path, is_jupyter, make_divisible, non_max_suppression, scale_boxes, xywh2xyxy,
+                           xyxy2xywh, yaml_load)
+from utils.torch_utils import copy_attr, smart_inference_mode
+
+
+def autopad(k, p=None, d=1):  # kernel, padding, dilation
+    # Pad to 'same' shape outputs
+    if d > 1:
+        k = d * (k - 1) + 1 if isinstance(k, int) else [d * (x - 1) + 1 for x in k]  # actual kernel-size
+    if p is None:
+        p = k // 2 if isinstance(k, int) else [x // 2 for x in k]  # auto-pad
+    return p
+
+
+class Conv(nn.Module):
+    # Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation)
+    default_act = nn.SiLU()  # default activation
+
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True):
+        super().__init__()
+        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p, d), groups=g, dilation=d, bias=False)
+        self.bn = nn.BatchNorm2d(c2)
+        self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()
+
+    def forward(self, x):
+        return self.act(self.bn(self.conv(x)))
+
+    def forward_fuse(self, x):
+        return self.act(self.conv(x))
+
+
+class DWConv(Conv):
+    # Depth-wise convolution
+    def __init__(self, c1, c2, k=1, s=1, d=1, act=True):  # ch_in, ch_out, kernel, stride, dilation, activation
+        super().__init__(c1, c2, k, s, g=math.gcd(c1, c2), d=d, act=act)
+
+
+class DWConvTranspose2d(nn.ConvTranspose2d):
+    # Depth-wise transpose convolution
+    def __init__(self, c1, c2, k=1, s=1, p1=0, p2=0):  # ch_in, ch_out, kernel, stride, padding, padding_out
+        super().__init__(c1, c2, k, s, p1, p2, groups=math.gcd(c1, c2))
+
+
+class TransformerLayer(nn.Module):
+    # Transformer layer https://arxiv.org/abs/2010.11929 (LayerNorm layers removed for better performance)
+    def __init__(self, c, num_heads):
+        super().__init__()
+        self.q = nn.Linear(c, c, bias=False)
+        self.k = nn.Linear(c, c, bias=False)
+        self.v = nn.Linear(c, c, bias=False)
+        self.ma = nn.MultiheadAttention(embed_dim=c, num_heads=num_heads)
+        self.fc1 = nn.Linear(c, c, bias=False)
+        self.fc2 = nn.Linear(c, c, bias=False)
+
+    def forward(self, x):
+        x = self.ma(self.q(x), self.k(x), self.v(x))[0] + x
+        x = self.fc2(self.fc1(x)) + x
+        return x
+
+
+class TransformerBlock(nn.Module):
+    # Vision Transformer https://arxiv.org/abs/2010.11929
+    def __init__(self, c1, c2, num_heads, num_layers):
+        super().__init__()
+        self.conv = None
+        if c1 != c2:
+            self.conv = Conv(c1, c2)
+        self.linear = nn.Linear(c2, c2)  # learnable position embedding
+        self.tr = nn.Sequential(*(TransformerLayer(c2, num_heads) for _ in range(num_layers)))
+        self.c2 = c2
+
+    def forward(self, x):
+        if self.conv is not None:
+            x = self.conv(x)
+        b, _, w, h = x.shape
+        p = x.flatten(2).permute(2, 0, 1)
+        return self.tr(p + self.linear(p)).permute(1, 2, 0).reshape(b, self.c2, w, h)
+
+
+class Bottleneck(nn.Module):
+    # Standard bottleneck
+    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, shortcut, groups, expansion
+        super().__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c_, c2, 3, 1, g=g)
+        self.add = shortcut and c1 == c2
+
+    def forward(self, x):
+        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
+
+
+class BottleneckCSP(nn.Module):
+    # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = nn.Conv2d(c1, c_, 1, 1, bias=False)
+        self.cv3 = nn.Conv2d(c_, c_, 1, 1, bias=False)
+        self.cv4 = Conv(2 * c_, c2, 1, 1)
+        self.bn = nn.BatchNorm2d(2 * c_)  # applied to cat(cv2, cv3)
+        self.act = nn.SiLU()
+        self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))
+
+    def forward(self, x):
+        y1 = self.cv3(self.m(self.cv1(x)))
+        y2 = self.cv2(x)
+        return self.cv4(self.act(self.bn(torch.cat((y1, y2), 1))))
+
+
+class CrossConv(nn.Module):
+    # Cross Convolution Downsample
+    def __init__(self, c1, c2, k=3, s=1, g=1, e=1.0, shortcut=False):
+        # ch_in, ch_out, kernel, stride, groups, expansion, shortcut
+        super().__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, (1, k), (1, s))
+        self.cv2 = Conv(c_, c2, (k, 1), (s, 1), g=g)
+        self.add = shortcut and c1 == c2
+
+    def forward(self, x):
+        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
+
+
+class C3(nn.Module):
+    # CSP Bottleneck with 3 convolutions
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c1, c_, 1, 1)
+        self.cv3 = Conv(2 * c_, c2, 1)  # optional act=FReLU(c2)
+        self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))
+
+    def forward(self, x):
+        return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1))
+
+
+class C3x(C3):
+    # C3 module with cross-convolutions
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2 * e)
+        self.m = nn.Sequential(*(CrossConv(c_, c_, 3, 1, g, 1.0, shortcut) for _ in range(n)))
+
+
+class C3TR(C3):
+    # C3 module with TransformerBlock()
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2 * e)
+        self.m = TransformerBlock(c_, c_, 4, n)
+
+
+class C3SPP(C3):
+    # C3 module with SPP()
+    def __init__(self, c1, c2, k=(5, 9, 13), n=1, shortcut=True, g=1, e=0.5):
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2 * e)
+        self.m = SPP(c_, c_, k)
+
+
+class C3Ghost(C3):
+    # C3 module with GhostBottleneck()
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2 * e)  # hidden channels
+        self.m = nn.Sequential(*(GhostBottleneck(c_, c_) for _ in range(n)))
+
+
+class SPP(nn.Module):
+    # Spatial Pyramid Pooling (SPP) layer https://arxiv.org/abs/1406.4729
+    def __init__(self, c1, c2, k=(5, 9, 13)):
+        super().__init__()
+        c_ = c1 // 2  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c_ * (len(k) + 1), c2, 1, 1)
+        self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])
+
+    def forward(self, x):
+        x = self.cv1(x)
+        with warnings.catch_warnings():
+            warnings.simplefilter('ignore')  # suppress torch 1.9.0 max_pool2d() warning
+            return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1))
+
+
+class SPPF(nn.Module):
+    # Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher
+    def __init__(self, c1, c2, k=5):  # equivalent to SPP(k=(5, 9, 13))
+        super().__init__()
+        c_ = c1 // 2  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c_ * 4, c2, 1, 1)
+        self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)
+
+    def forward(self, x):
+        x = self.cv1(x)
+        with warnings.catch_warnings():
+            warnings.simplefilter('ignore')  # suppress torch 1.9.0 max_pool2d() warning
+            y1 = self.m(x)
+            y2 = self.m(y1)
+            return self.cv2(torch.cat((x, y1, y2, self.m(y2)), 1))
+
+
+class Focus(nn.Module):
+    # Focus wh information into c-space
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
+        super().__init__()
+        self.conv = Conv(c1 * 4, c2, k, s, p, g, act=act)
+        # self.contract = Contract(gain=2)
+
+    def forward(self, x):  # x(b,c,w,h) -> y(b,4c,w/2,h/2)
+        return self.conv(torch.cat((x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]), 1))
+        # return self.conv(self.contract(x))
+
+
+class GhostConv(nn.Module):
+    # Ghost Convolution https://github.com/huawei-noah/ghostnet
+    def __init__(self, c1, c2, k=1, s=1, g=1, act=True):  # ch_in, ch_out, kernel, stride, groups
+        super().__init__()
+        c_ = c2 // 2  # hidden channels
+        self.cv1 = Conv(c1, c_, k, s, None, g, act=act)
+        self.cv2 = Conv(c_, c_, 5, 1, None, c_, act=act)
+
+    def forward(self, x):
+        y = self.cv1(x)
+        return torch.cat((y, self.cv2(y)), 1)
+
+
+class GhostBottleneck(nn.Module):
+    # Ghost Bottleneck https://github.com/huawei-noah/ghostnet
+    def __init__(self, c1, c2, k=3, s=1):  # ch_in, ch_out, kernel, stride
+        super().__init__()
+        c_ = c2 // 2
+        self.conv = nn.Sequential(
+            GhostConv(c1, c_, 1, 1),  # pw
+            DWConv(c_, c_, k, s, act=False) if s == 2 else nn.Identity(),  # dw
+            GhostConv(c_, c2, 1, 1, act=False))  # pw-linear
+        self.shortcut = nn.Sequential(DWConv(c1, c1, k, s, act=False), Conv(c1, c2, 1, 1,
+                                                                            act=False)) if s == 2 else nn.Identity()
+
+    def forward(self, x):
+        return self.conv(x) + self.shortcut(x)
+
+
+class Contract(nn.Module):
+    # Contract width-height into channels, i.e. x(1,64,80,80) to x(1,256,40,40)
+    def __init__(self, gain=2):
+        super().__init__()
+        self.gain = gain
+
+    def forward(self, x):
+        b, c, h, w = x.size()  # assert (h / s == 0) and (W / s == 0), 'Indivisible gain'
+        s = self.gain
+        x = x.view(b, c, h // s, s, w // s, s)  # x(1,64,40,2,40,2)
+        x = x.permute(0, 3, 5, 1, 2, 4).contiguous()  # x(1,2,2,64,40,40)
+        return x.view(b, c * s * s, h // s, w // s)  # x(1,256,40,40)
+
+
+class Expand(nn.Module):
+    # Expand channels into width-height, i.e. x(1,64,80,80) to x(1,16,160,160)
+    def __init__(self, gain=2):
+        super().__init__()
+        self.gain = gain
+
+    def forward(self, x):
+        b, c, h, w = x.size()  # assert C / s ** 2 == 0, 'Indivisible gain'
+        s = self.gain
+        x = x.view(b, s, s, c // s ** 2, h, w)  # x(1,2,2,16,80,80)
+        x = x.permute(0, 3, 4, 1, 5, 2).contiguous()  # x(1,16,80,2,80,2)
+        return x.view(b, c // s ** 2, h * s, w * s)  # x(1,16,160,160)
+
+
+class Concat(nn.Module):
+    # Concatenate a list of tensors along dimension
+    def __init__(self, dimension=1):
+        super().__init__()
+        self.d = dimension
+
+    def forward(self, x):
+        return torch.cat(x, self.d)
+
+
+class DetectMultiBackend(nn.Module):
+    # YOLOv5 MultiBackend class for python inference on various backends
+    def __init__(self, weights='yolov5s.pt', device=torch.device('cpu'), dnn=False, data=None, fp16=False, fuse=True):
+        # Usage:
+        #   PyTorch:              weights = *.pt
+        #   TorchScript:                    *.torchscript
+        #   ONNX Runtime:                   *.onnx
+        #   ONNX OpenCV DNN:                *.onnx --dnn
+        #   OpenVINO:                       *_openvino_model
+        #   CoreML:                         *.mlmodel
+        #   TensorRT:                       *.engine
+        #   TensorFlow SavedModel:          *_saved_model
+        #   TensorFlow GraphDef:            *.pb
+        #   TensorFlow Lite:                *.tflite
+        #   TensorFlow Edge TPU:            *_edgetpu.tflite
+        #   PaddlePaddle:                   *_paddle_model
+        from models.experimental import attempt_download, attempt_load  # scoped to avoid circular import
+
+        super().__init__()
+        w = str(weights[0] if isinstance(weights, list) else weights)
+        pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, paddle, triton = self._model_type(w)
+        fp16 &= pt or jit or onnx or engine or triton  # FP16
+        nhwc = coreml or saved_model or pb or tflite or edgetpu  # BHWC formats (vs torch BCWH)
+        stride = 32  # default stride
+        cuda = torch.cuda.is_available() and device.type != 'cpu'  # use CUDA
+        if not (pt or triton):
+            w = attempt_download(w)  # download if not local
+
+        if pt:  # PyTorch
+            model = attempt_load(weights if isinstance(weights, list) else w, device=device, inplace=True, fuse=fuse)
+            stride = max(int(model.stride.max()), 32)  # model stride
+            names = model.module.names if hasattr(model, 'module') else model.names  # get class names
+            model.half() if fp16 else model.float()
+            self.model = model  # explicitly assign for to(), cpu(), cuda(), half()
+        elif jit:  # TorchScript
+            LOGGER.info(f'Loading {w} for TorchScript inference...')
+            extra_files = {'config.txt': ''}  # model metadata
+            model = torch.jit.load(w, _extra_files=extra_files, map_location=device)
+            model.half() if fp16 else model.float()
+            if extra_files['config.txt']:  # load metadata dict
+                d = json.loads(extra_files['config.txt'],
+                               object_hook=lambda d: {
+                                   int(k) if k.isdigit() else k: v
+                                   for k, v in d.items()})
+                stride, names = int(d['stride']), d['names']
+        elif dnn:  # ONNX OpenCV DNN
+            LOGGER.info(f'Loading {w} for ONNX OpenCV DNN inference...')
+            check_requirements('opencv-python>=4.5.4')
+            net = cv2.dnn.readNetFromONNX(w)
+        elif onnx:  # ONNX Runtime
+            LOGGER.info(f'Loading {w} for ONNX Runtime inference...')
+            check_requirements(('onnx', 'onnxruntime-gpu' if cuda else 'onnxruntime'))
+            import onnxruntime
+            providers = ['CUDAExecutionProvider', 'CPUExecutionProvider'] if cuda else ['CPUExecutionProvider']
+            session = onnxruntime.InferenceSession(w, providers=providers)
+            output_names = [x.name for x in session.get_outputs()]
+            meta = session.get_modelmeta().custom_metadata_map  # metadata
+            if 'stride' in meta:
+                stride, names = int(meta['stride']), eval(meta['names'])
+        elif xml:  # OpenVINO
+            LOGGER.info(f'Loading {w} for OpenVINO inference...')
+            check_requirements('openvino>=2023.0')  # requires openvino-dev: https://pypi.org/project/openvino-dev/
+            from openvino.runtime import Core, Layout, get_batch
+            core = Core()
+            if not Path(w).is_file():  # if not *.xml
+                w = next(Path(w).glob('*.xml'))  # get *.xml file from *_openvino_model dir
+            ov_model = core.read_model(model=w, weights=Path(w).with_suffix('.bin'))
+            if ov_model.get_parameters()[0].get_layout().empty:
+                ov_model.get_parameters()[0].set_layout(Layout('NCHW'))
+            batch_dim = get_batch(ov_model)
+            if batch_dim.is_static:
+                batch_size = batch_dim.get_length()
+            ov_compiled_model = core.compile_model(ov_model, device_name='AUTO')  # AUTO selects best available device
+            stride, names = self._load_metadata(Path(w).with_suffix('.yaml'))  # load metadata
+        elif engine:  # TensorRT
+            LOGGER.info(f'Loading {w} for TensorRT inference...')
+            import tensorrt as trt  # https://developer.nvidia.com/nvidia-tensorrt-download
+            check_version(trt.__version__, '7.0.0', hard=True)  # require tensorrt>=7.0.0
+            if device.type == 'cpu':
+                device = torch.device('cuda:0')
+            Binding = namedtuple('Binding', ('name', 'dtype', 'shape', 'data', 'ptr'))
+            logger = trt.Logger(trt.Logger.INFO)
+            with open(w, 'rb') as f, trt.Runtime(logger) as runtime:
+                model = runtime.deserialize_cuda_engine(f.read())
+            context = model.create_execution_context()
+            bindings = OrderedDict()
+            output_names = []
+            fp16 = False  # default updated below
+            dynamic = False
+            for i in range(model.num_bindings):
+                name = model.get_binding_name(i)
+                dtype = trt.nptype(model.get_binding_dtype(i))
+                if model.binding_is_input(i):
+                    if -1 in tuple(model.get_binding_shape(i)):  # dynamic
+                        dynamic = True
+                        context.set_binding_shape(i, tuple(model.get_profile_shape(0, i)[2]))
+                    if dtype == np.float16:
+                        fp16 = True
+                else:  # output
+                    output_names.append(name)
+                shape = tuple(context.get_binding_shape(i))
+                im = torch.from_numpy(np.empty(shape, dtype=dtype)).to(device)
+                bindings[name] = Binding(name, dtype, shape, im, int(im.data_ptr()))
+            binding_addrs = OrderedDict((n, d.ptr) for n, d in bindings.items())
+            batch_size = bindings['images'].shape[0]  # if dynamic, this is instead max batch size
+        elif coreml:  # CoreML
+            LOGGER.info(f'Loading {w} for CoreML inference...')
+            import coremltools as ct
+            model = ct.models.MLModel(w)
+        elif saved_model:  # TF SavedModel
+            LOGGER.info(f'Loading {w} for TensorFlow SavedModel inference...')
+            import tensorflow as tf
+            keras = False  # assume TF1 saved_model
+            model = tf.keras.models.load_model(w) if keras else tf.saved_model.load(w)
+        elif pb:  # GraphDef https://www.tensorflow.org/guide/migrate#a_graphpb_or_graphpbtxt
+            LOGGER.info(f'Loading {w} for TensorFlow GraphDef inference...')
+            import tensorflow as tf
+
+            def wrap_frozen_graph(gd, inputs, outputs):
+                x = tf.compat.v1.wrap_function(lambda: tf.compat.v1.import_graph_def(gd, name=''), [])  # wrapped
+                ge = x.graph.as_graph_element
+                return x.prune(tf.nest.map_structure(ge, inputs), tf.nest.map_structure(ge, outputs))
+
+            def gd_outputs(gd):
+                name_list, input_list = [], []
+                for node in gd.node:  # tensorflow.core.framework.node_def_pb2.NodeDef
+                    name_list.append(node.name)
+                    input_list.extend(node.input)
+                return sorted(f'{x}:0' for x in list(set(name_list) - set(input_list)) if not x.startswith('NoOp'))
+
+            gd = tf.Graph().as_graph_def()  # TF GraphDef
+            with open(w, 'rb') as f:
+                gd.ParseFromString(f.read())
+            frozen_func = wrap_frozen_graph(gd, inputs='x:0', outputs=gd_outputs(gd))
+        elif tflite or edgetpu:  # https://www.tensorflow.org/lite/guide/python#install_tensorflow_lite_for_python
+            try:  # https://coral.ai/docs/edgetpu/tflite-python/#update-existing-tf-lite-code-for-the-edge-tpu
+                from tflite_runtime.interpreter import Interpreter, load_delegate
+            except ImportError:
+                import tensorflow as tf
+                Interpreter, load_delegate = tf.lite.Interpreter, tf.lite.experimental.load_delegate,
+            if edgetpu:  # TF Edge TPU https://coral.ai/software/#edgetpu-runtime
+                LOGGER.info(f'Loading {w} for TensorFlow Lite Edge TPU inference...')
+                delegate = {
+                    'Linux': 'libedgetpu.so.1',
+                    'Darwin': 'libedgetpu.1.dylib',
+                    'Windows': 'edgetpu.dll'}[platform.system()]
+                interpreter = Interpreter(model_path=w, experimental_delegates=[load_delegate(delegate)])
+            else:  # TFLite
+                LOGGER.info(f'Loading {w} for TensorFlow Lite inference...')
+                interpreter = Interpreter(model_path=w)  # load TFLite model
+            interpreter.allocate_tensors()  # allocate
+            input_details = interpreter.get_input_details()  # inputs
+            output_details = interpreter.get_output_details()  # outputs
+            # load metadata
+            with contextlib.suppress(zipfile.BadZipFile):
+                with zipfile.ZipFile(w, 'r') as model:
+                    meta_file = model.namelist()[0]
+                    meta = ast.literal_eval(model.read(meta_file).decode('utf-8'))
+                    stride, names = int(meta['stride']), meta['names']
+        elif tfjs:  # TF.js
+            raise NotImplementedError('ERROR: YOLOv5 TF.js inference is not supported')
+        elif paddle:  # PaddlePaddle
+            LOGGER.info(f'Loading {w} for PaddlePaddle inference...')
+            check_requirements('paddlepaddle-gpu' if cuda else 'paddlepaddle')
+            import paddle.inference as pdi
+            if not Path(w).is_file():  # if not *.pdmodel
+                w = next(Path(w).rglob('*.pdmodel'))  # get *.pdmodel file from *_paddle_model dir
+            weights = Path(w).with_suffix('.pdiparams')
+            config = pdi.Config(str(w), str(weights))
+            if cuda:
+                config.enable_use_gpu(memory_pool_init_size_mb=2048, device_id=0)
+            predictor = pdi.create_predictor(config)
+            input_handle = predictor.get_input_handle(predictor.get_input_names()[0])
+            output_names = predictor.get_output_names()
+        elif triton:  # NVIDIA Triton Inference Server
+            LOGGER.info(f'Using {w} as Triton Inference Server...')
+            check_requirements('tritonclient[all]')
+            from utils.triton import TritonRemoteModel
+            model = TritonRemoteModel(url=w)
+            nhwc = model.runtime.startswith('tensorflow')
+        else:
+            raise NotImplementedError(f'ERROR: {w} is not a supported format')
+
+        # class names
+        if 'names' not in locals():
+            names = yaml_load(data)['names'] if data else {i: f'class{i}' for i in range(999)}
+        if names[0] == 'n01440764' and len(names) == 1000:  # ImageNet
+            names = yaml_load(ROOT / 'data/ImageNet.yaml')['names']  # human-readable names
+
+        self.__dict__.update(locals())  # assign all variables to self
+
+    def forward(self, im, augment=False, visualize=False):
+        # YOLOv5 MultiBackend inference
+        b, ch, h, w = im.shape  # batch, channel, height, width
+        if self.fp16 and im.dtype != torch.float16:
+            im = im.half()  # to FP16
+        if self.nhwc:
+            im = im.permute(0, 2, 3, 1)  # torch BCHW to numpy BHWC shape(1,320,192,3)
+
+        if self.pt:  # PyTorch
+            y = self.model(im, augment=augment, visualize=visualize) if augment or visualize else self.model(im)
+        elif self.jit:  # TorchScript
+            y = self.model(im)
+        elif self.dnn:  # ONNX OpenCV DNN
+            im = im.cpu().numpy()  # torch to numpy
+            self.net.setInput(im)
+            y = self.net.forward()
+        elif self.onnx:  # ONNX Runtime
+            im = im.cpu().numpy()  # torch to numpy
+            y = self.session.run(self.output_names, {self.session.get_inputs()[0].name: im})
+        elif self.xml:  # OpenVINO
+            im = im.cpu().numpy()  # FP32
+            y = list(self.ov_compiled_model(im).values())
+        elif self.engine:  # TensorRT
+            if self.dynamic and im.shape != self.bindings['images'].shape:
+                i = self.model.get_binding_index('images')
+                self.context.set_binding_shape(i, im.shape)  # reshape if dynamic
+                self.bindings['images'] = self.bindings['images']._replace(shape=im.shape)
+                for name in self.output_names:
+                    i = self.model.get_binding_index(name)
+                    self.bindings[name].data.resize_(tuple(self.context.get_binding_shape(i)))
+            s = self.bindings['images'].shape
+            assert im.shape == s, f"input size {im.shape} {'>' if self.dynamic else 'not equal to'} max model size {s}"
+            self.binding_addrs['images'] = int(im.data_ptr())
+            self.context.execute_v2(list(self.binding_addrs.values()))
+            y = [self.bindings[x].data for x in sorted(self.output_names)]
+        elif self.coreml:  # CoreML
+            im = im.cpu().numpy()
+            im = Image.fromarray((im[0] * 255).astype('uint8'))
+            # im = im.resize((192, 320), Image.BILINEAR)
+            y = self.model.predict({'image': im})  # coordinates are xywh normalized
+            if 'confidence' in y:
+                box = xywh2xyxy(y['coordinates'] * [[w, h, w, h]])  # xyxy pixels
+                conf, cls = y['confidence'].max(1), y['confidence'].argmax(1).astype(np.float)
+                y = np.concatenate((box, conf.reshape(-1, 1), cls.reshape(-1, 1)), 1)
+            else:
+                y = list(reversed(y.values()))  # reversed for segmentation models (pred, proto)
+        elif self.paddle:  # PaddlePaddle
+            im = im.cpu().numpy().astype(np.float32)
+            self.input_handle.copy_from_cpu(im)
+            self.predictor.run()
+            y = [self.predictor.get_output_handle(x).copy_to_cpu() for x in self.output_names]
+        elif self.triton:  # NVIDIA Triton Inference Server
+            y = self.model(im)
+        else:  # TensorFlow (SavedModel, GraphDef, Lite, Edge TPU)
+            im = im.cpu().numpy()
+            if self.saved_model:  # SavedModel
+                y = self.model(im, training=False) if self.keras else self.model(im)
+            elif self.pb:  # GraphDef
+                y = self.frozen_func(x=self.tf.constant(im))
+            else:  # Lite or Edge TPU
+                input = self.input_details[0]
+                int8 = input['dtype'] == np.uint8  # is TFLite quantized uint8 model
+                if int8:
+                    scale, zero_point = input['quantization']
+                    im = (im / scale + zero_point).astype(np.uint8)  # de-scale
+                self.interpreter.set_tensor(input['index'], im)
+                self.interpreter.invoke()
+                y = []
+                for output in self.output_details:
+                    x = self.interpreter.get_tensor(output['index'])
+                    if int8:
+                        scale, zero_point = output['quantization']
+                        x = (x.astype(np.float32) - zero_point) * scale  # re-scale
+                    y.append(x)
+            y = [x if isinstance(x, np.ndarray) else x.numpy() for x in y]
+            y[0][..., :4] *= [w, h, w, h]  # xywh normalized to pixels
+
+        if isinstance(y, (list, tuple)):
+            return self.from_numpy(y[0]) if len(y) == 1 else [self.from_numpy(x) for x in y]
+        else:
+            return self.from_numpy(y)
+
+    def from_numpy(self, x):
+        return torch.from_numpy(x).to(self.device) if isinstance(x, np.ndarray) else x
+
+    def warmup(self, imgsz=(1, 3, 640, 640)):
+        # Warmup model by running inference once
+        warmup_types = self.pt, self.jit, self.onnx, self.engine, self.saved_model, self.pb, self.triton
+        if any(warmup_types) and (self.device.type != 'cpu' or self.triton):
+            im = torch.empty(*imgsz, dtype=torch.half if self.fp16 else torch.float, device=self.device)  # input
+            for _ in range(2 if self.jit else 1):  #
+                self.forward(im)  # warmup
+
+    @staticmethod
+    def _model_type(p='path/to/model.pt'):
+        # Return model type from model path, i.e. path='path/to/model.onnx' -> type=onnx
+        # types = [pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, paddle]
+        from export import export_formats
+        from utils.downloads import is_url
+        sf = list(export_formats().Suffix)  # export suffixes
+        if not is_url(p, check=False):
+            check_suffix(p, sf)  # checks
+        url = urlparse(p)  # if url may be Triton inference server
+        types = [s in Path(p).name for s in sf]
+        types[8] &= not types[9]  # tflite &= not edgetpu
+        triton = not any(types) and all([any(s in url.scheme for s in ['http', 'grpc']), url.netloc])
+        return types + [triton]
+
+    @staticmethod
+    def _load_metadata(f=Path('path/to/meta.yaml')):
+        # Load metadata from meta.yaml if it exists
+        if f.exists():
+            d = yaml_load(f)
+            return d['stride'], d['names']  # assign stride, names
+        return None, None
+
+
+class AutoShape(nn.Module):
+    # YOLOv5 input-robust model wrapper for passing cv2/np/PIL/torch inputs. Includes preprocessing, inference and NMS
+    conf = 0.25  # NMS confidence threshold
+    iou = 0.45  # NMS IoU threshold
+    agnostic = False  # NMS class-agnostic
+    multi_label = False  # NMS multiple labels per box
+    classes = None  # (optional list) filter by class, i.e. = [0, 15, 16] for COCO persons, cats and dogs
+    max_det = 1000  # maximum number of detections per image
+    amp = False  # Automatic Mixed Precision (AMP) inference
+
+    def __init__(self, model, verbose=True):
+        super().__init__()
+        if verbose:
+            LOGGER.info('Adding AutoShape... ')
+        copy_attr(self, model, include=('yaml', 'nc', 'hyp', 'names', 'stride', 'abc'), exclude=())  # copy attributes
+        self.dmb = isinstance(model, DetectMultiBackend)  # DetectMultiBackend() instance
+        self.pt = not self.dmb or model.pt  # PyTorch model
+        self.model = model.eval()
+        if self.pt:
+            m = self.model.model.model[-1] if self.dmb else self.model.model[-1]  # Detect()
+            m.inplace = False  # Detect.inplace=False for safe multithread inference
+            m.export = True  # do not output loss values
+
+    def _apply(self, fn):
+        # Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers
+        self = super()._apply(fn)
+        if self.pt:
+            m = self.model.model.model[-1] if self.dmb else self.model.model[-1]  # Detect()
+            m.stride = fn(m.stride)
+            m.grid = list(map(fn, m.grid))
+            if isinstance(m.anchor_grid, list):
+                m.anchor_grid = list(map(fn, m.anchor_grid))
+        return self
+
+    @smart_inference_mode()
+    def forward(self, ims, size=640, augment=False, profile=False):
+        # Inference from various sources. For size(height=640, width=1280), RGB images example inputs are:
+        #   file:        ims = 'data/images/zidane.jpg'  # str or PosixPath
+        #   URI:             = 'https://ultralytics.com/images/zidane.jpg'
+        #   OpenCV:          = cv2.imread('image.jpg')[:,:,::-1]  # HWC BGR to RGB x(640,1280,3)
+        #   PIL:             = Image.open('image.jpg') or ImageGrab.grab()  # HWC x(640,1280,3)
+        #   numpy:           = np.zeros((640,1280,3))  # HWC
+        #   torch:           = torch.zeros(16,3,320,640)  # BCHW (scaled to size=640, 0-1 values)
+        #   multiple:        = [Image.open('image1.jpg'), Image.open('image2.jpg'), ...]  # list of images
+
+        dt = (Profile(), Profile(), Profile())
+        with dt[0]:
+            if isinstance(size, int):  # expand
+                size = (size, size)
+            p = next(self.model.parameters()) if self.pt else torch.empty(1, device=self.model.device)  # param
+            autocast = self.amp and (p.device.type != 'cpu')  # Automatic Mixed Precision (AMP) inference
+            if isinstance(ims, torch.Tensor):  # torch
+                with amp.autocast(autocast):
+                    return self.model(ims.to(p.device).type_as(p), augment=augment)  # inference
+
+            # Pre-process
+            n, ims = (len(ims), list(ims)) if isinstance(ims, (list, tuple)) else (1, [ims])  # number, list of images
+            shape0, shape1, files = [], [], []  # image and inference shapes, filenames
+            for i, im in enumerate(ims):
+                f = f'image{i}'  # filename
+                if isinstance(im, (str, Path)):  # filename or uri
+                    im, f = Image.open(requests.get(im, stream=True).raw if str(im).startswith('http') else im), im
+                    im = np.asarray(exif_transpose(im))
+                elif isinstance(im, Image.Image):  # PIL Image
+                    im, f = np.asarray(exif_transpose(im)), getattr(im, 'filename', f) or f
+                files.append(Path(f).with_suffix('.jpg').name)
+                if im.shape[0] < 5:  # image in CHW
+                    im = im.transpose((1, 2, 0))  # reverse dataloader .transpose(2, 0, 1)
+                im = im[..., :3] if im.ndim == 3 else cv2.cvtColor(im, cv2.COLOR_GRAY2BGR)  # enforce 3ch input
+                s = im.shape[:2]  # HWC
+                shape0.append(s)  # image shape
+                g = max(size) / max(s)  # gain
+                shape1.append([int(y * g) for y in s])
+                ims[i] = im if im.data.contiguous else np.ascontiguousarray(im)  # update
+            shape1 = [make_divisible(x, self.stride) for x in np.array(shape1).max(0)]  # inf shape
+            x = [letterbox(im, shape1, auto=False)[0] for im in ims]  # pad
+            x = np.ascontiguousarray(np.array(x).transpose((0, 3, 1, 2)))  # stack and BHWC to BCHW
+            x = torch.from_numpy(x).to(p.device).type_as(p) / 255  # uint8 to fp16/32
+
+        with amp.autocast(autocast):
+            # Inference
+            with dt[1]:
+                y = self.model(x, augment=augment)  # forward
+
+            # Post-process
+            with dt[2]:
+                y = non_max_suppression(y if self.dmb else y[0],
+                                        self.conf,
+                                        self.iou,
+                                        self.classes,
+                                        self.agnostic,
+                                        self.multi_label,
+                                        max_det=self.max_det)  # NMS
+                for i in range(n):
+                    scale_boxes(shape1, y[i][:, :4], shape0[i])
+
+            return Detections(ims, y, files, dt, self.names, x.shape)
+
+
+class Detections:
+    # YOLOv5 detections class for inference results
+    def __init__(self, ims, pred, files, times=(0, 0, 0), names=None, shape=None):
+        super().__init__()
+        d = pred[0].device  # device
+        gn = [torch.tensor([*(im.shape[i] for i in [1, 0, 1, 0]), 1, 1], device=d) for im in ims]  # normalizations
+        self.ims = ims  # list of images as numpy arrays
+        self.pred = pred  # list of tensors pred[0] = (xyxy, conf, cls)
+        self.names = names  # class names
+        self.files = files  # image filenames
+        self.times = times  # profiling times
+        self.xyxy = pred  # xyxy pixels
+        self.xywh = [xyxy2xywh(x) for x in pred]  # xywh pixels
+        self.xyxyn = [x / g for x, g in zip(self.xyxy, gn)]  # xyxy normalized
+        self.xywhn = [x / g for x, g in zip(self.xywh, gn)]  # xywh normalized
+        self.n = len(self.pred)  # number of images (batch size)
+        self.t = tuple(x.t / self.n * 1E3 for x in times)  # timestamps (ms)
+        self.s = tuple(shape)  # inference BCHW shape
+
+    def _run(self, pprint=False, show=False, save=False, crop=False, render=False, labels=True, save_dir=Path('')):
+        s, crops = '', []
+        for i, (im, pred) in enumerate(zip(self.ims, self.pred)):
+            s += f'\nimage {i + 1}/{len(self.pred)}: {im.shape[0]}x{im.shape[1]} '  # string
+            if pred.shape[0]:
+                for c in pred[:, -1].unique():
+                    n = (pred[:, -1] == c).sum()  # detections per class
+                    s += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, "  # add to string
+                s = s.rstrip(', ')
+                if show or save or render or crop:
+                    annotator = Annotator(im, example=str(self.names))
+                    for *box, conf, cls in reversed(pred):  # xyxy, confidence, class
+                        label = f'{self.names[int(cls)]} {conf:.2f}'
+                        if crop:
+                            file = save_dir / 'crops' / self.names[int(cls)] / self.files[i] if save else None
+                            crops.append({
+                                'box': box,
+                                'conf': conf,
+                                'cls': cls,
+                                'label': label,
+                                'im': save_one_box(box, im, file=file, save=save)})
+                        else:  # all others
+                            annotator.box_label(box, label if labels else '', color=colors(cls))
+                    im = annotator.im
+            else:
+                s += '(no detections)'
+
+            im = Image.fromarray(im.astype(np.uint8)) if isinstance(im, np.ndarray) else im  # from np
+            if show:
+                if is_jupyter():
+                    from IPython.display import display
+                    display(im)
+                else:
+                    im.show(self.files[i])
+            if save:
+                f = self.files[i]
+                im.save(save_dir / f)  # save
+                if i == self.n - 1:
+                    LOGGER.info(f"Saved {self.n} image{'s' * (self.n > 1)} to {colorstr('bold', save_dir)}")
+            if render:
+                self.ims[i] = np.asarray(im)
+        if pprint:
+            s = s.lstrip('\n')
+            return f'{s}\nSpeed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {self.s}' % self.t
+        if crop:
+            if save:
+                LOGGER.info(f'Saved results to {save_dir}\n')
+            return crops
+
+    @TryExcept('Showing images is not supported in this environment')
+    def show(self, labels=True):
+        self._run(show=True, labels=labels)  # show results
+
+    def save(self, labels=True, save_dir='runs/detect/exp', exist_ok=False):
+        save_dir = increment_path(save_dir, exist_ok, mkdir=True)  # increment save_dir
+        self._run(save=True, labels=labels, save_dir=save_dir)  # save results
+
+    def crop(self, save=True, save_dir='runs/detect/exp', exist_ok=False):
+        save_dir = increment_path(save_dir, exist_ok, mkdir=True) if save else None
+        return self._run(crop=True, save=save, save_dir=save_dir)  # crop results
+
+    def render(self, labels=True):
+        self._run(render=True, labels=labels)  # render results
+        return self.ims
+
+    def pandas(self):
+        # return detections as pandas DataFrames, i.e. print(results.pandas().xyxy[0])
+        new = copy(self)  # return copy
+        ca = 'xmin', 'ymin', 'xmax', 'ymax', 'confidence', 'class', 'name'  # xyxy columns
+        cb = 'xcenter', 'ycenter', 'width', 'height', 'confidence', 'class', 'name'  # xywh columns
+        for k, c in zip(['xyxy', 'xyxyn', 'xywh', 'xywhn'], [ca, ca, cb, cb]):
+            a = [[x[:5] + [int(x[5]), self.names[int(x[5])]] for x in x.tolist()] for x in getattr(self, k)]  # update
+            setattr(new, k, [pd.DataFrame(x, columns=c) for x in a])
+        return new
+
+    def tolist(self):
+        # return a list of Detections objects, i.e. 'for result in results.tolist():'
+        r = range(self.n)  # iterable
+        x = [Detections([self.ims[i]], [self.pred[i]], [self.files[i]], self.times, self.names, self.s) for i in r]
+        # for d in x:
+        #    for k in ['ims', 'pred', 'xyxy', 'xyxyn', 'xywh', 'xywhn']:
+        #        setattr(d, k, getattr(d, k)[0])  # pop out of list
+        return x
+
+    def print(self):
+        LOGGER.info(self.__str__())
+
+    def __len__(self):  # override len(results)
+        return self.n
+
+    def __str__(self):  # override print(results)
+        return self._run(pprint=True)  # print results
+
+    def __repr__(self):
+        return f'YOLOv5 {self.__class__} instance\n' + self.__str__()
+
+
+class Proto(nn.Module):
+    # YOLOv5 mask Proto module for segmentation models
+    def __init__(self, c1, c_=256, c2=32):  # ch_in, number of protos, number of masks
+        super().__init__()
+        self.cv1 = Conv(c1, c_, k=3)
+        self.upsample = nn.Upsample(scale_factor=2, mode='nearest')
+        self.cv2 = Conv(c_, c_, k=3)
+        self.cv3 = Conv(c_, c2)
+
+    def forward(self, x):
+        return self.cv3(self.cv2(self.upsample(self.cv1(x))))
+
+
+class Classify(nn.Module):
+    # YOLOv5 classification head, i.e. x(b,c1,20,20) to x(b,c2)
+    def __init__(self,
+                 c1,
+                 c2,
+                 k=1,
+                 s=1,
+                 p=None,
+                 g=1,
+                 dropout_p=0.0):  # ch_in, ch_out, kernel, stride, padding, groups, dropout probability
+        super().__init__()
+        c_ = 1280  # efficientnet_b0 size
+        self.conv = Conv(c1, c_, k, s, autopad(k, p), g)
+        self.pool = nn.AdaptiveAvgPool2d(1)  # to x(b,c_,1,1)
+        self.drop = nn.Dropout(p=dropout_p, inplace=True)
+        self.linear = nn.Linear(c_, c2)  # to x(b,c2)
+
+    def forward(self, x):
+        if isinstance(x, list):
+            x = torch.cat(x, 1)
+        return self.linear(self.drop(self.pool(self.conv(x)).flatten(1)))

models/experimental.py

@@ -0,0 +1,111 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+"""
+Experimental modules
+"""
+import math
+
+import numpy as np
+import torch
+import torch.nn as nn
+
+from utils.downloads import attempt_download
+
+
+class Sum(nn.Module):
+    # Weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070
+    def __init__(self, n, weight=False):  # n: number of inputs
+        super().__init__()
+        self.weight = weight  # apply weights boolean
+        self.iter = range(n - 1)  # iter object
+        if weight:
+            self.w = nn.Parameter(-torch.arange(1.0, n) / 2, requires_grad=True)  # layer weights
+
+    def forward(self, x):
+        y = x[0]  # no weight
+        if self.weight:
+            w = torch.sigmoid(self.w) * 2
+            for i in self.iter:
+                y = y + x[i + 1] * w[i]
+        else:
+            for i in self.iter:
+                y = y + x[i + 1]
+        return y
+
+
+class MixConv2d(nn.Module):
+    # Mixed Depth-wise Conv https://arxiv.org/abs/1907.09595
+    def __init__(self, c1, c2, k=(1, 3), s=1, equal_ch=True):  # ch_in, ch_out, kernel, stride, ch_strategy
+        super().__init__()
+        n = len(k)  # number of convolutions
+        if equal_ch:  # equal c_ per group
+            i = torch.linspace(0, n - 1E-6, c2).floor()  # c2 indices
+            c_ = [(i == g).sum() for g in range(n)]  # intermediate channels
+        else:  # equal weight.numel() per group
+            b = [c2] + [0] * n
+            a = np.eye(n + 1, n, k=-1)
+            a -= np.roll(a, 1, axis=1)
+            a *= np.array(k) ** 2
+            a[0] = 1
+            c_ = np.linalg.lstsq(a, b, rcond=None)[0].round()  # solve for equal weight indices, ax = b
+
+        self.m = nn.ModuleList([
+            nn.Conv2d(c1, int(c_), k, s, k // 2, groups=math.gcd(c1, int(c_)), bias=False) for k, c_ in zip(k, c_)])
+        self.bn = nn.BatchNorm2d(c2)
+        self.act = nn.SiLU()
+
+    def forward(self, x):
+        return self.act(self.bn(torch.cat([m(x) for m in self.m], 1)))
+
+
+class Ensemble(nn.ModuleList):
+    # Ensemble of models
+    def __init__(self):
+        super().__init__()
+
+    def forward(self, x, augment=False, profile=False, visualize=False):
+        y = [module(x, augment, profile, visualize)[0] for module in self]
+        # y = torch.stack(y).max(0)[0]  # max ensemble
+        # y = torch.stack(y).mean(0)  # mean ensemble
+        y = torch.cat(y, 1)  # nms ensemble
+        return y, None  # inference, train output
+
+
+def attempt_load(weights, device=None, inplace=True, fuse=True):
+    # Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a
+    from models.yolo import Detect, Model
+
+    model = Ensemble()
+    for w in weights if isinstance(weights, list) else [weights]:
+        ckpt = torch.load(attempt_download(w), map_location='cpu')  # load
+        ckpt = (ckpt.get('ema') or ckpt['model']).to(device).float()  # FP32 model
+
+        # Model compatibility updates
+        if not hasattr(ckpt, 'stride'):
+            ckpt.stride = torch.tensor([32.])
+        if hasattr(ckpt, 'names') and isinstance(ckpt.names, (list, tuple)):
+            ckpt.names = dict(enumerate(ckpt.names))  # convert to dict
+
+        model.append(ckpt.fuse().eval() if fuse and hasattr(ckpt, 'fuse') else ckpt.eval())  # model in eval mode
+
+    # Module updates
+    for m in model.modules():
+        t = type(m)
+        if t in (nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU, Detect, Model):
+            m.inplace = inplace
+            if t is Detect and not isinstance(m.anchor_grid, list):
+                delattr(m, 'anchor_grid')
+                setattr(m, 'anchor_grid', [torch.zeros(1)] * m.nl)
+        elif t is nn.Upsample and not hasattr(m, 'recompute_scale_factor'):
+            m.recompute_scale_factor = None  # torch 1.11.0 compatibility
+
+    # Return model
+    if len(model) == 1:
+        return model[-1]
+
+    # Return detection ensemble
+    print(f'Ensemble created with {weights}\n')
+    for k in 'names', 'nc', 'yaml':
+        setattr(model, k, getattr(model[0], k))
+    model.stride = model[torch.argmax(torch.tensor([m.stride.max() for m in model])).int()].stride  # max stride
+    assert all(model[0].nc == m.nc for m in model), f'Models have different class counts: {[m.nc for m in model]}'
+    return model

models/hub/anchors.yaml

@@ -0,0 +1,59 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+# Default anchors for COCO data
+
+
+# P5 -------------------------------------------------------------------------------------------------------------------
+# P5-640:
+anchors_p5_640:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+
+# P6 -------------------------------------------------------------------------------------------------------------------
+# P6-640:  thr=0.25: 0.9964 BPR, 5.54 anchors past thr, n=12, img_size=640, metric_all=0.281/0.716-mean/best, past_thr=0.469-mean: 9,11,  21,19,  17,41,  43,32,  39,70,  86,64,  65,131,  134,130,  120,265,  282,180,  247,354,  512,387
+anchors_p6_640:
+  - [9,11,  21,19,  17,41]  # P3/8
+  - [43,32,  39,70,  86,64]  # P4/16
+  - [65,131,  134,130,  120,265]  # P5/32
+  - [282,180,  247,354,  512,387]  # P6/64
+
+# P6-1280:  thr=0.25: 0.9950 BPR, 5.55 anchors past thr, n=12, img_size=1280, metric_all=0.281/0.714-mean/best, past_thr=0.468-mean: 19,27,  44,40,  38,94,  96,68,  86,152,  180,137,  140,301,  303,264,  238,542,  436,615,  739,380,  925,792
+anchors_p6_1280:
+  - [19,27,  44,40,  38,94]  # P3/8
+  - [96,68,  86,152,  180,137]  # P4/16
+  - [140,301,  303,264,  238,542]  # P5/32
+  - [436,615,  739,380,  925,792]  # P6/64
+
+# P6-1920:  thr=0.25: 0.9950 BPR, 5.55 anchors past thr, n=12, img_size=1920, metric_all=0.281/0.714-mean/best, past_thr=0.468-mean: 28,41,  67,59,  57,141,  144,103,  129,227,  270,205,  209,452,  455,396,  358,812,  653,922,  1109,570,  1387,1187
+anchors_p6_1920:
+  - [28,41,  67,59,  57,141]  # P3/8
+  - [144,103,  129,227,  270,205]  # P4/16
+  - [209,452,  455,396,  358,812]  # P5/32
+  - [653,922,  1109,570,  1387,1187]  # P6/64
+
+
+# P7 -------------------------------------------------------------------------------------------------------------------
+# P7-640:  thr=0.25: 0.9962 BPR, 6.76 anchors past thr, n=15, img_size=640, metric_all=0.275/0.733-mean/best, past_thr=0.466-mean: 11,11,  13,30,  29,20,  30,46,  61,38,  39,92,  78,80,  146,66,  79,163,  149,150,  321,143,  157,303,  257,402,  359,290,  524,372
+anchors_p7_640:
+  - [11,11,  13,30,  29,20]  # P3/8
+  - [30,46,  61,38,  39,92]  # P4/16
+  - [78,80,  146,66,  79,163]  # P5/32
+  - [149,150,  321,143,  157,303]  # P6/64
+  - [257,402,  359,290,  524,372]  # P7/128
+
+# P7-1280:  thr=0.25: 0.9968 BPR, 6.71 anchors past thr, n=15, img_size=1280, metric_all=0.273/0.732-mean/best, past_thr=0.463-mean: 19,22,  54,36,  32,77,  70,83,  138,71,  75,173,  165,159,  148,334,  375,151,  334,317,  251,626,  499,474,  750,326,  534,814,  1079,818
+anchors_p7_1280:
+  - [19,22,  54,36,  32,77]  # P3/8
+  - [70,83,  138,71,  75,173]  # P4/16
+  - [165,159,  148,334,  375,151]  # P5/32
+  - [334,317,  251,626,  499,474]  # P6/64
+  - [750,326,  534,814,  1079,818]  # P7/128
+
+# P7-1920:  thr=0.25: 0.9968 BPR, 6.71 anchors past thr, n=15, img_size=1920, metric_all=0.273/0.732-mean/best, past_thr=0.463-mean: 29,34,  81,55,  47,115,  105,124,  207,107,  113,259,  247,238,  222,500,  563,227,  501,476,  376,939,  749,711,  1126,489,  801,1222,  1618,1227
+anchors_p7_1920:
+  - [29,34,  81,55,  47,115]  # P3/8
+  - [105,124,  207,107,  113,259]  # P4/16
+  - [247,238,  222,500,  563,227]  # P5/32
+  - [501,476,  376,939,  749,711]  # P6/64
+  - [1126,489,  801,1222,  1618,1227]  # P7/128

models/hub/yolov3-spp.yaml

@@ -0,0 +1,51 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# darknet53 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [32, 3, 1]],  # 0
+   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2
+   [-1, 1, Bottleneck, [64]],
+   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4
+   [-1, 2, Bottleneck, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 5-P3/8
+   [-1, 8, Bottleneck, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 7-P4/16
+   [-1, 8, Bottleneck, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P5/32
+   [-1, 4, Bottleneck, [1024]],  # 10
+  ]
+
+# YOLOv3-SPP head
+head:
+  [[-1, 1, Bottleneck, [1024, False]],
+   [-1, 1, SPP, [512, [5, 9, 13]]],
+   [-1, 1, Conv, [1024, 3, 1]],
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [1024, 3, 1]],  # 15 (P5/32-large)
+
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P4
+   [-1, 1, Bottleneck, [512, False]],
+   [-1, 1, Bottleneck, [512, False]],
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],  # 22 (P4/16-medium)
+
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P3
+   [-1, 1, Bottleneck, [256, False]],
+   [-1, 2, Bottleneck, [256, False]],  # 27 (P3/8-small)
+
+   [[27, 22, 15], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

models/hub/yolov3-tiny.yaml

@@ -0,0 +1,41 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors:
+  - [10,14, 23,27, 37,58]  # P4/16
+  - [81,82, 135,169, 344,319]  # P5/32
+
+# YOLOv3-tiny backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [16, 3, 1]],  # 0
+   [-1, 1, nn.MaxPool2d, [2, 2, 0]],  # 1-P1/2
+   [-1, 1, Conv, [32, 3, 1]],
+   [-1, 1, nn.MaxPool2d, [2, 2, 0]],  # 3-P2/4
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, nn.MaxPool2d, [2, 2, 0]],  # 5-P3/8
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, nn.MaxPool2d, [2, 2, 0]],  # 7-P4/16
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, nn.MaxPool2d, [2, 2, 0]],  # 9-P5/32
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, nn.ZeroPad2d, [[0, 1, 0, 1]]],  # 11
+   [-1, 1, nn.MaxPool2d, [2, 1, 0]],  # 12
+  ]
+
+# YOLOv3-tiny head
+head:
+  [[-1, 1, Conv, [1024, 3, 1]],
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],  # 15 (P5/32-large)
+
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P4
+   [-1, 1, Conv, [256, 3, 1]],  # 19 (P4/16-medium)
+
+   [[19, 15], 1, Detect, [nc, anchors]],  # Detect(P4, P5)
+  ]

models/hub/yolov3.yaml

@@ -0,0 +1,51 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# darknet53 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [32, 3, 1]],  # 0
+   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2
+   [-1, 1, Bottleneck, [64]],
+   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4
+   [-1, 2, Bottleneck, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 5-P3/8
+   [-1, 8, Bottleneck, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 7-P4/16
+   [-1, 8, Bottleneck, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P5/32
+   [-1, 4, Bottleneck, [1024]],  # 10
+  ]
+
+# YOLOv3 head
+head:
+  [[-1, 1, Bottleneck, [1024, False]],
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [1024, 3, 1]],
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [1024, 3, 1]],  # 15 (P5/32-large)
+
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P4
+   [-1, 1, Bottleneck, [512, False]],
+   [-1, 1, Bottleneck, [512, False]],
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],  # 22 (P4/16-medium)
+
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P3
+   [-1, 1, Bottleneck, [256, False]],
+   [-1, 2, Bottleneck, [256, False]],  # 27 (P3/8-small)
+
+   [[27, 22, 15], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

models/hub/yolov5-bifpn.yaml

@@ -0,0 +1,48 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 BiFPN head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14, 6], 1, Concat, [1]],  # cat P4 <--- BiFPN change
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

models/hub/yolov5-fpn.yaml

@@ -0,0 +1,42 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 FPN head
+head:
+  [[-1, 3, C3, [1024, False]],  # 10 (P5/32-large)
+
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 3, C3, [512, False]],  # 14 (P4/16-medium)
+
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 3, C3, [256, False]],  # 18 (P3/8-small)
+
+   [[18, 14, 10], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

models/hub/yolov5-p2.yaml

@@ -0,0 +1,54 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors: 3  # AutoAnchor evolves 3 anchors per P output layer
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head with (P2, P3, P4, P5) outputs
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 2], 1, Concat, [1]],  # cat backbone P2
+   [-1, 1, C3, [128, False]],  # 21 (P2/4-xsmall)
+
+   [-1, 1, Conv, [128, 3, 2]],
+   [[-1, 18], 1, Concat, [1]],  # cat head P3
+   [-1, 3, C3, [256, False]],  # 24 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 27 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 30 (P5/32-large)
+
+   [[21, 24, 27, 30], 1, Detect, [nc, anchors]],  # Detect(P2, P3, P4, P5)
+  ]

models/hub/yolov5-p34.yaml

@@ -0,0 +1,41 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.50  # layer channel multiple
+anchors: 3  # AutoAnchor evolves 3 anchors per P output layer
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [ [ -1, 1, Conv, [ 64, 6, 2, 2 ] ],  # 0-P1/2
+    [ -1, 1, Conv, [ 128, 3, 2 ] ],  # 1-P2/4
+    [ -1, 3, C3, [ 128 ] ],
+    [ -1, 1, Conv, [ 256, 3, 2 ] ],  # 3-P3/8
+    [ -1, 6, C3, [ 256 ] ],
+    [ -1, 1, Conv, [ 512, 3, 2 ] ],  # 5-P4/16
+    [ -1, 9, C3, [ 512 ] ],
+    [ -1, 1, Conv, [ 1024, 3, 2 ] ],  # 7-P5/32
+    [ -1, 3, C3, [ 1024 ] ],
+    [ -1, 1, SPPF, [ 1024, 5 ] ],  # 9
+  ]
+
+# YOLOv5 v6.0 head with (P3, P4) outputs
+head:
+  [ [ -1, 1, Conv, [ 512, 1, 1 ] ],
+    [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
+    [ [ -1, 6 ], 1, Concat, [ 1 ] ],  # cat backbone P4
+    [ -1, 3, C3, [ 512, False ] ],  # 13
+
+    [ -1, 1, Conv, [ 256, 1, 1 ] ],
+    [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
+    [ [ -1, 4 ], 1, Concat, [ 1 ] ],  # cat backbone P3
+    [ -1, 3, C3, [ 256, False ] ],  # 17 (P3/8-small)
+
+    [ -1, 1, Conv, [ 256, 3, 2 ] ],
+    [ [ -1, 14 ], 1, Concat, [ 1 ] ],  # cat head P4
+    [ -1, 3, C3, [ 512, False ] ],  # 20 (P4/16-medium)
+
+    [ [ 17, 20 ], 1, Detect, [ nc, anchors ] ],  # Detect(P3, P4)
+  ]

models/hub/yolov5-p6.yaml

@@ -0,0 +1,56 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors: 3  # AutoAnchor evolves 3 anchors per P output layer
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [768]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 11
+  ]
+
+# YOLOv5 v6.0 head with (P3, P4, P5, P6) outputs
+head:
+  [[-1, 1, Conv, [768, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
+   [-1, 3, C3, [768, False]],  # 15
+
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 19
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 23 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 20], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 26 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 16], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [768, False]],  # 29 (P5/32-large)
+
+   [-1, 1, Conv, [768, 3, 2]],
+   [[-1, 12], 1, Concat, [1]],  # cat head P6
+   [-1, 3, C3, [1024, False]],  # 32 (P6/64-xlarge)
+
+   [[23, 26, 29, 32], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5, P6)
+  ]

models/hub/yolov5-p7.yaml

@@ -0,0 +1,67 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors: 3  # AutoAnchor evolves 3 anchors per P output layer
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [768]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
+   [-1, 3, C3, [1024]],
+   [-1, 1, Conv, [1280, 3, 2]],  # 11-P7/128
+   [-1, 3, C3, [1280]],
+   [-1, 1, SPPF, [1280, 5]],  # 13
+  ]
+
+# YOLOv5 v6.0 head with (P3, P4, P5, P6, P7) outputs
+head:
+  [[-1, 1, Conv, [1024, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 10], 1, Concat, [1]],  # cat backbone P6
+   [-1, 3, C3, [1024, False]],  # 17
+
+   [-1, 1, Conv, [768, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
+   [-1, 3, C3, [768, False]],  # 21
+
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 25
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 29 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 26], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 32 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 22], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [768, False]],  # 35 (P5/32-large)
+
+   [-1, 1, Conv, [768, 3, 2]],
+   [[-1, 18], 1, Concat, [1]],  # cat head P6
+   [-1, 3, C3, [1024, False]],  # 38 (P6/64-xlarge)
+
+   [-1, 1, Conv, [1024, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P7
+   [-1, 3, C3, [1280, False]],  # 41 (P7/128-xxlarge)
+
+   [[29, 32, 35, 38, 41], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5, P6, P7)
+  ]

models/hub/yolov5-panet.yaml

@@ -0,0 +1,48 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 PANet head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

models/hub/yolov5l6.yaml

@@ -0,0 +1,60 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors:
+  - [19,27,  44,40,  38,94]  # P3/8
+  - [96,68,  86,152,  180,137]  # P4/16
+  - [140,301,  303,264,  238,542]  # P5/32
+  - [436,615,  739,380,  925,792]  # P6/64
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [768]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 11
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [768, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
+   [-1, 3, C3, [768, False]],  # 15
+
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 19
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 23 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 20], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 26 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 16], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [768, False]],  # 29 (P5/32-large)
+
+   [-1, 1, Conv, [768, 3, 2]],
+   [[-1, 12], 1, Concat, [1]],  # cat head P6
+   [-1, 3, C3, [1024, False]],  # 32 (P6/64-xlarge)
+
+   [[23, 26, 29, 32], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5, P6)
+  ]

models/hub/yolov5m6.yaml

@@ -0,0 +1,60 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.67  # model depth multiple
+width_multiple: 0.75  # layer channel multiple
+anchors:
+  - [19,27,  44,40,  38,94]  # P3/8
+  - [96,68,  86,152,  180,137]  # P4/16
+  - [140,301,  303,264,  238,542]  # P5/32
+  - [436,615,  739,380,  925,792]  # P6/64
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [768]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 11
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [768, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
+   [-1, 3, C3, [768, False]],  # 15
+
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 19
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 23 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 20], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 26 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 16], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [768, False]],  # 29 (P5/32-large)
+
+   [-1, 1, Conv, [768, 3, 2]],
+   [[-1, 12], 1, Concat, [1]],  # cat head P6
+   [-1, 3, C3, [1024, False]],  # 32 (P6/64-xlarge)
+
+   [[23, 26, 29, 32], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5, P6)
+  ]

models/hub/yolov5n6.yaml

@@ -0,0 +1,60 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.25  # layer channel multiple
+anchors:
+  - [19,27,  44,40,  38,94]  # P3/8
+  - [96,68,  86,152,  180,137]  # P4/16
+  - [140,301,  303,264,  238,542]  # P5/32
+  - [436,615,  739,380,  925,792]  # P6/64
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [768]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 11
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [768, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
+   [-1, 3, C3, [768, False]],  # 15
+
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 19
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 23 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 20], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 26 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 16], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [768, False]],  # 29 (P5/32-large)
+
+   [-1, 1, Conv, [768, 3, 2]],
+   [[-1, 12], 1, Concat, [1]],  # cat head P6
+   [-1, 3, C3, [1024, False]],  # 32 (P6/64-xlarge)
+
+   [[23, 26, 29, 32], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5, P6)
+  ]

models/hub/yolov5s-LeakyReLU.yaml

@@ -0,0 +1,49 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+activation: nn.LeakyReLU(0.1)  # <----- Conv() activation used throughout entire YOLOv5 model
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.50  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

models/hub/yolov5s-ghost.yaml

@@ -0,0 +1,48 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.50  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, GhostConv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3Ghost, [128]],
+   [-1, 1, GhostConv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3Ghost, [256]],
+   [-1, 1, GhostConv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3Ghost, [512]],
+   [-1, 1, GhostConv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3Ghost, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, GhostConv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3Ghost, [512, False]],  # 13
+
+   [-1, 1, GhostConv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3Ghost, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, GhostConv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3Ghost, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, GhostConv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3Ghost, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

models/hub/yolov5s-transformer.yaml

@@ -0,0 +1,48 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.50  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3TR, [1024]],  # 9 <--- C3TR() Transformer module
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

models/hub/yolov5s6.yaml

@@ -0,0 +1,60 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.50  # layer channel multiple
+anchors:
+  - [19,27,  44,40,  38,94]  # P3/8
+  - [96,68,  86,152,  180,137]  # P4/16
+  - [140,301,  303,264,  238,542]  # P5/32
+  - [436,615,  739,380,  925,792]  # P6/64
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [768]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 11
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [768, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
+   [-1, 3, C3, [768, False]],  # 15
+
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 19
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 23 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 20], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 26 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 16], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [768, False]],  # 29 (P5/32-large)
+
+   [-1, 1, Conv, [768, 3, 2]],
+   [[-1, 12], 1, Concat, [1]],  # cat head P6
+   [-1, 3, C3, [1024, False]],  # 32 (P6/64-xlarge)
+
+   [[23, 26, 29, 32], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5, P6)
+  ]

models/hub/yolov5x6.yaml

@@ -0,0 +1,60 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.33  # model depth multiple
+width_multiple: 1.25  # layer channel multiple
+anchors:
+  - [19,27,  44,40,  38,94]  # P3/8
+  - [96,68,  86,152,  180,137]  # P4/16
+  - [140,301,  303,264,  238,542]  # P5/32
+  - [436,615,  739,380,  925,792]  # P6/64
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [768]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 11
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [768, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
+   [-1, 3, C3, [768, False]],  # 15
+
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 19
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 23 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 20], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 26 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 16], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [768, False]],  # 29 (P5/32-large)
+
+   [-1, 1, Conv, [768, 3, 2]],
+   [[-1, 12], 1, Concat, [1]],  # cat head P6
+   [-1, 3, C3, [1024, False]],  # 32 (P6/64-xlarge)
+
+   [[23, 26, 29, 32], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5, P6)
+  ]

models/segment/yolov5l-seg.yaml

@@ -0,0 +1,48 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Segment, [nc, anchors, 32, 256]],  # Detect(P3, P4, P5)
+  ]

models/segment/yolov5m-seg.yaml

@@ -0,0 +1,48 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.67  # model depth multiple
+width_multiple: 0.75  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Segment, [nc, anchors, 32, 256]],  # Detect(P3, P4, P5)
+  ]

models/segment/yolov5n-seg.yaml

@@ -0,0 +1,48 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.25  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Segment, [nc, anchors, 32, 256]],  # Detect(P3, P4, P5)
+  ]

models/segment/yolov5s-seg.yaml

@@ -0,0 +1,48 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.5  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Segment, [nc, anchors, 32, 256]],  # Detect(P3, P4, P5)
+  ]

models/segment/yolov5x-seg.yaml

@@ -0,0 +1,48 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.33  # model depth multiple
+width_multiple: 1.25  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Segment, [nc, anchors, 32, 256]],  # Detect(P3, P4, P5)
+  ]

models/tf.py

@@ -0,0 +1,608 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+"""
+TensorFlow, Keras and TFLite versions of YOLOv5
+Authored by https://github.com/zldrobit in PR https://github.com/ultralytics/yolov5/pull/1127
+
+Usage:
+    $ python models/tf.py --weights yolov5s.pt
+
+Export:
+    $ python export.py --weights yolov5s.pt --include saved_model pb tflite tfjs
+"""
+
+import argparse
+import sys
+from copy import deepcopy
+from pathlib import Path
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[1]  # YOLOv5 root directory
+if str(ROOT) not in sys.path:
+    sys.path.append(str(ROOT))  # add ROOT to PATH
+# ROOT = ROOT.relative_to(Path.cwd())  # relative
+
+import numpy as np
+import tensorflow as tf
+import torch
+import torch.nn as nn
+from tensorflow import keras
+
+from models.common import (C3, SPP, SPPF, Bottleneck, BottleneckCSP, C3x, Concat, Conv, CrossConv, DWConv,
+                           DWConvTranspose2d, Focus, autopad)
+from models.experimental import MixConv2d, attempt_load
+from models.yolo import Detect, Segment
+from utils.activations import SiLU
+from utils.general import LOGGER, make_divisible, print_args
+
+
+class TFBN(keras.layers.Layer):
+    # TensorFlow BatchNormalization wrapper
+    def __init__(self, w=None):
+        super().__init__()
+        self.bn = keras.layers.BatchNormalization(
+            beta_initializer=keras.initializers.Constant(w.bias.numpy()),
+            gamma_initializer=keras.initializers.Constant(w.weight.numpy()),
+            moving_mean_initializer=keras.initializers.Constant(w.running_mean.numpy()),
+            moving_variance_initializer=keras.initializers.Constant(w.running_var.numpy()),
+            epsilon=w.eps)
+
+    def call(self, inputs):
+        return self.bn(inputs)
+
+
+class TFPad(keras.layers.Layer):
+    # Pad inputs in spatial dimensions 1 and 2
+    def __init__(self, pad):
+        super().__init__()
+        if isinstance(pad, int):
+            self.pad = tf.constant([[0, 0], [pad, pad], [pad, pad], [0, 0]])
+        else:  # tuple/list
+            self.pad = tf.constant([[0, 0], [pad[0], pad[0]], [pad[1], pad[1]], [0, 0]])
+
+    def call(self, inputs):
+        return tf.pad(inputs, self.pad, mode='constant', constant_values=0)
+
+
+class TFConv(keras.layers.Layer):
+    # Standard convolution
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True, w=None):
+        # ch_in, ch_out, weights, kernel, stride, padding, groups
+        super().__init__()
+        assert g == 1, "TF v2.2 Conv2D does not support 'groups' argument"
+        # TensorFlow convolution padding is inconsistent with PyTorch (e.g. k=3 s=2 'SAME' padding)
+        # see https://stackoverflow.com/questions/52975843/comparing-conv2d-with-padding-between-tensorflow-and-pytorch
+        conv = keras.layers.Conv2D(
+            filters=c2,
+            kernel_size=k,
+            strides=s,
+            padding='SAME' if s == 1 else 'VALID',
+            use_bias=not hasattr(w, 'bn'),
+            kernel_initializer=keras.initializers.Constant(w.conv.weight.permute(2, 3, 1, 0).numpy()),
+            bias_initializer='zeros' if hasattr(w, 'bn') else keras.initializers.Constant(w.conv.bias.numpy()))
+        self.conv = conv if s == 1 else keras.Sequential([TFPad(autopad(k, p)), conv])
+        self.bn = TFBN(w.bn) if hasattr(w, 'bn') else tf.identity
+        self.act = activations(w.act) if act else tf.identity
+
+    def call(self, inputs):
+        return self.act(self.bn(self.conv(inputs)))
+
+
+class TFDWConv(keras.layers.Layer):
+    # Depthwise convolution
+    def __init__(self, c1, c2, k=1, s=1, p=None, act=True, w=None):
+        # ch_in, ch_out, weights, kernel, stride, padding, groups
+        super().__init__()
+        assert c2 % c1 == 0, f'TFDWConv() output={c2} must be a multiple of input={c1} channels'
+        conv = keras.layers.DepthwiseConv2D(
+            kernel_size=k,
+            depth_multiplier=c2 // c1,
+            strides=s,
+            padding='SAME' if s == 1 else 'VALID',
+            use_bias=not hasattr(w, 'bn'),
+            depthwise_initializer=keras.initializers.Constant(w.conv.weight.permute(2, 3, 1, 0).numpy()),
+            bias_initializer='zeros' if hasattr(w, 'bn') else keras.initializers.Constant(w.conv.bias.numpy()))
+        self.conv = conv if s == 1 else keras.Sequential([TFPad(autopad(k, p)), conv])
+        self.bn = TFBN(w.bn) if hasattr(w, 'bn') else tf.identity
+        self.act = activations(w.act) if act else tf.identity
+
+    def call(self, inputs):
+        return self.act(self.bn(self.conv(inputs)))
+
+
+class TFDWConvTranspose2d(keras.layers.Layer):
+    # Depthwise ConvTranspose2d
+    def __init__(self, c1, c2, k=1, s=1, p1=0, p2=0, w=None):
+        # ch_in, ch_out, weights, kernel, stride, padding, groups
+        super().__init__()
+        assert c1 == c2, f'TFDWConv() output={c2} must be equal to input={c1} channels'
+        assert k == 4 and p1 == 1, 'TFDWConv() only valid for k=4 and p1=1'
+        weight, bias = w.weight.permute(2, 3, 1, 0).numpy(), w.bias.numpy()
+        self.c1 = c1
+        self.conv = [
+            keras.layers.Conv2DTranspose(filters=1,
+                                         kernel_size=k,
+                                         strides=s,
+                                         padding='VALID',
+                                         output_padding=p2,
+                                         use_bias=True,
+                                         kernel_initializer=keras.initializers.Constant(weight[..., i:i + 1]),
+                                         bias_initializer=keras.initializers.Constant(bias[i])) for i in range(c1)]
+
+    def call(self, inputs):
+        return tf.concat([m(x) for m, x in zip(self.conv, tf.split(inputs, self.c1, 3))], 3)[:, 1:-1, 1:-1]
+
+
+class TFFocus(keras.layers.Layer):
+    # Focus wh information into c-space
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True, w=None):
+        # ch_in, ch_out, kernel, stride, padding, groups
+        super().__init__()
+        self.conv = TFConv(c1 * 4, c2, k, s, p, g, act, w.conv)
+
+    def call(self, inputs):  # x(b,w,h,c) -> y(b,w/2,h/2,4c)
+        # inputs = inputs / 255  # normalize 0-255 to 0-1
+        inputs = [inputs[:, ::2, ::2, :], inputs[:, 1::2, ::2, :], inputs[:, ::2, 1::2, :], inputs[:, 1::2, 1::2, :]]
+        return self.conv(tf.concat(inputs, 3))
+
+
+class TFBottleneck(keras.layers.Layer):
+    # Standard bottleneck
+    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5, w=None):  # ch_in, ch_out, shortcut, groups, expansion
+        super().__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
+        self.cv2 = TFConv(c_, c2, 3, 1, g=g, w=w.cv2)
+        self.add = shortcut and c1 == c2
+
+    def call(self, inputs):
+        return inputs + self.cv2(self.cv1(inputs)) if self.add else self.cv2(self.cv1(inputs))
+
+
+class TFCrossConv(keras.layers.Layer):
+    # Cross Convolution
+    def __init__(self, c1, c2, k=3, s=1, g=1, e=1.0, shortcut=False, w=None):
+        super().__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = TFConv(c1, c_, (1, k), (1, s), w=w.cv1)
+        self.cv2 = TFConv(c_, c2, (k, 1), (s, 1), g=g, w=w.cv2)
+        self.add = shortcut and c1 == c2
+
+    def call(self, inputs):
+        return inputs + self.cv2(self.cv1(inputs)) if self.add else self.cv2(self.cv1(inputs))
+
+
+class TFConv2d(keras.layers.Layer):
+    # Substitution for PyTorch nn.Conv2D
+    def __init__(self, c1, c2, k, s=1, g=1, bias=True, w=None):
+        super().__init__()
+        assert g == 1, "TF v2.2 Conv2D does not support 'groups' argument"
+        self.conv = keras.layers.Conv2D(filters=c2,
+                                        kernel_size=k,
+                                        strides=s,
+                                        padding='VALID',
+                                        use_bias=bias,
+                                        kernel_initializer=keras.initializers.Constant(
+                                            w.weight.permute(2, 3, 1, 0).numpy()),
+                                        bias_initializer=keras.initializers.Constant(w.bias.numpy()) if bias else None)
+
+    def call(self, inputs):
+        return self.conv(inputs)
+
+
+class TFBottleneckCSP(keras.layers.Layer):
+    # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, w=None):
+        # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
+        self.cv2 = TFConv2d(c1, c_, 1, 1, bias=False, w=w.cv2)
+        self.cv3 = TFConv2d(c_, c_, 1, 1, bias=False, w=w.cv3)
+        self.cv4 = TFConv(2 * c_, c2, 1, 1, w=w.cv4)
+        self.bn = TFBN(w.bn)
+        self.act = lambda x: keras.activations.swish(x)
+        self.m = keras.Sequential([TFBottleneck(c_, c_, shortcut, g, e=1.0, w=w.m[j]) for j in range(n)])
+
+    def call(self, inputs):
+        y1 = self.cv3(self.m(self.cv1(inputs)))
+        y2 = self.cv2(inputs)
+        return self.cv4(self.act(self.bn(tf.concat((y1, y2), axis=3))))
+
+
+class TFC3(keras.layers.Layer):
+    # CSP Bottleneck with 3 convolutions
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, w=None):
+        # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
+        self.cv2 = TFConv(c1, c_, 1, 1, w=w.cv2)
+        self.cv3 = TFConv(2 * c_, c2, 1, 1, w=w.cv3)
+        self.m = keras.Sequential([TFBottleneck(c_, c_, shortcut, g, e=1.0, w=w.m[j]) for j in range(n)])
+
+    def call(self, inputs):
+        return self.cv3(tf.concat((self.m(self.cv1(inputs)), self.cv2(inputs)), axis=3))
+
+
+class TFC3x(keras.layers.Layer):
+    # 3 module with cross-convolutions
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, w=None):
+        # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
+        self.cv2 = TFConv(c1, c_, 1, 1, w=w.cv2)
+        self.cv3 = TFConv(2 * c_, c2, 1, 1, w=w.cv3)
+        self.m = keras.Sequential([
+            TFCrossConv(c_, c_, k=3, s=1, g=g, e=1.0, shortcut=shortcut, w=w.m[j]) for j in range(n)])
+
+    def call(self, inputs):
+        return self.cv3(tf.concat((self.m(self.cv1(inputs)), self.cv2(inputs)), axis=3))
+
+
+class TFSPP(keras.layers.Layer):
+    # Spatial pyramid pooling layer used in YOLOv3-SPP
+    def __init__(self, c1, c2, k=(5, 9, 13), w=None):
+        super().__init__()
+        c_ = c1 // 2  # hidden channels
+        self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
+        self.cv2 = TFConv(c_ * (len(k) + 1), c2, 1, 1, w=w.cv2)
+        self.m = [keras.layers.MaxPool2D(pool_size=x, strides=1, padding='SAME') for x in k]
+
+    def call(self, inputs):
+        x = self.cv1(inputs)
+        return self.cv2(tf.concat([x] + [m(x) for m in self.m], 3))
+
+
+class TFSPPF(keras.layers.Layer):
+    # Spatial pyramid pooling-Fast layer
+    def __init__(self, c1, c2, k=5, w=None):
+        super().__init__()
+        c_ = c1 // 2  # hidden channels
+        self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
+        self.cv2 = TFConv(c_ * 4, c2, 1, 1, w=w.cv2)
+        self.m = keras.layers.MaxPool2D(pool_size=k, strides=1, padding='SAME')
+
+    def call(self, inputs):
+        x = self.cv1(inputs)
+        y1 = self.m(x)
+        y2 = self.m(y1)
+        return self.cv2(tf.concat([x, y1, y2, self.m(y2)], 3))
+
+
+class TFDetect(keras.layers.Layer):
+    # TF YOLOv5 Detect layer
+    def __init__(self, nc=80, anchors=(), ch=(), imgsz=(640, 640), w=None):  # detection layer
+        super().__init__()
+        self.stride = tf.convert_to_tensor(w.stride.numpy(), dtype=tf.float32)
+        self.nc = nc  # number of classes
+        self.no = nc + 5  # number of outputs per anchor
+        self.nl = len(anchors)  # number of detection layers
+        self.na = len(anchors[0]) // 2  # number of anchors
+        self.grid = [tf.zeros(1)] * self.nl  # init grid
+        self.anchors = tf.convert_to_tensor(w.anchors.numpy(), dtype=tf.float32)
+        self.anchor_grid = tf.reshape(self.anchors * tf.reshape(self.stride, [self.nl, 1, 1]), [self.nl, 1, -1, 1, 2])
+        self.m = [TFConv2d(x, self.no * self.na, 1, w=w.m[i]) for i, x in enumerate(ch)]
+        self.training = False  # set to False after building model
+        self.imgsz = imgsz
+        for i in range(self.nl):
+            ny, nx = self.imgsz[0] // self.stride[i], self.imgsz[1] // self.stride[i]
+            self.grid[i] = self._make_grid(nx, ny)
+
+    def call(self, inputs):
+        z = []  # inference output
+        x = []
+        for i in range(self.nl):
+            x.append(self.m[i](inputs[i]))
+            # x(bs,20,20,255) to x(bs,3,20,20,85)
+            ny, nx = self.imgsz[0] // self.stride[i], self.imgsz[1] // self.stride[i]
+            x[i] = tf.reshape(x[i], [-1, ny * nx, self.na, self.no])
+
+            if not self.training:  # inference
+                y = x[i]
+                grid = tf.transpose(self.grid[i], [0, 2, 1, 3]) - 0.5
+                anchor_grid = tf.transpose(self.anchor_grid[i], [0, 2, 1, 3]) * 4
+                xy = (tf.sigmoid(y[..., 0:2]) * 2 + grid) * self.stride[i]  # xy
+                wh = tf.sigmoid(y[..., 2:4]) ** 2 * anchor_grid
+                # Normalize xywh to 0-1 to reduce calibration error
+                xy /= tf.constant([[self.imgsz[1], self.imgsz[0]]], dtype=tf.float32)
+                wh /= tf.constant([[self.imgsz[1], self.imgsz[0]]], dtype=tf.float32)
+                y = tf.concat([xy, wh, tf.sigmoid(y[..., 4:5 + self.nc]), y[..., 5 + self.nc:]], -1)
+                z.append(tf.reshape(y, [-1, self.na * ny * nx, self.no]))
+
+        return tf.transpose(x, [0, 2, 1, 3]) if self.training else (tf.concat(z, 1), )
+
+    @staticmethod
+    def _make_grid(nx=20, ny=20):
+        # yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)])
+        # return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float()
+        xv, yv = tf.meshgrid(tf.range(nx), tf.range(ny))
+        return tf.cast(tf.reshape(tf.stack([xv, yv], 2), [1, 1, ny * nx, 2]), dtype=tf.float32)
+
+
+class TFSegment(TFDetect):
+    # YOLOv5 Segment head for segmentation models
+    def __init__(self, nc=80, anchors=(), nm=32, npr=256, ch=(), imgsz=(640, 640), w=None):
+        super().__init__(nc, anchors, ch, imgsz, w)
+        self.nm = nm  # number of masks
+        self.npr = npr  # number of protos
+        self.no = 5 + nc + self.nm  # number of outputs per anchor
+        self.m = [TFConv2d(x, self.no * self.na, 1, w=w.m[i]) for i, x in enumerate(ch)]  # output conv
+        self.proto = TFProto(ch[0], self.npr, self.nm, w=w.proto)  # protos
+        self.detect = TFDetect.call
+
+    def call(self, x):
+        p = self.proto(x[0])
+        # p = TFUpsample(None, scale_factor=4, mode='nearest')(self.proto(x[0]))  # (optional) full-size protos
+        p = tf.transpose(p, [0, 3, 1, 2])  # from shape(1,160,160,32) to shape(1,32,160,160)
+        x = self.detect(self, x)
+        return (x, p) if self.training else (x[0], p)
+
+
+class TFProto(keras.layers.Layer):
+
+    def __init__(self, c1, c_=256, c2=32, w=None):
+        super().__init__()
+        self.cv1 = TFConv(c1, c_, k=3, w=w.cv1)
+        self.upsample = TFUpsample(None, scale_factor=2, mode='nearest')
+        self.cv2 = TFConv(c_, c_, k=3, w=w.cv2)
+        self.cv3 = TFConv(c_, c2, w=w.cv3)
+
+    def call(self, inputs):
+        return self.cv3(self.cv2(self.upsample(self.cv1(inputs))))
+
+
+class TFUpsample(keras.layers.Layer):
+    # TF version of torch.nn.Upsample()
+    def __init__(self, size, scale_factor, mode, w=None):  # warning: all arguments needed including 'w'
+        super().__init__()
+        assert scale_factor % 2 == 0, 'scale_factor must be multiple of 2'
+        self.upsample = lambda x: tf.image.resize(x, (x.shape[1] * scale_factor, x.shape[2] * scale_factor), mode)
+        # self.upsample = keras.layers.UpSampling2D(size=scale_factor, interpolation=mode)
+        # with default arguments: align_corners=False, half_pixel_centers=False
+        # self.upsample = lambda x: tf.raw_ops.ResizeNearestNeighbor(images=x,
+        #                                                            size=(x.shape[1] * 2, x.shape[2] * 2))
+
+    def call(self, inputs):
+        return self.upsample(inputs)
+
+
+class TFConcat(keras.layers.Layer):
+    # TF version of torch.concat()
+    def __init__(self, dimension=1, w=None):
+        super().__init__()
+        assert dimension == 1, 'convert only NCHW to NHWC concat'
+        self.d = 3
+
+    def call(self, inputs):
+        return tf.concat(inputs, self.d)
+
+
+def parse_model(d, ch, model, imgsz):  # model_dict, input_channels(3)
+    LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10}  {'module':<40}{'arguments':<30}")
+    anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
+    na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors  # number of anchors
+    no = na * (nc + 5)  # number of outputs = anchors * (classes + 5)
+
+    layers, save, c2 = [], [], ch[-1]  # layers, savelist, ch out
+    for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):  # from, number, module, args
+        m_str = m
+        m = eval(m) if isinstance(m, str) else m  # eval strings
+        for j, a in enumerate(args):
+            try:
+                args[j] = eval(a) if isinstance(a, str) else a  # eval strings
+            except NameError:
+                pass
+
+        n = max(round(n * gd), 1) if n > 1 else n  # depth gain
+        if m in [
+                nn.Conv2d, Conv, DWConv, DWConvTranspose2d, Bottleneck, SPP, SPPF, MixConv2d, Focus, CrossConv,
+                BottleneckCSP, C3, C3x]:
+            c1, c2 = ch[f], args[0]
+            c2 = make_divisible(c2 * gw, 8) if c2 != no else c2
+
+            args = [c1, c2, *args[1:]]
+            if m in [BottleneckCSP, C3, C3x]:
+                args.insert(2, n)
+                n = 1
+        elif m is nn.BatchNorm2d:
+            args = [ch[f]]
+        elif m is Concat:
+            c2 = sum(ch[-1 if x == -1 else x + 1] for x in f)
+        elif m in [Detect, Segment]:
+            args.append([ch[x + 1] for x in f])
+            if isinstance(args[1], int):  # number of anchors
+                args[1] = [list(range(args[1] * 2))] * len(f)
+            if m is Segment:
+                args[3] = make_divisible(args[3] * gw, 8)
+            args.append(imgsz)
+        else:
+            c2 = ch[f]
+
+        tf_m = eval('TF' + m_str.replace('nn.', ''))
+        m_ = keras.Sequential([tf_m(*args, w=model.model[i][j]) for j in range(n)]) if n > 1 \
+            else tf_m(*args, w=model.model[i])  # module
+
+        torch_m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args)  # module
+        t = str(m)[8:-2].replace('__main__.', '')  # module type
+        np = sum(x.numel() for x in torch_m_.parameters())  # number params
+        m_.i, m_.f, m_.type, m_.np = i, f, t, np  # attach index, 'from' index, type, number params
+        LOGGER.info(f'{i:>3}{str(f):>18}{str(n):>3}{np:>10}  {t:<40}{str(args):<30}')  # print
+        save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1)  # append to savelist
+        layers.append(m_)
+        ch.append(c2)
+    return keras.Sequential(layers), sorted(save)
+
+
+class TFModel:
+    # TF YOLOv5 model
+    def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, model=None, imgsz=(640, 640)):  # model, channels, classes
+        super().__init__()
+        if isinstance(cfg, dict):
+            self.yaml = cfg  # model dict
+        else:  # is *.yaml
+            import yaml  # for torch hub
+            self.yaml_file = Path(cfg).name
+            with open(cfg) as f:
+                self.yaml = yaml.load(f, Loader=yaml.FullLoader)  # model dict
+
+        # Define model
+        if nc and nc != self.yaml['nc']:
+            LOGGER.info(f"Overriding {cfg} nc={self.yaml['nc']} with nc={nc}")
+            self.yaml['nc'] = nc  # override yaml value
+        self.model, self.savelist = parse_model(deepcopy(self.yaml), ch=[ch], model=model, imgsz=imgsz)
+
+    def predict(self,
+                inputs,
+                tf_nms=False,
+                agnostic_nms=False,
+                topk_per_class=100,
+                topk_all=100,
+                iou_thres=0.45,
+                conf_thres=0.25):
+        y = []  # outputs
+        x = inputs
+        for m in self.model.layers:
+            if m.f != -1:  # if not from previous layer
+                x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f]  # from earlier layers
+
+            x = m(x)  # run
+            y.append(x if m.i in self.savelist else None)  # save output
+
+        # Add TensorFlow NMS
+        if tf_nms:
+            boxes = self._xywh2xyxy(x[0][..., :4])
+            probs = x[0][:, :, 4:5]
+            classes = x[0][:, :, 5:]
+            scores = probs * classes
+            if agnostic_nms:
+                nms = AgnosticNMS()((boxes, classes, scores), topk_all, iou_thres, conf_thres)
+            else:
+                boxes = tf.expand_dims(boxes, 2)
+                nms = tf.image.combined_non_max_suppression(boxes,
+                                                            scores,
+                                                            topk_per_class,
+                                                            topk_all,
+                                                            iou_thres,
+                                                            conf_thres,
+                                                            clip_boxes=False)
+            return (nms, )
+        return x  # output [1,6300,85] = [xywh, conf, class0, class1, ...]
+        # x = x[0]  # [x(1,6300,85), ...] to x(6300,85)
+        # xywh = x[..., :4]  # x(6300,4) boxes
+        # conf = x[..., 4:5]  # x(6300,1) confidences
+        # cls = tf.reshape(tf.cast(tf.argmax(x[..., 5:], axis=1), tf.float32), (-1, 1))  # x(6300,1)  classes
+        # return tf.concat([conf, cls, xywh], 1)
+
+    @staticmethod
+    def _xywh2xyxy(xywh):
+        # Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
+        x, y, w, h = tf.split(xywh, num_or_size_splits=4, axis=-1)
+        return tf.concat([x - w / 2, y - h / 2, x + w / 2, y + h / 2], axis=-1)
+
+
+class AgnosticNMS(keras.layers.Layer):
+    # TF Agnostic NMS
+    def call(self, input, topk_all, iou_thres, conf_thres):
+        # wrap map_fn to avoid TypeSpec related error https://stackoverflow.com/a/65809989/3036450
+        return tf.map_fn(lambda x: self._nms(x, topk_all, iou_thres, conf_thres),
+                         input,
+                         fn_output_signature=(tf.float32, tf.float32, tf.float32, tf.int32),
+                         name='agnostic_nms')
+
+    @staticmethod
+    def _nms(x, topk_all=100, iou_thres=0.45, conf_thres=0.25):  # agnostic NMS
+        boxes, classes, scores = x
+        class_inds = tf.cast(tf.argmax(classes, axis=-1), tf.float32)
+        scores_inp = tf.reduce_max(scores, -1)
+        selected_inds = tf.image.non_max_suppression(boxes,
+                                                     scores_inp,
+                                                     max_output_size=topk_all,
+                                                     iou_threshold=iou_thres,
+                                                     score_threshold=conf_thres)
+        selected_boxes = tf.gather(boxes, selected_inds)
+        padded_boxes = tf.pad(selected_boxes,
+                              paddings=[[0, topk_all - tf.shape(selected_boxes)[0]], [0, 0]],
+                              mode='CONSTANT',
+                              constant_values=0.0)
+        selected_scores = tf.gather(scores_inp, selected_inds)
+        padded_scores = tf.pad(selected_scores,
+                               paddings=[[0, topk_all - tf.shape(selected_boxes)[0]]],
+                               mode='CONSTANT',
+                               constant_values=-1.0)
+        selected_classes = tf.gather(class_inds, selected_inds)
+        padded_classes = tf.pad(selected_classes,
+                                paddings=[[0, topk_all - tf.shape(selected_boxes)[0]]],
+                                mode='CONSTANT',
+                                constant_values=-1.0)
+        valid_detections = tf.shape(selected_inds)[0]
+        return padded_boxes, padded_scores, padded_classes, valid_detections
+
+
+def activations(act=nn.SiLU):
+    # Returns TF activation from input PyTorch activation
+    if isinstance(act, nn.LeakyReLU):
+        return lambda x: keras.activations.relu(x, alpha=0.1)
+    elif isinstance(act, nn.Hardswish):
+        return lambda x: x * tf.nn.relu6(x + 3) * 0.166666667
+    elif isinstance(act, (nn.SiLU, SiLU)):
+        return lambda x: keras.activations.swish(x)
+    else:
+        raise Exception(f'no matching TensorFlow activation found for PyTorch activation {act}')
+
+
+def representative_dataset_gen(dataset, ncalib=100):
+    # Representative dataset generator for use with converter.representative_dataset, returns a generator of np arrays
+    for n, (path, img, im0s, vid_cap, string) in enumerate(dataset):
+        im = np.transpose(img, [1, 2, 0])
+        im = np.expand_dims(im, axis=0).astype(np.float32)
+        im /= 255
+        yield [im]
+        if n >= ncalib:
+            break
+
+
+def run(
+        weights=ROOT / 'yolov5s.pt',  # weights path
+        imgsz=(640, 640),  # inference size h,w
+        batch_size=1,  # batch size
+        dynamic=False,  # dynamic batch size
+):
+    # PyTorch model
+    im = torch.zeros((batch_size, 3, *imgsz))  # BCHW image
+    model = attempt_load(weights, device=torch.device('cpu'), inplace=True, fuse=False)
+    _ = model(im)  # inference
+    model.info()
+
+    # TensorFlow model
+    im = tf.zeros((batch_size, *imgsz, 3))  # BHWC image
+    tf_model = TFModel(cfg=model.yaml, model=model, nc=model.nc, imgsz=imgsz)
+    _ = tf_model.predict(im)  # inference
+
+    # Keras model
+    im = keras.Input(shape=(*imgsz, 3), batch_size=None if dynamic else batch_size)
+    keras_model = keras.Model(inputs=im, outputs=tf_model.predict(im))
+    keras_model.summary()
+
+    LOGGER.info('PyTorch, TensorFlow and Keras models successfully verified.\nUse export.py for TF model export.')
+
+
+def parse_opt():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.pt', help='weights path')
+    parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')
+    parser.add_argument('--batch-size', type=int, default=1, help='batch size')
+    parser.add_argument('--dynamic', action='store_true', help='dynamic batch size')
+    opt = parser.parse_args()
+    opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1  # expand
+    print_args(vars(opt))
+    return opt
+
+
+def main(opt):
+    run(**vars(opt))
+
+
+if __name__ == '__main__':
+    opt = parse_opt()
+    main(opt)

models/yolo.py

@@ -0,0 +1,391 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+"""
+YOLO-specific modules
+
+Usage:
+    $ python models/yolo.py --cfg yolov5s.yaml
+"""
+
+import argparse
+import contextlib
+import os
+import platform
+import sys
+from copy import deepcopy
+from pathlib import Path
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[1]  # YOLOv5 root directory
+if str(ROOT) not in sys.path:
+    sys.path.append(str(ROOT))  # add ROOT to PATH
+if platform.system() != 'Windows':
+    ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative
+
+from models.common import *  # noqa
+from models.experimental import *  # noqa
+from utils.autoanchor import check_anchor_order
+from utils.general import LOGGER, check_version, check_yaml, make_divisible, print_args
+from utils.plots import feature_visualization
+from utils.torch_utils import (fuse_conv_and_bn, initialize_weights, model_info, profile, scale_img, select_device,
+                               time_sync)
+
+try:
+    import thop  # for FLOPs computation
+except ImportError:
+    thop = None
+
+
+class Detect(nn.Module):
+    # YOLOv5 Detect head for detection models
+    stride = None  # strides computed during build
+    dynamic = False  # force grid reconstruction
+    export = False  # export mode
+
+    def __init__(self, nc=80, anchors=(), ch=(), inplace=True):  # detection layer
+        super().__init__()
+        self.nc = nc  # number of classes
+        self.no = nc + 5  # number of outputs per anchor
+        self.nl = len(anchors)  # number of detection layers
+        self.na = len(anchors[0]) // 2  # number of anchors
+        self.grid = [torch.empty(0) for _ in range(self.nl)]  # init grid
+        self.anchor_grid = [torch.empty(0) for _ in range(self.nl)]  # init anchor grid
+        self.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl, -1, 2))  # shape(nl,na,2)
+        self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch)  # output conv
+        self.inplace = inplace  # use inplace ops (e.g. slice assignment)
+
+    def forward(self, x):
+        z = []  # inference output
+        for i in range(self.nl):
+            x[i] = self.m[i](x[i])  # conv
+            bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
+            x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
+
+            if not self.training:  # inference
+                if self.dynamic or self.grid[i].shape[2:4] != x[i].shape[2:4]:
+                    self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)
+
+                if isinstance(self, Segment):  # (boxes + masks)
+                    xy, wh, conf, mask = x[i].split((2, 2, self.nc + 1, self.no - self.nc - 5), 4)
+                    xy = (xy.sigmoid() * 2 + self.grid[i]) * self.stride[i]  # xy
+                    wh = (wh.sigmoid() * 2) ** 2 * self.anchor_grid[i]  # wh
+                    y = torch.cat((xy, wh, conf.sigmoid(), mask), 4)
+                else:  # Detect (boxes only)
+                    xy, wh, conf = x[i].sigmoid().split((2, 2, self.nc + 1), 4)
+                    xy = (xy * 2 + self.grid[i]) * self.stride[i]  # xy
+                    wh = (wh * 2) ** 2 * self.anchor_grid[i]  # wh
+                    y = torch.cat((xy, wh, conf), 4)
+                z.append(y.view(bs, self.na * nx * ny, self.no))
+
+        return x if self.training else (torch.cat(z, 1), ) if self.export else (torch.cat(z, 1), x)
+
+    def _make_grid(self, nx=20, ny=20, i=0, torch_1_10=check_version(torch.__version__, '1.10.0')):
+        d = self.anchors[i].device
+        t = self.anchors[i].dtype
+        shape = 1, self.na, ny, nx, 2  # grid shape
+        y, x = torch.arange(ny, device=d, dtype=t), torch.arange(nx, device=d, dtype=t)
+        yv, xv = torch.meshgrid(y, x, indexing='ij') if torch_1_10 else torch.meshgrid(y, x)  # torch>=0.7 compatibility
+        grid = torch.stack((xv, yv), 2).expand(shape) - 0.5  # add grid offset, i.e. y = 2.0 * x - 0.5
+        anchor_grid = (self.anchors[i] * self.stride[i]).view((1, self.na, 1, 1, 2)).expand(shape)
+        return grid, anchor_grid
+
+
+class Segment(Detect):
+    # YOLOv5 Segment head for segmentation models
+    def __init__(self, nc=80, anchors=(), nm=32, npr=256, ch=(), inplace=True):
+        super().__init__(nc, anchors, ch, inplace)
+        self.nm = nm  # number of masks
+        self.npr = npr  # number of protos
+        self.no = 5 + nc + self.nm  # number of outputs per anchor
+        self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch)  # output conv
+        self.proto = Proto(ch[0], self.npr, self.nm)  # protos
+        self.detect = Detect.forward
+
+    def forward(self, x):
+        p = self.proto(x[0])
+        x = self.detect(self, x)
+        return (x, p) if self.training else (x[0], p) if self.export else (x[0], p, x[1])
+
+
+class BaseModel(nn.Module):
+    # YOLOv5 base model
+    def forward(self, x, profile=False, visualize=False):
+        return self._forward_once(x, profile, visualize)  # single-scale inference, train
+
+    def _forward_once(self, x, profile=False, visualize=False):
+        y, dt = [], []  # outputs
+        for m in self.model:
+            if m.f != -1:  # if not from previous layer
+                x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f]  # from earlier layers
+            if profile:
+                self._profile_one_layer(m, x, dt)
+            x = m(x)  # run
+            y.append(x if m.i in self.save else None)  # save output
+            if visualize:
+                feature_visualization(x, m.type, m.i, save_dir=visualize)
+        return x
+
+    def _profile_one_layer(self, m, x, dt):
+        c = m == self.model[-1]  # is final layer, copy input as inplace fix
+        o = thop.profile(m, inputs=(x.copy() if c else x, ), verbose=False)[0] / 1E9 * 2 if thop else 0  # FLOPs
+        t = time_sync()
+        for _ in range(10):
+            m(x.copy() if c else x)
+        dt.append((time_sync() - t) * 100)
+        if m == self.model[0]:
+            LOGGER.info(f"{'time (ms)':>10s} {'GFLOPs':>10s} {'params':>10s}  module")
+        LOGGER.info(f'{dt[-1]:10.2f} {o:10.2f} {m.np:10.0f}  {m.type}')
+        if c:
+            LOGGER.info(f"{sum(dt):10.2f} {'-':>10s} {'-':>10s}  Total")
+
+    def fuse(self):  # fuse model Conv2d() + BatchNorm2d() layers
+        LOGGER.info('Fusing layers... ')
+        for m in self.model.modules():
+            if isinstance(m, (Conv, DWConv)) and hasattr(m, 'bn'):
+                m.conv = fuse_conv_and_bn(m.conv, m.bn)  # update conv
+                delattr(m, 'bn')  # remove batchnorm
+                m.forward = m.forward_fuse  # update forward
+        self.info()
+        return self
+
+    def info(self, verbose=False, img_size=640):  # print model information
+        model_info(self, verbose, img_size)
+
+    def _apply(self, fn):
+        # Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers
+        self = super()._apply(fn)
+        m = self.model[-1]  # Detect()
+        if isinstance(m, (Detect, Segment)):
+            m.stride = fn(m.stride)
+            m.grid = list(map(fn, m.grid))
+            if isinstance(m.anchor_grid, list):
+                m.anchor_grid = list(map(fn, m.anchor_grid))
+        return self
+
+
+class DetectionModel(BaseModel):
+    # YOLOv5 detection model
+    def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None):  # model, input channels, number of classes
+        super().__init__()
+        if isinstance(cfg, dict):
+            self.yaml = cfg  # model dict
+        else:  # is *.yaml
+            import yaml  # for torch hub
+            self.yaml_file = Path(cfg).name
+            with open(cfg, encoding='ascii', errors='ignore') as f:
+                self.yaml = yaml.safe_load(f)  # model dict
+
+        # Define model
+        ch = self.yaml['ch'] = self.yaml.get('ch', ch)  # input channels
+        if nc and nc != self.yaml['nc']:
+            LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
+            self.yaml['nc'] = nc  # override yaml value
+        if anchors:
+            LOGGER.info(f'Overriding model.yaml anchors with anchors={anchors}')
+            self.yaml['anchors'] = round(anchors)  # override yaml value
+        self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch])  # model, savelist
+        self.names = [str(i) for i in range(self.yaml['nc'])]  # default names
+        self.inplace = self.yaml.get('inplace', True)
+
+        # Build strides, anchors
+        m = self.model[-1]  # Detect()
+        if isinstance(m, (Detect, Segment)):
+            s = 256  # 2x min stride
+            m.inplace = self.inplace
+            forward = lambda x: self.forward(x)[0] if isinstance(m, Segment) else self.forward(x)
+            m.stride = torch.tensor([s / x.shape[-2] for x in forward(torch.zeros(1, ch, s, s))])  # forward
+            check_anchor_order(m)
+            m.anchors /= m.stride.view(-1, 1, 1)
+            self.stride = m.stride
+            self._initialize_biases()  # only run once
+
+        # Init weights, biases
+        initialize_weights(self)
+        self.info()
+        LOGGER.info('')
+
+    def forward(self, x, augment=False, profile=False, visualize=False):
+        if augment:
+            return self._forward_augment(x)  # augmented inference, None
+        return self._forward_once(x, profile, visualize)  # single-scale inference, train
+
+    def _forward_augment(self, x):
+        img_size = x.shape[-2:]  # height, width
+        s = [1, 0.83, 0.67]  # scales
+        f = [None, 3, None]  # flips (2-ud, 3-lr)
+        y = []  # outputs
+        for si, fi in zip(s, f):
+            xi = scale_img(x.flip(fi) if fi else x, si, gs=int(self.stride.max()))
+            yi = self._forward_once(xi)[0]  # forward
+            # cv2.imwrite(f'img_{si}.jpg', 255 * xi[0].cpu().numpy().transpose((1, 2, 0))[:, :, ::-1])  # save
+            yi = self._descale_pred(yi, fi, si, img_size)
+            y.append(yi)
+        y = self._clip_augmented(y)  # clip augmented tails
+        return torch.cat(y, 1), None  # augmented inference, train
+
+    def _descale_pred(self, p, flips, scale, img_size):
+        # de-scale predictions following augmented inference (inverse operation)
+        if self.inplace:
+            p[..., :4] /= scale  # de-scale
+            if flips == 2:
+                p[..., 1] = img_size[0] - p[..., 1]  # de-flip ud
+            elif flips == 3:
+                p[..., 0] = img_size[1] - p[..., 0]  # de-flip lr
+        else:
+            x, y, wh = p[..., 0:1] / scale, p[..., 1:2] / scale, p[..., 2:4] / scale  # de-scale
+            if flips == 2:
+                y = img_size[0] - y  # de-flip ud
+            elif flips == 3:
+                x = img_size[1] - x  # de-flip lr
+            p = torch.cat((x, y, wh, p[..., 4:]), -1)
+        return p
+
+    def _clip_augmented(self, y):
+        # Clip YOLOv5 augmented inference tails
+        nl = self.model[-1].nl  # number of detection layers (P3-P5)
+        g = sum(4 ** x for x in range(nl))  # grid points
+        e = 1  # exclude layer count
+        i = (y[0].shape[1] // g) * sum(4 ** x for x in range(e))  # indices
+        y[0] = y[0][:, :-i]  # large
+        i = (y[-1].shape[1] // g) * sum(4 ** (nl - 1 - x) for x in range(e))  # indices
+        y[-1] = y[-1][:, i:]  # small
+        return y
+
+    def _initialize_biases(self, cf=None):  # initialize biases into Detect(), cf is class frequency
+        # https://arxiv.org/abs/1708.02002 section 3.3
+        # cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
+        m = self.model[-1]  # Detect() module
+        for mi, s in zip(m.m, m.stride):  # from
+            b = mi.bias.view(m.na, -1)  # conv.bias(255) to (3,85)
+            b.data[:, 4] += math.log(8 / (640 / s) ** 2)  # obj (8 objects per 640 image)
+            b.data[:, 5:5 + m.nc] += math.log(0.6 / (m.nc - 0.99999)) if cf is None else torch.log(cf / cf.sum())  # cls
+            mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
+
+
+Model = DetectionModel  # retain YOLOv5 'Model' class for backwards compatibility
+
+
+class SegmentationModel(DetectionModel):
+    # YOLOv5 segmentation model
+    def __init__(self, cfg='yolov5s-seg.yaml', ch=3, nc=None, anchors=None):
+        super().__init__(cfg, ch, nc, anchors)
+
+
+class ClassificationModel(BaseModel):
+    # YOLOv5 classification model
+    def __init__(self, cfg=None, model=None, nc=1000, cutoff=10):  # yaml, model, number of classes, cutoff index
+        super().__init__()
+        self._from_detection_model(model, nc, cutoff) if model is not None else self._from_yaml(cfg)
+
+    def _from_detection_model(self, model, nc=1000, cutoff=10):
+        # Create a YOLOv5 classification model from a YOLOv5 detection model
+        if isinstance(model, DetectMultiBackend):
+            model = model.model  # unwrap DetectMultiBackend
+        model.model = model.model[:cutoff]  # backbone
+        m = model.model[-1]  # last layer
+        ch = m.conv.in_channels if hasattr(m, 'conv') else m.cv1.conv.in_channels  # ch into module
+        c = Classify(ch, nc)  # Classify()
+        c.i, c.f, c.type = m.i, m.f, 'models.common.Classify'  # index, from, type
+        model.model[-1] = c  # replace
+        self.model = model.model
+        self.stride = model.stride
+        self.save = []
+        self.nc = nc
+
+    def _from_yaml(self, cfg):
+        # Create a YOLOv5 classification model from a *.yaml file
+        self.model = None
+
+
+def parse_model(d, ch):  # model_dict, input_channels(3)
+    # Parse a YOLOv5 model.yaml dictionary
+    LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10}  {'module':<40}{'arguments':<30}")
+    anchors, nc, gd, gw, act = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple'], d.get('activation')
+    if act:
+        Conv.default_act = eval(act)  # redefine default activation, i.e. Conv.default_act = nn.SiLU()
+        LOGGER.info(f"{colorstr('activation:')} {act}")  # print
+    na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors  # number of anchors
+    no = na * (nc + 5)  # number of outputs = anchors * (classes + 5)
+
+    layers, save, c2 = [], [], ch[-1]  # layers, savelist, ch out
+    for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):  # from, number, module, args
+        m = eval(m) if isinstance(m, str) else m  # eval strings
+        for j, a in enumerate(args):
+            with contextlib.suppress(NameError):
+                args[j] = eval(a) if isinstance(a, str) else a  # eval strings
+
+        n = n_ = max(round(n * gd), 1) if n > 1 else n  # depth gain
+        if m in {
+                Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
+                BottleneckCSP, C3, C3TR, C3SPP, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x}:
+            c1, c2 = ch[f], args[0]
+            if c2 != no:  # if not output
+                c2 = make_divisible(c2 * gw, 8)
+
+            args = [c1, c2, *args[1:]]
+            if m in {BottleneckCSP, C3, C3TR, C3Ghost, C3x}:
+                args.insert(2, n)  # number of repeats
+                n = 1
+        elif m is nn.BatchNorm2d:
+            args = [ch[f]]
+        elif m is Concat:
+            c2 = sum(ch[x] for x in f)
+        # TODO: channel, gw, gd
+        elif m in {Detect, Segment}:
+            args.append([ch[x] for x in f])
+            if isinstance(args[1], int):  # number of anchors
+                args[1] = [list(range(args[1] * 2))] * len(f)
+            if m is Segment:
+                args[3] = make_divisible(args[3] * gw, 8)
+        elif m is Contract:
+            c2 = ch[f] * args[0] ** 2
+        elif m is Expand:
+            c2 = ch[f] // args[0] ** 2
+        else:
+            c2 = ch[f]
+
+        m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args)  # module
+        t = str(m)[8:-2].replace('__main__.', '')  # module type
+        np = sum(x.numel() for x in m_.parameters())  # number params
+        m_.i, m_.f, m_.type, m_.np = i, f, t, np  # attach index, 'from' index, type, number params
+        LOGGER.info(f'{i:>3}{str(f):>18}{n_:>3}{np:10.0f}  {t:<40}{str(args):<30}')  # print
+        save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1)  # append to savelist
+        layers.append(m_)
+        if i == 0:
+            ch = []
+        ch.append(c2)
+    return nn.Sequential(*layers), sorted(save)
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--cfg', type=str, default='yolov5s.yaml', help='model.yaml')
+    parser.add_argument('--batch-size', type=int, default=1, help='total batch size for all GPUs')
+    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    parser.add_argument('--profile', action='store_true', help='profile model speed')
+    parser.add_argument('--line-profile', action='store_true', help='profile model speed layer by layer')
+    parser.add_argument('--test', action='store_true', help='test all yolo*.yaml')
+    opt = parser.parse_args()
+    opt.cfg = check_yaml(opt.cfg)  # check YAML
+    print_args(vars(opt))
+    device = select_device(opt.device)
+
+    # Create model
+    im = torch.rand(opt.batch_size, 3, 640, 640).to(device)
+    model = Model(opt.cfg).to(device)
+
+    # Options
+    if opt.line_profile:  # profile layer by layer
+        model(im, profile=True)
+
+    elif opt.profile:  # profile forward-backward
+        results = profile(input=im, ops=[model], n=3)
+
+    elif opt.test:  # test all models
+        for cfg in Path(ROOT / 'models').rglob('yolo*.yaml'):
+            try:
+                _ = Model(cfg)
+            except Exception as e:
+                print(f'Error in {cfg}: {e}')
+
+    else:  # report fused model summary
+        model.fuse()

models/yolov5l.yaml

@@ -0,0 +1,48 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

models/yolov5m.yaml

@@ -0,0 +1,48 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.67  # model depth multiple
+width_multiple: 0.75  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

models/yolov5n.yaml

@@ -0,0 +1,48 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.25  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

models/yolov5s.yaml

@@ -0,0 +1,48 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.50  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

models/yolov5x.yaml

@@ -0,0 +1,48 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.33  # model depth multiple
+width_multiple: 1.25  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

segment/predict.py

@@ -0,0 +1,285 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+"""
+Run YOLOv5 segmentation inference on images, videos, directories, streams, etc.
+
+Usage - sources:
+    $ python segment/predict.py --weights yolov5s-seg.pt --source 0                               # webcam
+                                                                  img.jpg                         # image
+                                                                  vid.mp4                         # video
+                                                                  screen                          # screenshot
+                                                                  path/                           # directory
+                                                                  list.txt                        # list of images
+                                                                  list.streams                    # list of streams
+                                                                  'path/*.jpg'                    # glob
+                                                                  'https://youtu.be/Zgi9g1ksQHc'  # YouTube
+                                                                  'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream
+
+Usage - formats:
+    $ python segment/predict.py --weights yolov5s-seg.pt                 # PyTorch
+                                          yolov5s-seg.torchscript        # TorchScript
+                                          yolov5s-seg.onnx               # ONNX Runtime or OpenCV DNN with --dnn
+                                          yolov5s-seg_openvino_model     # OpenVINO
+                                          yolov5s-seg.engine             # TensorRT
+                                          yolov5s-seg.mlmodel            # CoreML (macOS-only)
+                                          yolov5s-seg_saved_model        # TensorFlow SavedModel
+                                          yolov5s-seg.pb                 # TensorFlow GraphDef
+                                          yolov5s-seg.tflite             # TensorFlow Lite
+                                          yolov5s-seg_edgetpu.tflite     # TensorFlow Edge TPU
+                                          yolov5s-seg_paddle_model       # PaddlePaddle
+"""
+
+import argparse
+import os
+import platform
+import sys
+from pathlib import Path
+
+import torch
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[1]  # YOLOv5 root directory
+if str(ROOT) not in sys.path:
+    sys.path.append(str(ROOT))  # add ROOT to PATH
+ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative
+
+from ultralytics.utils.plotting import Annotator, colors, save_one_box
+
+from models.common import DetectMultiBackend
+from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadScreenshots, LoadStreams
+from utils.general import (LOGGER, Profile, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2,
+                           increment_path, non_max_suppression, print_args, scale_boxes, scale_segments,
+                           strip_optimizer)
+from utils.segment.general import masks2segments, process_mask, process_mask_native
+from utils.torch_utils import select_device, smart_inference_mode
+
+
+@smart_inference_mode()
+def run(
+    weights=ROOT / 'yolov5s-seg.pt',  # model.pt path(s)
+    source=ROOT / 'data/images',  # file/dir/URL/glob/screen/0(webcam)
+    data=ROOT / 'data/coco128.yaml',  # dataset.yaml path
+    imgsz=(640, 640),  # inference size (height, width)
+    conf_thres=0.25,  # confidence threshold
+    iou_thres=0.45,  # NMS IOU threshold
+    max_det=1000,  # maximum detections per image
+    device='',  # cuda device, i.e. 0 or 0,1,2,3 or cpu
+    view_img=False,  # show results
+    save_txt=False,  # save results to *.txt
+    save_conf=False,  # save confidences in --save-txt labels
+    save_crop=False,  # save cropped prediction boxes
+    nosave=False,  # do not save images/videos
+    classes=None,  # filter by class: --class 0, or --class 0 2 3
+    agnostic_nms=False,  # class-agnostic NMS
+    augment=False,  # augmented inference
+    visualize=False,  # visualize features
+    update=False,  # update all models
+    project=ROOT / 'runs/predict-seg',  # save results to project/name
+    name='exp',  # save results to project/name
+    exist_ok=False,  # existing project/name ok, do not increment
+    line_thickness=3,  # bounding box thickness (pixels)
+    hide_labels=False,  # hide labels
+    hide_conf=False,  # hide confidences
+    half=False,  # use FP16 half-precision inference
+    dnn=False,  # use OpenCV DNN for ONNX inference
+    vid_stride=1,  # video frame-rate stride
+    retina_masks=False,
+):
+    source = str(source)
+    save_img = not nosave and not source.endswith('.txt')  # save inference images
+    is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
+    is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
+    webcam = source.isnumeric() or source.endswith('.streams') or (is_url and not is_file)
+    screenshot = source.lower().startswith('screen')
+    if is_url and is_file:
+        source = check_file(source)  # download
+
+    # Directories
+    save_dir = increment_path(Path(project) / name, exist_ok=exist_ok)  # increment run
+    (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir
+
+    # Load model
+    device = select_device(device)
+    model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
+    stride, names, pt = model.stride, model.names, model.pt
+    imgsz = check_img_size(imgsz, s=stride)  # check image size
+
+    # Dataloader
+    bs = 1  # batch_size
+    if webcam:
+        view_img = check_imshow(warn=True)
+        dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride)
+        bs = len(dataset)
+    elif screenshot:
+        dataset = LoadScreenshots(source, img_size=imgsz, stride=stride, auto=pt)
+    else:
+        dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride)
+    vid_path, vid_writer = [None] * bs, [None] * bs
+
+    # Run inference
+    model.warmup(imgsz=(1 if pt else bs, 3, *imgsz))  # warmup
+    seen, windows, dt = 0, [], (Profile(), Profile(), Profile())
+    for path, im, im0s, vid_cap, s in dataset:
+        with dt[0]:
+            im = torch.from_numpy(im).to(model.device)
+            im = im.half() if model.fp16 else im.float()  # uint8 to fp16/32
+            im /= 255  # 0 - 255 to 0.0 - 1.0
+            if len(im.shape) == 3:
+                im = im[None]  # expand for batch dim
+
+        # Inference
+        with dt[1]:
+            visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
+            pred, proto = model(im, augment=augment, visualize=visualize)[:2]
+
+        # NMS
+        with dt[2]:
+            pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det, nm=32)
+
+        # Second-stage classifier (optional)
+        # pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)
+
+        # Process predictions
+        for i, det in enumerate(pred):  # per image
+            seen += 1
+            if webcam:  # batch_size >= 1
+                p, im0, frame = path[i], im0s[i].copy(), dataset.count
+                s += f'{i}: '
+            else:
+                p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0)
+
+            p = Path(p)  # to Path
+            save_path = str(save_dir / p.name)  # im.jpg
+            txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}')  # im.txt
+            s += '%gx%g ' % im.shape[2:]  # print string
+            imc = im0.copy() if save_crop else im0  # for save_crop
+            annotator = Annotator(im0, line_width=line_thickness, example=str(names))
+            if len(det):
+                if retina_masks:
+                    # scale bbox first the crop masks
+                    det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], im0.shape).round()  # rescale boxes to im0 size
+                    masks = process_mask_native(proto[i], det[:, 6:], det[:, :4], im0.shape[:2])  # HWC
+                else:
+                    masks = process_mask(proto[i], det[:, 6:], det[:, :4], im.shape[2:], upsample=True)  # HWC
+                    det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], im0.shape).round()  # rescale boxes to im0 size
+
+                # Segments
+                if save_txt:
+                    segments = [
+                        scale_segments(im0.shape if retina_masks else im.shape[2:], x, im0.shape, normalize=True)
+                        for x in reversed(masks2segments(masks))]
+
+                # Print results
+                for c in det[:, 5].unique():
+                    n = (det[:, 5] == c).sum()  # detections per class
+                    s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string
+
+                # Mask plotting
+                annotator.masks(
+                    masks,
+                    colors=[colors(x, True) for x in det[:, 5]],
+                    im_gpu=torch.as_tensor(im0, dtype=torch.float16).to(device).permute(2, 0, 1).flip(0).contiguous() /
+                    255 if retina_masks else im[i])
+
+                # Write results
+                for j, (*xyxy, conf, cls) in enumerate(reversed(det[:, :6])):
+                    if save_txt:  # Write to file
+                        seg = segments[j].reshape(-1)  # (n,2) to (n*2)
+                        line = (cls, *seg, conf) if save_conf else (cls, *seg)  # label format
+                        with open(f'{txt_path}.txt', 'a') as f:
+                            f.write(('%g ' * len(line)).rstrip() % line + '\n')
+
+                    if save_img or save_crop or view_img:  # Add bbox to image
+                        c = int(cls)  # integer class
+                        label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')
+                        annotator.box_label(xyxy, label, color=colors(c, True))
+                        # annotator.draw.polygon(segments[j], outline=colors(c, True), width=3)
+                    if save_crop:
+                        save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)
+
+            # Stream results
+            im0 = annotator.result()
+            if view_img:
+                if platform.system() == 'Linux' and p not in windows:
+                    windows.append(p)
+                    cv2.namedWindow(str(p), cv2.WINDOW_NORMAL | cv2.WINDOW_KEEPRATIO)  # allow window resize (Linux)
+                    cv2.resizeWindow(str(p), im0.shape[1], im0.shape[0])
+                cv2.imshow(str(p), im0)
+                if cv2.waitKey(1) == ord('q'):  # 1 millisecond
+                    exit()
+
+            # Save results (image with detections)
+            if save_img:
+                if dataset.mode == 'image':
+                    cv2.imwrite(save_path, im0)
+                else:  # 'video' or 'stream'
+                    if vid_path[i] != save_path:  # new video
+                        vid_path[i] = save_path
+                        if isinstance(vid_writer[i], cv2.VideoWriter):
+                            vid_writer[i].release()  # release previous video writer
+                        if vid_cap:  # video
+                            fps = vid_cap.get(cv2.CAP_PROP_FPS)
+                            w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+                            h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+                        else:  # stream
+                            fps, w, h = 30, im0.shape[1], im0.shape[0]
+                        save_path = str(Path(save_path).with_suffix('.mp4'))  # force *.mp4 suffix on results videos
+                        vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
+                    vid_writer[i].write(im0)
+
+        # Print time (inference-only)
+        LOGGER.info(f"{s}{'' if len(det) else '(no detections), '}{dt[1].dt * 1E3:.1f}ms")
+
+    # Print results
+    t = tuple(x.t / seen * 1E3 for x in dt)  # speeds per image
+    LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t)
+    if save_txt or save_img:
+        s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
+        LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
+    if update:
+        strip_optimizer(weights[0])  # update model (to fix SourceChangeWarning)
+
+
+def parse_opt():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'yolov5s-seg.pt', help='model path(s)')
+    parser.add_argument('--source', type=str, default=ROOT / 'data/images', help='file/dir/URL/glob/screen/0(webcam)')
+    parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='(optional) dataset.yaml path')
+    parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')
+    parser.add_argument('--conf-thres', type=float, default=0.25, help='confidence threshold')
+    parser.add_argument('--iou-thres', type=float, default=0.45, help='NMS IoU threshold')
+    parser.add_argument('--max-det', type=int, default=1000, help='maximum detections per image')
+    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    parser.add_argument('--view-img', action='store_true', help='show results')
+    parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
+    parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
+    parser.add_argument('--save-crop', action='store_true', help='save cropped prediction boxes')
+    parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
+    parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --classes 0, or --classes 0 2 3')
+    parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
+    parser.add_argument('--augment', action='store_true', help='augmented inference')
+    parser.add_argument('--visualize', action='store_true', help='visualize features')
+    parser.add_argument('--update', action='store_true', help='update all models')
+    parser.add_argument('--project', default=ROOT / 'runs/predict-seg', help='save results to project/name')
+    parser.add_argument('--name', default='exp', help='save results to project/name')
+    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
+    parser.add_argument('--line-thickness', default=3, type=int, help='bounding box thickness (pixels)')
+    parser.add_argument('--hide-labels', default=False, action='store_true', help='hide labels')
+    parser.add_argument('--hide-conf', default=False, action='store_true', help='hide confidences')
+    parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')
+    parser.add_argument('--dnn', action='store_true', help='use OpenCV DNN for ONNX inference')
+    parser.add_argument('--vid-stride', type=int, default=1, help='video frame-rate stride')
+    parser.add_argument('--retina-masks', action='store_true', help='whether to plot masks in native resolution')
+    opt = parser.parse_args()
+    opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1  # expand
+    print_args(vars(opt))
+    return opt
+
+
+def main(opt):
+    check_requirements(ROOT / 'requirements.txt', exclude=('tensorboard', 'thop'))
+    run(**vars(opt))
+
+
+if __name__ == '__main__':
+    opt = parse_opt()
+    main(opt)

segment/train.py

@@ -0,0 +1,666 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+"""
+Train a YOLOv5 segment model on a segment dataset
+Models and datasets download automatically from the latest YOLOv5 release.
+
+Usage - Single-GPU training:
+    $ python segment/train.py --data coco128-seg.yaml --weights yolov5s-seg.pt --img 640  # from pretrained (recommended)
+    $ python segment/train.py --data coco128-seg.yaml --weights '' --cfg yolov5s-seg.yaml --img 640  # from scratch
+
+Usage - Multi-GPU DDP training:
+    $ python -m torch.distributed.run --nproc_per_node 4 --master_port 1 segment/train.py --data coco128-seg.yaml --weights yolov5s-seg.pt --img 640 --device 0,1,2,3
+
+Models:     https://github.com/ultralytics/yolov5/tree/master/models
+Datasets:   https://github.com/ultralytics/yolov5/tree/master/data
+Tutorial:   https://docs.ultralytics.com/yolov5/tutorials/train_custom_data
+"""
+
+import argparse
+import math
+import os
+import random
+import subprocess
+import sys
+import time
+from copy import deepcopy
+from datetime import datetime
+from pathlib import Path
+
+import numpy as np
+import torch
+import torch.distributed as dist
+import torch.nn as nn
+import yaml
+from torch.optim import lr_scheduler
+from tqdm import tqdm
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[1]  # YOLOv5 root directory
+if str(ROOT) not in sys.path:
+    sys.path.append(str(ROOT))  # add ROOT to PATH
+ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative
+
+import segment.val as validate  # for end-of-epoch mAP
+from models.experimental import attempt_load
+from models.yolo import SegmentationModel
+from utils.autoanchor import check_anchors
+from utils.autobatch import check_train_batch_size
+from utils.callbacks import Callbacks
+from utils.downloads import attempt_download, is_url
+from utils.general import (LOGGER, TQDM_BAR_FORMAT, check_amp, check_dataset, check_file, check_git_info,
+                           check_git_status, check_img_size, check_requirements, check_suffix, check_yaml, colorstr,
+                           get_latest_run, increment_path, init_seeds, intersect_dicts, labels_to_class_weights,
+                           labels_to_image_weights, one_cycle, print_args, print_mutation, strip_optimizer, yaml_save)
+from utils.loggers import GenericLogger
+from utils.plots import plot_evolve, plot_labels
+from utils.segment.dataloaders import create_dataloader
+from utils.segment.loss import ComputeLoss
+from utils.segment.metrics import KEYS, fitness
+from utils.segment.plots import plot_images_and_masks, plot_results_with_masks
+from utils.torch_utils import (EarlyStopping, ModelEMA, de_parallel, select_device, smart_DDP, smart_optimizer,
+                               smart_resume, torch_distributed_zero_first)
+
+LOCAL_RANK = int(os.getenv('LOCAL_RANK', -1))  # https://pytorch.org/docs/stable/elastic/run.html
+RANK = int(os.getenv('RANK', -1))
+WORLD_SIZE = int(os.getenv('WORLD_SIZE', 1))
+GIT_INFO = check_git_info()
+
+
+def train(hyp, opt, device, callbacks):  # hyp is path/to/hyp.yaml or hyp dictionary
+    save_dir, epochs, batch_size, weights, single_cls, evolve, data, cfg, resume, noval, nosave, workers, freeze, mask_ratio = \
+        Path(opt.save_dir), opt.epochs, opt.batch_size, opt.weights, opt.single_cls, opt.evolve, opt.data, opt.cfg, \
+        opt.resume, opt.noval, opt.nosave, opt.workers, opt.freeze, opt.mask_ratio
+    # callbacks.run('on_pretrain_routine_start')
+
+    # Directories
+    w = save_dir / 'weights'  # weights dir
+    (w.parent if evolve else w).mkdir(parents=True, exist_ok=True)  # make dir
+    last, best = w / 'last.pt', w / 'best.pt'
+
+    # Hyperparameters
+    if isinstance(hyp, str):
+        with open(hyp, errors='ignore') as f:
+            hyp = yaml.safe_load(f)  # load hyps dict
+    LOGGER.info(colorstr('hyperparameters: ') + ', '.join(f'{k}={v}' for k, v in hyp.items()))
+    opt.hyp = hyp.copy()  # for saving hyps to checkpoints
+
+    # Save run settings
+    if not evolve:
+        yaml_save(save_dir / 'hyp.yaml', hyp)
+        yaml_save(save_dir / 'opt.yaml', vars(opt))
+
+    # Loggers
+    data_dict = None
+    if RANK in {-1, 0}:
+        logger = GenericLogger(opt=opt, console_logger=LOGGER)
+
+    # Config
+    plots = not evolve and not opt.noplots  # create plots
+    overlap = not opt.no_overlap
+    cuda = device.type != 'cpu'
+    init_seeds(opt.seed + 1 + RANK, deterministic=True)
+    with torch_distributed_zero_first(LOCAL_RANK):
+        data_dict = data_dict or check_dataset(data)  # check if None
+    train_path, val_path = data_dict['train'], data_dict['val']
+    nc = 1 if single_cls else int(data_dict['nc'])  # number of classes
+    names = {0: 'item'} if single_cls and len(data_dict['names']) != 1 else data_dict['names']  # class names
+    is_coco = isinstance(val_path, str) and val_path.endswith('coco/val2017.txt')  # COCO dataset
+
+    # Model
+    check_suffix(weights, '.pt')  # check weights
+    pretrained = weights.endswith('.pt')
+    if pretrained:
+        with torch_distributed_zero_first(LOCAL_RANK):
+            weights = attempt_download(weights)  # download if not found locally
+        ckpt = torch.load(weights, map_location='cpu')  # load checkpoint to CPU to avoid CUDA memory leak
+        model = SegmentationModel(cfg or ckpt['model'].yaml, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device)
+        exclude = ['anchor'] if (cfg or hyp.get('anchors')) and not resume else []  # exclude keys
+        csd = ckpt['model'].float().state_dict()  # checkpoint state_dict as FP32
+        csd = intersect_dicts(csd, model.state_dict(), exclude=exclude)  # intersect
+        model.load_state_dict(csd, strict=False)  # load
+        LOGGER.info(f'Transferred {len(csd)}/{len(model.state_dict())} items from {weights}')  # report
+    else:
+        model = SegmentationModel(cfg, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device)  # create
+    amp = check_amp(model)  # check AMP
+
+    # Freeze
+    freeze = [f'model.{x}.' for x in (freeze if len(freeze) > 1 else range(freeze[0]))]  # layers to freeze
+    for k, v in model.named_parameters():
+        v.requires_grad = True  # train all layers
+        # v.register_hook(lambda x: torch.nan_to_num(x))  # NaN to 0 (commented for erratic training results)
+        if any(x in k for x in freeze):
+            LOGGER.info(f'freezing {k}')
+            v.requires_grad = False
+
+    # Image size
+    gs = max(int(model.stride.max()), 32)  # grid size (max stride)
+    imgsz = check_img_size(opt.imgsz, gs, floor=gs * 2)  # verify imgsz is gs-multiple
+
+    # Batch size
+    if RANK == -1 and batch_size == -1:  # single-GPU only, estimate best batch size
+        batch_size = check_train_batch_size(model, imgsz, amp)
+        logger.update_params({'batch_size': batch_size})
+        # loggers.on_params_update({"batch_size": batch_size})
+
+    # Optimizer
+    nbs = 64  # nominal batch size
+    accumulate = max(round(nbs / batch_size), 1)  # accumulate loss before optimizing
+    hyp['weight_decay'] *= batch_size * accumulate / nbs  # scale weight_decay
+    optimizer = smart_optimizer(model, opt.optimizer, hyp['lr0'], hyp['momentum'], hyp['weight_decay'])
+
+    # Scheduler
+    if opt.cos_lr:
+        lf = one_cycle(1, hyp['lrf'], epochs)  # cosine 1->hyp['lrf']
+    else:
+        lf = lambda x: (1 - x / epochs) * (1.0 - hyp['lrf']) + hyp['lrf']  # linear
+    scheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lf)  # plot_lr_scheduler(optimizer, scheduler, epochs)
+
+    # EMA
+    ema = ModelEMA(model) if RANK in {-1, 0} else None
+
+    # Resume
+    best_fitness, start_epoch = 0.0, 0
+    if pretrained:
+        if resume:
+            best_fitness, start_epoch, epochs = smart_resume(ckpt, optimizer, ema, weights, epochs, resume)
+        del ckpt, csd
+
+    # DP mode
+    if cuda and RANK == -1 and torch.cuda.device_count() > 1:
+        LOGGER.warning(
+            'WARNING ⚠️ DP not recommended, use torch.distributed.run for best DDP Multi-GPU results.\n'
+            'See Multi-GPU Tutorial at https://docs.ultralytics.com/yolov5/tutorials/multi_gpu_training to get started.'
+        )
+        model = torch.nn.DataParallel(model)
+
+    # SyncBatchNorm
+    if opt.sync_bn and cuda and RANK != -1:
+        model = torch.nn.SyncBatchNorm.convert_sync_batchnorm(model).to(device)
+        LOGGER.info('Using SyncBatchNorm()')
+
+    # Trainloader
+    train_loader, dataset = create_dataloader(
+        train_path,
+        imgsz,
+        batch_size // WORLD_SIZE,
+        gs,
+        single_cls,
+        hyp=hyp,
+        augment=True,
+        cache=None if opt.cache == 'val' else opt.cache,
+        rect=opt.rect,
+        rank=LOCAL_RANK,
+        workers=workers,
+        image_weights=opt.image_weights,
+        quad=opt.quad,
+        prefix=colorstr('train: '),
+        shuffle=True,
+        mask_downsample_ratio=mask_ratio,
+        overlap_mask=overlap,
+    )
+    labels = np.concatenate(dataset.labels, 0)
+    mlc = int(labels[:, 0].max())  # max label class
+    assert mlc < nc, f'Label class {mlc} exceeds nc={nc} in {data}. Possible class labels are 0-{nc - 1}'
+
+    # Process 0
+    if RANK in {-1, 0}:
+        val_loader = create_dataloader(val_path,
+                                       imgsz,
+                                       batch_size // WORLD_SIZE * 2,
+                                       gs,
+                                       single_cls,
+                                       hyp=hyp,
+                                       cache=None if noval else opt.cache,
+                                       rect=True,
+                                       rank=-1,
+                                       workers=workers * 2,
+                                       pad=0.5,
+                                       mask_downsample_ratio=mask_ratio,
+                                       overlap_mask=overlap,
+                                       prefix=colorstr('val: '))[0]
+
+        if not resume:
+            if not opt.noautoanchor:
+                check_anchors(dataset, model=model, thr=hyp['anchor_t'], imgsz=imgsz)  # run AutoAnchor
+            model.half().float()  # pre-reduce anchor precision
+
+            if plots:
+                plot_labels(labels, names, save_dir)
+        # callbacks.run('on_pretrain_routine_end', labels, names)
+
+    # DDP mode
+    if cuda and RANK != -1:
+        model = smart_DDP(model)
+
+    # Model attributes
+    nl = de_parallel(model).model[-1].nl  # number of detection layers (to scale hyps)
+    hyp['box'] *= 3 / nl  # scale to layers
+    hyp['cls'] *= nc / 80 * 3 / nl  # scale to classes and layers
+    hyp['obj'] *= (imgsz / 640) ** 2 * 3 / nl  # scale to image size and layers
+    hyp['label_smoothing'] = opt.label_smoothing
+    model.nc = nc  # attach number of classes to model
+    model.hyp = hyp  # attach hyperparameters to model
+    model.class_weights = labels_to_class_weights(dataset.labels, nc).to(device) * nc  # attach class weights
+    model.names = names
+
+    # Start training
+    t0 = time.time()
+    nb = len(train_loader)  # number of batches
+    nw = max(round(hyp['warmup_epochs'] * nb), 100)  # number of warmup iterations, max(3 epochs, 100 iterations)
+    # nw = min(nw, (epochs - start_epoch) / 2 * nb)  # limit warmup to < 1/2 of training
+    last_opt_step = -1
+    maps = np.zeros(nc)  # mAP per class
+    results = (0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)  # P, R, mAP@.5, mAP@.5-.95, val_loss(box, obj, cls)
+    scheduler.last_epoch = start_epoch - 1  # do not move
+    scaler = torch.cuda.amp.GradScaler(enabled=amp)
+    stopper, stop = EarlyStopping(patience=opt.patience), False
+    compute_loss = ComputeLoss(model, overlap=overlap)  # init loss class
+    # callbacks.run('on_train_start')
+    LOGGER.info(f'Image sizes {imgsz} train, {imgsz} val\n'
+                f'Using {train_loader.num_workers * WORLD_SIZE} dataloader workers\n'
+                f"Logging results to {colorstr('bold', save_dir)}\n"
+                f'Starting training for {epochs} epochs...')
+    for epoch in range(start_epoch, epochs):  # epoch ------------------------------------------------------------------
+        # callbacks.run('on_train_epoch_start')
+        model.train()
+
+        # Update image weights (optional, single-GPU only)
+        if opt.image_weights:
+            cw = model.class_weights.cpu().numpy() * (1 - maps) ** 2 / nc  # class weights
+            iw = labels_to_image_weights(dataset.labels, nc=nc, class_weights=cw)  # image weights
+            dataset.indices = random.choices(range(dataset.n), weights=iw, k=dataset.n)  # rand weighted idx
+
+        # Update mosaic border (optional)
+        # b = int(random.uniform(0.25 * imgsz, 0.75 * imgsz + gs) // gs * gs)
+        # dataset.mosaic_border = [b - imgsz, -b]  # height, width borders
+
+        mloss = torch.zeros(4, device=device)  # mean losses
+        if RANK != -1:
+            train_loader.sampler.set_epoch(epoch)
+        pbar = enumerate(train_loader)
+        LOGGER.info(('\n' + '%11s' * 8) %
+                    ('Epoch', 'GPU_mem', 'box_loss', 'seg_loss', 'obj_loss', 'cls_loss', 'Instances', 'Size'))
+        if RANK in {-1, 0}:
+            pbar = tqdm(pbar, total=nb, bar_format=TQDM_BAR_FORMAT)  # progress bar
+        optimizer.zero_grad()
+        for i, (imgs, targets, paths, _, masks) in pbar:  # batch ------------------------------------------------------
+            # callbacks.run('on_train_batch_start')
+            ni = i + nb * epoch  # number integrated batches (since train start)
+            imgs = imgs.to(device, non_blocking=True).float() / 255  # uint8 to float32, 0-255 to 0.0-1.0
+
+            # Warmup
+            if ni <= nw:
+                xi = [0, nw]  # x interp
+                # compute_loss.gr = np.interp(ni, xi, [0.0, 1.0])  # iou loss ratio (obj_loss = 1.0 or iou)
+                accumulate = max(1, np.interp(ni, xi, [1, nbs / batch_size]).round())
+                for j, x in enumerate(optimizer.param_groups):
+                    # bias lr falls from 0.1 to lr0, all other lrs rise from 0.0 to lr0
+                    x['lr'] = np.interp(ni, xi, [hyp['warmup_bias_lr'] if j == 0 else 0.0, x['initial_lr'] * lf(epoch)])
+                    if 'momentum' in x:
+                        x['momentum'] = np.interp(ni, xi, [hyp['warmup_momentum'], hyp['momentum']])
+
+            # Multi-scale
+            if opt.multi_scale:
+                sz = random.randrange(int(imgsz * 0.5), int(imgsz * 1.5) + gs) // gs * gs  # size
+                sf = sz / max(imgs.shape[2:])  # scale factor
+                if sf != 1:
+                    ns = [math.ceil(x * sf / gs) * gs for x in imgs.shape[2:]]  # new shape (stretched to gs-multiple)
+                    imgs = nn.functional.interpolate(imgs, size=ns, mode='bilinear', align_corners=False)
+
+            # Forward
+            with torch.cuda.amp.autocast(amp):
+                pred = model(imgs)  # forward
+                loss, loss_items = compute_loss(pred, targets.to(device), masks=masks.to(device).float())
+                if RANK != -1:
+                    loss *= WORLD_SIZE  # gradient averaged between devices in DDP mode
+                if opt.quad:
+                    loss *= 4.
+
+            # Backward
+            scaler.scale(loss).backward()
+
+            # Optimize - https://pytorch.org/docs/master/notes/amp_examples.html
+            if ni - last_opt_step >= accumulate:
+                scaler.unscale_(optimizer)  # unscale gradients
+                torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm=10.0)  # clip gradients
+                scaler.step(optimizer)  # optimizer.step
+                scaler.update()
+                optimizer.zero_grad()
+                if ema:
+                    ema.update(model)
+                last_opt_step = ni
+
+            # Log
+            if RANK in {-1, 0}:
+                mloss = (mloss * i + loss_items) / (i + 1)  # update mean losses
+                mem = f'{torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0:.3g}G'  # (GB)
+                pbar.set_description(('%11s' * 2 + '%11.4g' * 6) %
+                                     (f'{epoch}/{epochs - 1}', mem, *mloss, targets.shape[0], imgs.shape[-1]))
+                # callbacks.run('on_train_batch_end', model, ni, imgs, targets, paths)
+                # if callbacks.stop_training:
+                #    return
+
+                # Mosaic plots
+                if plots:
+                    if ni < 3:
+                        plot_images_and_masks(imgs, targets, masks, paths, save_dir / f'train_batch{ni}.jpg')
+                    if ni == 10:
+                        files = sorted(save_dir.glob('train*.jpg'))
+                        logger.log_images(files, 'Mosaics', epoch)
+            # end batch ------------------------------------------------------------------------------------------------
+
+        # Scheduler
+        lr = [x['lr'] for x in optimizer.param_groups]  # for loggers
+        scheduler.step()
+
+        if RANK in {-1, 0}:
+            # mAP
+            # callbacks.run('on_train_epoch_end', epoch=epoch)
+            ema.update_attr(model, include=['yaml', 'nc', 'hyp', 'names', 'stride', 'class_weights'])
+            final_epoch = (epoch + 1 == epochs) or stopper.possible_stop
+            if not noval or final_epoch:  # Calculate mAP
+                results, maps, _ = validate.run(data_dict,
+                                                batch_size=batch_size // WORLD_SIZE * 2,
+                                                imgsz=imgsz,
+                                                half=amp,
+                                                model=ema.ema,
+                                                single_cls=single_cls,
+                                                dataloader=val_loader,
+                                                save_dir=save_dir,
+                                                plots=False,
+                                                callbacks=callbacks,
+                                                compute_loss=compute_loss,
+                                                mask_downsample_ratio=mask_ratio,
+                                                overlap=overlap)
+
+            # Update best mAP
+            fi = fitness(np.array(results).reshape(1, -1))  # weighted combination of [P, R, mAP@.5, mAP@.5-.95]
+            stop = stopper(epoch=epoch, fitness=fi)  # early stop check
+            if fi > best_fitness:
+                best_fitness = fi
+            log_vals = list(mloss) + list(results) + lr
+            # callbacks.run('on_fit_epoch_end', log_vals, epoch, best_fitness, fi)
+            # Log val metrics and media
+            metrics_dict = dict(zip(KEYS, log_vals))
+            logger.log_metrics(metrics_dict, epoch)
+
+            # Save model
+            if (not nosave) or (final_epoch and not evolve):  # if save
+                ckpt = {
+                    'epoch': epoch,
+                    'best_fitness': best_fitness,
+                    'model': deepcopy(de_parallel(model)).half(),
+                    'ema': deepcopy(ema.ema).half(),
+                    'updates': ema.updates,
+                    'optimizer': optimizer.state_dict(),
+                    'opt': vars(opt),
+                    'git': GIT_INFO,  # {remote, branch, commit} if a git repo
+                    'date': datetime.now().isoformat()}
+
+                # Save last, best and delete
+                torch.save(ckpt, last)
+                if best_fitness == fi:
+                    torch.save(ckpt, best)
+                if opt.save_period > 0 and epoch % opt.save_period == 0:
+                    torch.save(ckpt, w / f'epoch{epoch}.pt')
+                    logger.log_model(w / f'epoch{epoch}.pt')
+                del ckpt
+                # callbacks.run('on_model_save', last, epoch, final_epoch, best_fitness, fi)
+
+        # EarlyStopping
+        if RANK != -1:  # if DDP training
+            broadcast_list = [stop if RANK == 0 else None]
+            dist.broadcast_object_list(broadcast_list, 0)  # broadcast 'stop' to all ranks
+            if RANK != 0:
+                stop = broadcast_list[0]
+        if stop:
+            break  # must break all DDP ranks
+
+        # end epoch ----------------------------------------------------------------------------------------------------
+    # end training -----------------------------------------------------------------------------------------------------
+    if RANK in {-1, 0}:
+        LOGGER.info(f'\n{epoch - start_epoch + 1} epochs completed in {(time.time() - t0) / 3600:.3f} hours.')
+        for f in last, best:
+            if f.exists():
+                strip_optimizer(f)  # strip optimizers
+                if f is best:
+                    LOGGER.info(f'\nValidating {f}...')
+                    results, _, _ = validate.run(
+                        data_dict,
+                        batch_size=batch_size // WORLD_SIZE * 2,
+                        imgsz=imgsz,
+                        model=attempt_load(f, device).half(),
+                        iou_thres=0.65 if is_coco else 0.60,  # best pycocotools at iou 0.65
+                        single_cls=single_cls,
+                        dataloader=val_loader,
+                        save_dir=save_dir,
+                        save_json=is_coco,
+                        verbose=True,
+                        plots=plots,
+                        callbacks=callbacks,
+                        compute_loss=compute_loss,
+                        mask_downsample_ratio=mask_ratio,
+                        overlap=overlap)  # val best model with plots
+                    if is_coco:
+                        # callbacks.run('on_fit_epoch_end', list(mloss) + list(results) + lr, epoch, best_fitness, fi)
+                        metrics_dict = dict(zip(KEYS, list(mloss) + list(results) + lr))
+                        logger.log_metrics(metrics_dict, epoch)
+
+        # callbacks.run('on_train_end', last, best, epoch, results)
+        # on train end callback using genericLogger
+        logger.log_metrics(dict(zip(KEYS[4:16], results)), epochs)
+        if not opt.evolve:
+            logger.log_model(best, epoch)
+        if plots:
+            plot_results_with_masks(file=save_dir / 'results.csv')  # save results.png
+            files = ['results.png', 'confusion_matrix.png', *(f'{x}_curve.png' for x in ('F1', 'PR', 'P', 'R'))]
+            files = [(save_dir / f) for f in files if (save_dir / f).exists()]  # filter
+            LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}")
+            logger.log_images(files, 'Results', epoch + 1)
+            logger.log_images(sorted(save_dir.glob('val*.jpg')), 'Validation', epoch + 1)
+    torch.cuda.empty_cache()
+    return results
+
+
+def parse_opt(known=False):
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s-seg.pt', help='initial weights path')
+    parser.add_argument('--cfg', type=str, default='', help='model.yaml path')
+    parser.add_argument('--data', type=str, default=ROOT / 'data/coco128-seg.yaml', help='dataset.yaml path')
+    parser.add_argument('--hyp', type=str, default=ROOT / 'data/hyps/hyp.scratch-low.yaml', help='hyperparameters path')
+    parser.add_argument('--epochs', type=int, default=100, help='total training epochs')
+    parser.add_argument('--batch-size', type=int, default=16, help='total batch size for all GPUs, -1 for autobatch')
+    parser.add_argument('--imgsz', '--img', '--img-size', type=int, default=640, help='train, val image size (pixels)')
+    parser.add_argument('--rect', action='store_true', help='rectangular training')
+    parser.add_argument('--resume', nargs='?', const=True, default=False, help='resume most recent training')
+    parser.add_argument('--nosave', action='store_true', help='only save final checkpoint')
+    parser.add_argument('--noval', action='store_true', help='only validate final epoch')
+    parser.add_argument('--noautoanchor', action='store_true', help='disable AutoAnchor')
+    parser.add_argument('--noplots', action='store_true', help='save no plot files')
+    parser.add_argument('--evolve', type=int, nargs='?', const=300, help='evolve hyperparameters for x generations')
+    parser.add_argument('--bucket', type=str, default='', help='gsutil bucket')
+    parser.add_argument('--cache', type=str, nargs='?', const='ram', help='image --cache ram/disk')
+    parser.add_argument('--image-weights', action='store_true', help='use weighted image selection for training')
+    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    parser.add_argument('--multi-scale', action='store_true', help='vary img-size +/- 50%%')
+    parser.add_argument('--single-cls', action='store_true', help='train multi-class data as single-class')
+    parser.add_argument('--optimizer', type=str, choices=['SGD', 'Adam', 'AdamW'], default='SGD', help='optimizer')
+    parser.add_argument('--sync-bn', action='store_true', help='use SyncBatchNorm, only available in DDP mode')
+    parser.add_argument('--workers', type=int, default=8, help='max dataloader workers (per RANK in DDP mode)')
+    parser.add_argument('--project', default=ROOT / 'runs/train-seg', help='save to project/name')
+    parser.add_argument('--name', default='exp', help='save to project/name')
+    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
+    parser.add_argument('--quad', action='store_true', help='quad dataloader')
+    parser.add_argument('--cos-lr', action='store_true', help='cosine LR scheduler')
+    parser.add_argument('--label-smoothing', type=float, default=0.0, help='Label smoothing epsilon')
+    parser.add_argument('--patience', type=int, default=100, help='EarlyStopping patience (epochs without improvement)')
+    parser.add_argument('--freeze', nargs='+', type=int, default=[0], help='Freeze layers: backbone=10, first3=0 1 2')
+    parser.add_argument('--save-period', type=int, default=-1, help='Save checkpoint every x epochs (disabled if < 1)')
+    parser.add_argument('--seed', type=int, default=0, help='Global training seed')
+    parser.add_argument('--local_rank', type=int, default=-1, help='Automatic DDP Multi-GPU argument, do not modify')
+
+    # Instance Segmentation Args
+    parser.add_argument('--mask-ratio', type=int, default=4, help='Downsample the truth masks to saving memory')
+    parser.add_argument('--no-overlap', action='store_true', help='Overlap masks train faster at slightly less mAP')
+
+    return parser.parse_known_args()[0] if known else parser.parse_args()
+
+
+def main(opt, callbacks=Callbacks()):
+    # Checks
+    if RANK in {-1, 0}:
+        print_args(vars(opt))
+        check_git_status()
+        check_requirements(ROOT / 'requirements.txt')
+
+    # Resume
+    if opt.resume and not opt.evolve:  # resume from specified or most recent last.pt
+        last = Path(check_file(opt.resume) if isinstance(opt.resume, str) else get_latest_run())
+        opt_yaml = last.parent.parent / 'opt.yaml'  # train options yaml
+        opt_data = opt.data  # original dataset
+        if opt_yaml.is_file():
+            with open(opt_yaml, errors='ignore') as f:
+                d = yaml.safe_load(f)
+        else:
+            d = torch.load(last, map_location='cpu')['opt']
+        opt = argparse.Namespace(**d)  # replace
+        opt.cfg, opt.weights, opt.resume = '', str(last), True  # reinstate
+        if is_url(opt_data):
+            opt.data = check_file(opt_data)  # avoid HUB resume auth timeout
+    else:
+        opt.data, opt.cfg, opt.hyp, opt.weights, opt.project = \
+            check_file(opt.data), check_yaml(opt.cfg), check_yaml(opt.hyp), str(opt.weights), str(opt.project)  # checks
+        assert len(opt.cfg) or len(opt.weights), 'either --cfg or --weights must be specified'
+        if opt.evolve:
+            if opt.project == str(ROOT / 'runs/train-seg'):  # if default project name, rename to runs/evolve-seg
+                opt.project = str(ROOT / 'runs/evolve-seg')
+            opt.exist_ok, opt.resume = opt.resume, False  # pass resume to exist_ok and disable resume
+        if opt.name == 'cfg':
+            opt.name = Path(opt.cfg).stem  # use model.yaml as name
+        opt.save_dir = str(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok))
+
+    # DDP mode
+    device = select_device(opt.device, batch_size=opt.batch_size)
+    if LOCAL_RANK != -1:
+        msg = 'is not compatible with YOLOv5 Multi-GPU DDP training'
+        assert not opt.image_weights, f'--image-weights {msg}'
+        assert not opt.evolve, f'--evolve {msg}'
+        assert opt.batch_size != -1, f'AutoBatch with --batch-size -1 {msg}, please pass a valid --batch-size'
+        assert opt.batch_size % WORLD_SIZE == 0, f'--batch-size {opt.batch_size} must be multiple of WORLD_SIZE'
+        assert torch.cuda.device_count() > LOCAL_RANK, 'insufficient CUDA devices for DDP command'
+        torch.cuda.set_device(LOCAL_RANK)
+        device = torch.device('cuda', LOCAL_RANK)
+        dist.init_process_group(backend='nccl' if dist.is_nccl_available() else 'gloo')
+
+    # Train
+    if not opt.evolve:
+        train(opt.hyp, opt, device, callbacks)
+
+    # Evolve hyperparameters (optional)
+    else:
+        # Hyperparameter evolution metadata (mutation scale 0-1, lower_limit, upper_limit)
+        meta = {
+            'lr0': (1, 1e-5, 1e-1),  # initial learning rate (SGD=1E-2, Adam=1E-3)
+            'lrf': (1, 0.01, 1.0),  # final OneCycleLR learning rate (lr0 * lrf)
+            'momentum': (0.3, 0.6, 0.98),  # SGD momentum/Adam beta1
+            'weight_decay': (1, 0.0, 0.001),  # optimizer weight decay
+            'warmup_epochs': (1, 0.0, 5.0),  # warmup epochs (fractions ok)
+            'warmup_momentum': (1, 0.0, 0.95),  # warmup initial momentum
+            'warmup_bias_lr': (1, 0.0, 0.2),  # warmup initial bias lr
+            'box': (1, 0.02, 0.2),  # box loss gain
+            'cls': (1, 0.2, 4.0),  # cls loss gain
+            'cls_pw': (1, 0.5, 2.0),  # cls BCELoss positive_weight
+            'obj': (1, 0.2, 4.0),  # obj loss gain (scale with pixels)
+            'obj_pw': (1, 0.5, 2.0),  # obj BCELoss positive_weight
+            'iou_t': (0, 0.1, 0.7),  # IoU training threshold
+            'anchor_t': (1, 2.0, 8.0),  # anchor-multiple threshold
+            'anchors': (2, 2.0, 10.0),  # anchors per output grid (0 to ignore)
+            'fl_gamma': (0, 0.0, 2.0),  # focal loss gamma (efficientDet default gamma=1.5)
+            'hsv_h': (1, 0.0, 0.1),  # image HSV-Hue augmentation (fraction)
+            'hsv_s': (1, 0.0, 0.9),  # image HSV-Saturation augmentation (fraction)
+            'hsv_v': (1, 0.0, 0.9),  # image HSV-Value augmentation (fraction)
+            'degrees': (1, 0.0, 45.0),  # image rotation (+/- deg)
+            'translate': (1, 0.0, 0.9),  # image translation (+/- fraction)
+            'scale': (1, 0.0, 0.9),  # image scale (+/- gain)
+            'shear': (1, 0.0, 10.0),  # image shear (+/- deg)
+            'perspective': (0, 0.0, 0.001),  # image perspective (+/- fraction), range 0-0.001
+            'flipud': (1, 0.0, 1.0),  # image flip up-down (probability)
+            'fliplr': (0, 0.0, 1.0),  # image flip left-right (probability)
+            'mosaic': (1, 0.0, 1.0),  # image mixup (probability)
+            'mixup': (1, 0.0, 1.0),  # image mixup (probability)
+            'copy_paste': (1, 0.0, 1.0)}  # segment copy-paste (probability)
+
+        with open(opt.hyp, errors='ignore') as f:
+            hyp = yaml.safe_load(f)  # load hyps dict
+            if 'anchors' not in hyp:  # anchors commented in hyp.yaml
+                hyp['anchors'] = 3
+        if opt.noautoanchor:
+            del hyp['anchors'], meta['anchors']
+        opt.noval, opt.nosave, save_dir = True, True, Path(opt.save_dir)  # only val/save final epoch
+        # ei = [isinstance(x, (int, float)) for x in hyp.values()]  # evolvable indices
+        evolve_yaml, evolve_csv = save_dir / 'hyp_evolve.yaml', save_dir / 'evolve.csv'
+        if opt.bucket:
+            # download evolve.csv if exists
+            subprocess.run([
+                'gsutil',
+                'cp',
+                f'gs://{opt.bucket}/evolve.csv',
+                str(evolve_csv), ])
+
+        for _ in range(opt.evolve):  # generations to evolve
+            if evolve_csv.exists():  # if evolve.csv exists: select best hyps and mutate
+                # Select parent(s)
+                parent = 'single'  # parent selection method: 'single' or 'weighted'
+                x = np.loadtxt(evolve_csv, ndmin=2, delimiter=',', skiprows=1)
+                n = min(5, len(x))  # number of previous results to consider
+                x = x[np.argsort(-fitness(x))][:n]  # top n mutations
+                w = fitness(x) - fitness(x).min() + 1E-6  # weights (sum > 0)
+                if parent == 'single' or len(x) == 1:
+                    # x = x[random.randint(0, n - 1)]  # random selection
+                    x = x[random.choices(range(n), weights=w)[0]]  # weighted selection
+                elif parent == 'weighted':
+                    x = (x * w.reshape(n, 1)).sum(0) / w.sum()  # weighted combination
+
+                # Mutate
+                mp, s = 0.8, 0.2  # mutation probability, sigma
+                npr = np.random
+                npr.seed(int(time.time()))
+                g = np.array([meta[k][0] for k in hyp.keys()])  # gains 0-1
+                ng = len(meta)
+                v = np.ones(ng)
+                while all(v == 1):  # mutate until a change occurs (prevent duplicates)
+                    v = (g * (npr.random(ng) < mp) * npr.randn(ng) * npr.random() * s + 1).clip(0.3, 3.0)
+                for i, k in enumerate(hyp.keys()):  # plt.hist(v.ravel(), 300)
+                    hyp[k] = float(x[i + 12] * v[i])  # mutate
+
+            # Constrain to limits
+            for k, v in meta.items():
+                hyp[k] = max(hyp[k], v[1])  # lower limit
+                hyp[k] = min(hyp[k], v[2])  # upper limit
+                hyp[k] = round(hyp[k], 5)  # significant digits
+
+            # Train mutation
+            results = train(hyp.copy(), opt, device, callbacks)
+            callbacks = Callbacks()
+            # Write mutation results
+            print_mutation(KEYS[4:16], results, hyp.copy(), save_dir, opt.bucket)
+
+        # Plot results
+        plot_evolve(evolve_csv)
+        LOGGER.info(f'Hyperparameter evolution finished {opt.evolve} generations\n'
+                    f"Results saved to {colorstr('bold', save_dir)}\n"
+                    f'Usage example: $ python train.py --hyp {evolve_yaml}')
+
+
+def run(**kwargs):
+    # Usage: import train; train.run(data='coco128.yaml', imgsz=320, weights='yolov5m.pt')
+    opt = parse_opt(True)
+    for k, v in kwargs.items():
+        setattr(opt, k, v)
+    main(opt)
+    return opt
+
+
+if __name__ == '__main__':
+    opt = parse_opt()
+    main(opt)

segment/tutorial.ipynb

@@ -0,0 +1,595 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "t6MPjfT5NrKQ"
+      },
+      "source": [
+        "<div align=\"center\">\n",
+        "\n",
+        "  <a href=\"https://ultralytics.com/yolov5\" target=\"_blank\">\n",
+        "    <img width=\"1024\", src=\"https://raw.githubusercontent.com/ultralytics/assets/main/yolov5/v70/splash.png\"></a>\n",
+        "\n",
+        "\n",
+        "<br>\n",
+        "  <a href=\"https://bit.ly/yolov5-paperspace-notebook\"><img src=\"https://assets.paperspace.io/img/gradient-badge.svg\" alt=\"Run on Gradient\"></a>\n",
+        "  <a href=\"https://colab.research.google.com/github/ultralytics/yolov5/blob/master/segment/tutorial.ipynb\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"></a>\n",
+        "  <a href=\"https://www.kaggle.com/ultralytics/yolov5\"><img src=\"https://kaggle.com/static/images/open-in-kaggle.svg\" alt=\"Open In Kaggle\"></a>\n",
+        "<br>\n",
+        "\n",
+        "This <a href=\"https://github.com/ultralytics/yolov5\">YOLOv5</a> 🚀 notebook by <a href=\"https://ultralytics.com\">Ultralytics</a> presents simple train, validate and predict examples to help start your AI adventure.<br>See <a href=\"https://github.com/ultralytics/yolov5/issues/new/choose\">GitHub</a> for community support or <a href=\"https://ultralytics.com/contact\">contact us</a> for professional support.\n",
+        "\n",
+        "</div>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "7mGmQbAO5pQb"
+      },
+      "source": [
+        "# Setup\n",
+        "\n",
+        "Clone GitHub [repository](https://github.com/ultralytics/yolov5), install [dependencies](https://github.com/ultralytics/yolov5/blob/master/requirements.txt) and check PyTorch and GPU."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "wbvMlHd_QwMG",
+        "outputId": "171b23f0-71b9-4cbf-b666-6fa2ecef70c8"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "YOLOv5 🚀 v7.0-2-gc9d47ae Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB)\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Setup complete ✅ (2 CPUs, 12.7 GB RAM, 22.6/78.2 GB disk)\n"
+          ]
+        }
+      ],
+      "source": [
+        "!git clone https://github.com/ultralytics/yolov5  # clone\n",
+        "%cd yolov5\n",
+        "%pip install -qr requirements.txt comet_ml  # install\n",
+        "\n",
+        "import torch\n",
+        "import utils\n",
+        "display = utils.notebook_init()  # checks"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "4JnkELT0cIJg"
+      },
+      "source": [
+        "# 1. Predict\n",
+        "\n",
+        "`segment/predict.py` runs YOLOv5 instance segmentation inference on a variety of sources, downloading models automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases), and saving results to `runs/predict`. Example inference sources are:\n",
+        "\n",
+        "```shell\n",
+        "python segment/predict.py --source 0  # webcam\n",
+        "                             img.jpg  # image \n",
+        "                             vid.mp4  # video\n",
+        "                             screen  # screenshot\n",
+        "                             path/  # directory\n",
+        "                             'path/*.jpg'  # glob\n",
+        "                             'https://youtu.be/Zgi9g1ksQHc'  # YouTube\n",
+        "                             'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream\n",
+        "```"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "zR9ZbuQCH7FX",
+        "outputId": "3f67f1c7-f15e-4fa5-d251-967c3b77eaad"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "\u001b[34m\u001b[1msegment/predict: \u001b[0mweights=['yolov5s-seg.pt'], source=data/images, data=data/coco128.yaml, imgsz=[640, 640], conf_thres=0.25, iou_thres=0.45, max_det=1000, device=, view_img=False, save_txt=False, save_conf=False, save_crop=False, nosave=False, classes=None, agnostic_nms=False, augment=False, visualize=False, update=False, project=runs/predict-seg, name=exp, exist_ok=False, line_thickness=3, hide_labels=False, hide_conf=False, half=False, dnn=False, vid_stride=1, retina_masks=False\n",
+            "YOLOv5 🚀 v7.0-2-gc9d47ae Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB)\n",
+            "\n",
+            "Downloading https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5s-seg.pt to yolov5s-seg.pt...\n",
+            "100% 14.9M/14.9M [00:01<00:00, 12.0MB/s]\n",
+            "\n",
+            "Fusing layers... \n",
+            "YOLOv5s-seg summary: 224 layers, 7611485 parameters, 0 gradients, 26.4 GFLOPs\n",
+            "image 1/2 /content/yolov5/data/images/bus.jpg: 640x480 4 persons, 1 bus, 18.2ms\n",
+            "image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 2 persons, 1 tie, 13.4ms\n",
+            "Speed: 0.5ms pre-process, 15.8ms inference, 18.5ms NMS per image at shape (1, 3, 640, 640)\n",
+            "Results saved to \u001b[1mruns/predict-seg/exp\u001b[0m\n"
+          ]
+        }
+      ],
+      "source": [
+        "!python segment/predict.py --weights yolov5s-seg.pt --img 640 --conf 0.25 --source data/images\n",
+        "#display.Image(filename='runs/predict-seg/exp/zidane.jpg', width=600)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "hkAzDWJ7cWTr"
+      },
+      "source": [
+        "&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;\n",
+        "<img align=\"left\" src=\"https://user-images.githubusercontent.com/26833433/199030123-08c72f8d-6871-4116-8ed3-c373642cf28e.jpg\" width=\"600\">"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0eq1SMWl6Sfn"
+      },
+      "source": [
+        "# 2. Validate\n",
+        "Validate a model's accuracy on the [COCO](https://cocodataset.org/#home) dataset's `val` or `test` splits. Models are downloaded automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases). To show results by class use the `--verbose` flag."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "WQPtK1QYVaD_",
+        "outputId": "9d751d8c-bee8-4339-cf30-9854ca530449"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Downloading https://github.com/ultralytics/yolov5/releases/download/v1.0/coco2017labels-segments.zip  ...\n",
+            "Downloading http://images.cocodataset.org/zips/val2017.zip ...\n",
+            "######################################################################## 100.0%\n",
+            "######################################################################## 100.0%\n"
+          ]
+        }
+      ],
+      "source": [
+        "# Download COCO val\n",
+        "!bash data/scripts/get_coco.sh --val --segments  # download (780M - 5000 images)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "X58w8JLpMnjH",
+        "outputId": "a140d67a-02da-479e-9ddb-7d54bf9e407a"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "\u001b[34m\u001b[1msegment/val: \u001b[0mdata=/content/yolov5/data/coco.yaml, weights=['yolov5s-seg.pt'], batch_size=32, imgsz=640, conf_thres=0.001, iou_thres=0.6, max_det=300, task=val, device=, workers=8, single_cls=False, augment=False, verbose=False, save_txt=False, save_hybrid=False, save_conf=False, save_json=False, project=runs/val-seg, name=exp, exist_ok=False, half=True, dnn=False\n",
+            "YOLOv5 🚀 v7.0-2-gc9d47ae Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB)\n",
+            "\n",
+            "Fusing layers... \n",
+            "YOLOv5s-seg summary: 224 layers, 7611485 parameters, 0 gradients, 26.4 GFLOPs\n",
+            "\u001b[34m\u001b[1mval: \u001b[0mScanning /content/datasets/coco/val2017... 4952 images, 48 backgrounds, 0 corrupt: 100% 5000/5000 [00:03<00:00, 1361.31it/s]\n",
+            "\u001b[34m\u001b[1mval: \u001b[0mNew cache created: /content/datasets/coco/val2017.cache\n",
+            "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95)     Mask(P          R      mAP50  mAP50-95): 100% 157/157 [01:54<00:00,  1.37it/s]\n",
+            "                   all       5000      36335      0.673      0.517      0.566      0.373      0.672       0.49      0.532      0.319\n",
+            "Speed: 0.6ms pre-process, 4.4ms inference, 2.9ms NMS per image at shape (32, 3, 640, 640)\n",
+            "Results saved to \u001b[1mruns/val-seg/exp\u001b[0m\n"
+          ]
+        }
+      ],
+      "source": [
+        "# Validate YOLOv5s-seg on COCO val\n",
+        "!python segment/val.py --weights yolov5s-seg.pt --data coco.yaml --img 640 --half"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ZY2VXXXu74w5"
+      },
+      "source": [
+        "# 3. Train\n",
+        "\n",
+        "<p align=\"\"><a href=\"https://roboflow.com/?ref=ultralytics\"><img width=\"1000\" src=\"https://github.com/ultralytics/assets/raw/main/im/integrations-loop.png\"/></a></p>\n",
+        "Close the active learning loop by sampling images from your inference conditions with the `roboflow` pip package\n",
+        "<br><br>\n",
+        "\n",
+        "Train a YOLOv5s-seg model on the [COCO128](https://www.kaggle.com/ultralytics/coco128) dataset with `--data coco128-seg.yaml`, starting from pretrained `--weights yolov5s-seg.pt`, or from randomly initialized `--weights '' --cfg yolov5s-seg.yaml`.\n",
+        "\n",
+        "- **Pretrained [Models](https://github.com/ultralytics/yolov5/tree/master/models)** are downloaded\n",
+        "automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases)\n",
+        "- **[Datasets](https://github.com/ultralytics/yolov5/tree/master/data)** available for autodownload include: [COCO](https://github.com/ultralytics/yolov5/blob/master/data/coco.yaml), [COCO128](https://github.com/ultralytics/yolov5/blob/master/data/coco128.yaml), [VOC](https://github.com/ultralytics/yolov5/blob/master/data/VOC.yaml), [Argoverse](https://github.com/ultralytics/yolov5/blob/master/data/Argoverse.yaml), [VisDrone](https://github.com/ultralytics/yolov5/blob/master/data/VisDrone.yaml), [GlobalWheat](https://github.com/ultralytics/yolov5/blob/master/data/GlobalWheat2020.yaml), [xView](https://github.com/ultralytics/yolov5/blob/master/data/xView.yaml), [Objects365](https://github.com/ultralytics/yolov5/blob/master/data/Objects365.yaml), [SKU-110K](https://github.com/ultralytics/yolov5/blob/master/data/SKU-110K.yaml).\n",
+        "- **Training Results** are saved to `runs/train-seg/` with incrementing run directories, i.e. `runs/train-seg/exp2`, `runs/train-seg/exp3` etc.\n",
+        "<br><br>\n",
+        "\n",
+        "A **Mosaic Dataloader** is used for training which combines 4 images into 1 mosaic.\n",
+        "\n",
+        "## Train on Custom Data with Roboflow 🌟 NEW\n",
+        "\n",
+        "[Roboflow](https://roboflow.com/?ref=ultralytics) enables you to easily **organize, label, and prepare** a high quality dataset with your own custom data. Roboflow also makes it easy to establish an active learning pipeline, collaborate with your team on dataset improvement, and integrate directly into your model building workflow with the `roboflow` pip package.\n",
+        "\n",
+        "- Custom Training Example: [https://blog.roboflow.com/train-yolov5-instance-segmentation-custom-dataset/](https://blog.roboflow.com/train-yolov5-instance-segmentation-custom-dataset/?ref=ultralytics)\n",
+        "- Custom Training Notebook: [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1JTz7kpmHsg-5qwVz2d2IH3AaenI1tv0N?usp=sharing)\n",
+        "<br>\n",
+        "\n",
+        "<p align=\"\"><a href=\"https://roboflow.com/?ref=ultralytics\"><img width=\"480\" src=\"https://robflow-public-assets.s3.amazonaws.com/how-to-train-yolov5-segmentation-annotation.gif\"/></a></p>Label images lightning fast (including with model-assisted labeling)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "i3oKtE4g-aNn"
+      },
+      "outputs": [],
+      "source": [
+        "#@title Select YOLOv5 🚀 logger {run: 'auto'}\n",
+        "logger = 'Comet' #@param ['Comet', 'ClearML', 'TensorBoard']\n",
+        "\n",
+        "if logger == 'Comet':\n",
+        "  %pip install -q comet_ml\n",
+        "  import comet_ml; comet_ml.init()\n",
+        "elif logger == 'ClearML':\n",
+        "  %pip install -q clearml\n",
+        "  import clearml; clearml.browser_login()\n",
+        "elif logger == 'TensorBoard':\n",
+        "  %load_ext tensorboard\n",
+        "  %tensorboard --logdir runs/train"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "1NcFxRcFdJ_O",
+        "outputId": "3a3e0cf7-e79c-47a5-c8e7-2d26eeeab988"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "\u001b[34m\u001b[1msegment/train: \u001b[0mweights=yolov5s-seg.pt, cfg=, data=coco128-seg.yaml, hyp=data/hyps/hyp.scratch-low.yaml, epochs=3, batch_size=16, imgsz=640, rect=False, resume=False, nosave=False, noval=False, noautoanchor=False, noplots=False, evolve=None, bucket=, cache=ram, image_weights=False, device=, multi_scale=False, single_cls=False, optimizer=SGD, sync_bn=False, workers=8, project=runs/train-seg, name=exp, exist_ok=False, quad=False, cos_lr=False, label_smoothing=0.0, patience=100, freeze=[0], save_period=-1, seed=0, local_rank=-1, mask_ratio=4, no_overlap=False\n",
+            "\u001b[34m\u001b[1mgithub: \u001b[0mup to date with https://github.com/ultralytics/yolov5 ✅\n",
+            "YOLOv5 🚀 v7.0-2-gc9d47ae Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB)\n",
+            "\n",
+            "\u001b[34m\u001b[1mhyperparameters: \u001b[0mlr0=0.01, lrf=0.01, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=0.05, cls=0.5, cls_pw=1.0, obj=1.0, obj_pw=1.0, iou_t=0.2, anchor_t=4.0, fl_gamma=0.0, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, mosaic=1.0, mixup=0.0, copy_paste=0.0\n",
+            "\u001b[34m\u001b[1mTensorBoard: \u001b[0mStart with 'tensorboard --logdir runs/train-seg', view at http://localhost:6006/\n",
+            "\n",
+            "Dataset not found ⚠️, missing paths ['/content/datasets/coco128-seg/images/train2017']\n",
+            "Downloading https://ultralytics.com/assets/coco128-seg.zip to coco128-seg.zip...\n",
+            "100% 6.79M/6.79M [00:01<00:00, 6.73MB/s]\n",
+            "Dataset download success ✅ (1.9s), saved to \u001b[1m/content/datasets\u001b[0m\n",
+            "\n",
+            "                 from  n    params  module                                  arguments                     \n",
+            "  0                -1  1      3520  models.common.Conv                      [3, 32, 6, 2, 2]              \n",
+            "  1                -1  1     18560  models.common.Conv                      [32, 64, 3, 2]                \n",
+            "  2                -1  1     18816  models.common.C3                        [64, 64, 1]                   \n",
+            "  3                -1  1     73984  models.common.Conv                      [64, 128, 3, 2]               \n",
+            "  4                -1  2    115712  models.common.C3                        [128, 128, 2]                 \n",
+            "  5                -1  1    295424  models.common.Conv                      [128, 256, 3, 2]              \n",
+            "  6                -1  3    625152  models.common.C3                        [256, 256, 3]                 \n",
+            "  7                -1  1   1180672  models.common.Conv                      [256, 512, 3, 2]              \n",
+            "  8                -1  1   1182720  models.common.C3                        [512, 512, 1]                 \n",
+            "  9                -1  1    656896  models.common.SPPF                      [512, 512, 5]                 \n",
+            " 10                -1  1    131584  models.common.Conv                      [512, 256, 1, 1]              \n",
+            " 11                -1  1         0  torch.nn.modules.upsampling.Upsample    [None, 2, 'nearest']          \n",
+            " 12           [-1, 6]  1         0  models.common.Concat                    [1]                           \n",
+            " 13                -1  1    361984  models.common.C3                        [512, 256, 1, False]          \n",
+            " 14                -1  1     33024  models.common.Conv                      [256, 128, 1, 1]              \n",
+            " 15                -1  1         0  torch.nn.modules.upsampling.Upsample    [None, 2, 'nearest']          \n",
+            " 16           [-1, 4]  1         0  models.common.Concat                    [1]                           \n",
+            " 17                -1  1     90880  models.common.C3                        [256, 128, 1, False]          \n",
+            " 18                -1  1    147712  models.common.Conv                      [128, 128, 3, 2]              \n",
+            " 19          [-1, 14]  1         0  models.common.Concat                    [1]                           \n",
+            " 20                -1  1    296448  models.common.C3                        [256, 256, 1, False]          \n",
+            " 21                -1  1    590336  models.common.Conv                      [256, 256, 3, 2]              \n",
+            " 22          [-1, 10]  1         0  models.common.Concat                    [1]                           \n",
+            " 23                -1  1   1182720  models.common.C3                        [512, 512, 1, False]          \n",
+            " 24      [17, 20, 23]  1    615133  models.yolo.Segment                     [80, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], 32, 128, [128, 256, 512]]\n",
+            "Model summary: 225 layers, 7621277 parameters, 7621277 gradients, 26.6 GFLOPs\n",
+            "\n",
+            "Transferred 367/367 items from yolov5s-seg.pt\n",
+            "\u001b[34m\u001b[1mAMP: \u001b[0mchecks passed ✅\n",
+            "\u001b[34m\u001b[1moptimizer:\u001b[0m SGD(lr=0.01) with parameter groups 60 weight(decay=0.0), 63 weight(decay=0.0005), 63 bias\n",
+            "\u001b[34m\u001b[1malbumentations: \u001b[0mBlur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01), CLAHE(p=0.01, clip_limit=(1, 4.0), tile_grid_size=(8, 8))\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mScanning /content/datasets/coco128-seg/labels/train2017... 126 images, 2 backgrounds, 0 corrupt: 100% 128/128 [00:00<00:00, 1389.59it/s]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mNew cache created: /content/datasets/coco128-seg/labels/train2017.cache\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 238.86it/s]\n",
+            "\u001b[34m\u001b[1mval: \u001b[0mScanning /content/datasets/coco128-seg/labels/train2017.cache... 126 images, 2 backgrounds, 0 corrupt: 100% 128/128 [00:00<?, ?it/s]\n",
+            "\u001b[34m\u001b[1mval: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:01<00:00, 98.90it/s]\n",
+            "\n",
+            "\u001b[34m\u001b[1mAutoAnchor: \u001b[0m4.27 anchors/target, 0.994 Best Possible Recall (BPR). Current anchors are a good fit to dataset ✅\n",
+            "Plotting labels to runs/train-seg/exp/labels.jpg... \n",
+            "Image sizes 640 train, 640 val\n",
+            "Using 2 dataloader workers\n",
+            "Logging results to \u001b[1mruns/train-seg/exp\u001b[0m\n",
+            "Starting training for 3 epochs...\n",
+            "\n",
+            "      Epoch    GPU_mem   box_loss   seg_loss   obj_loss   cls_loss  Instances       Size\n",
+            "        0/2      4.92G     0.0417    0.04646    0.06066    0.02126        192        640: 100% 8/8 [00:08<00:00,  1.10s/it]\n",
+            "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95)     Mask(P          R      mAP50  mAP50-95): 100% 4/4 [00:02<00:00,  1.81it/s]\n",
+            "                   all        128        929      0.737      0.649      0.715      0.492      0.719      0.617      0.658      0.408\n",
+            "\n",
+            "      Epoch    GPU_mem   box_loss   seg_loss   obj_loss   cls_loss  Instances       Size\n",
+            "        1/2      6.29G    0.04157    0.04503    0.05772    0.01777        208        640: 100% 8/8 [00:09<00:00,  1.21s/it]\n",
+            "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95)     Mask(P          R      mAP50  mAP50-95): 100% 4/4 [00:02<00:00,  1.87it/s]\n",
+            "                   all        128        929      0.756      0.674      0.738      0.506      0.725       0.64       0.68      0.422\n",
+            "\n",
+            "      Epoch    GPU_mem   box_loss   seg_loss   obj_loss   cls_loss  Instances       Size\n",
+            "        2/2      6.29G     0.0425    0.04793    0.06784    0.01863        161        640: 100% 8/8 [00:03<00:00,  2.02it/s]\n",
+            "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95)     Mask(P          R      mAP50  mAP50-95): 100% 4/4 [00:02<00:00,  1.88it/s]\n",
+            "                   all        128        929      0.736      0.694      0.747      0.522      0.769      0.622      0.683      0.427\n",
+            "\n",
+            "3 epochs completed in 0.009 hours.\n",
+            "Optimizer stripped from runs/train-seg/exp/weights/last.pt, 15.6MB\n",
+            "Optimizer stripped from runs/train-seg/exp/weights/best.pt, 15.6MB\n",
+            "\n",
+            "Validating runs/train-seg/exp/weights/best.pt...\n",
+            "Fusing layers... \n",
+            "Model summary: 165 layers, 7611485 parameters, 0 gradients, 26.4 GFLOPs\n",
+            "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95)     Mask(P          R      mAP50  mAP50-95): 100% 4/4 [00:06<00:00,  1.59s/it]\n",
+            "                   all        128        929      0.738      0.694      0.746      0.522      0.759      0.625      0.682      0.426\n",
+            "                person        128        254      0.845      0.756      0.836       0.55      0.861      0.669      0.759      0.407\n",
+            "               bicycle        128          6      0.475      0.333      0.549      0.341      0.711      0.333      0.526      0.322\n",
+            "                   car        128         46      0.612      0.565      0.539      0.257      0.555      0.435      0.477      0.171\n",
+            "            motorcycle        128          5       0.73        0.8      0.752      0.571      0.747        0.8      0.752       0.42\n",
+            "              airplane        128          6          1      0.943      0.995      0.732       0.92      0.833      0.839      0.555\n",
+            "                   bus        128          7      0.677      0.714      0.722      0.653      0.711      0.714      0.722      0.593\n",
+            "                 train        128          3          1      0.951      0.995      0.551          1      0.884      0.995      0.781\n",
+            "                 truck        128         12      0.555      0.417      0.457      0.285      0.624      0.417      0.397      0.277\n",
+            "                  boat        128          6      0.624        0.5      0.584      0.186          1      0.326      0.412      0.133\n",
+            "         traffic light        128         14      0.513      0.302      0.411      0.247      0.435      0.214      0.376      0.251\n",
+            "             stop sign        128          2      0.824          1      0.995      0.796      0.906          1      0.995      0.747\n",
+            "                 bench        128          9       0.75      0.667      0.763      0.367      0.724      0.585      0.698      0.209\n",
+            "                  bird        128         16      0.961          1      0.995      0.686      0.918      0.938       0.91      0.525\n",
+            "                   cat        128          4      0.771      0.857      0.945      0.752       0.76        0.8      0.945      0.728\n",
+            "                   dog        128          9      0.987      0.778      0.963      0.681          1      0.705       0.89      0.574\n",
+            "                 horse        128          2      0.703          1      0.995      0.697      0.759          1      0.995      0.249\n",
+            "              elephant        128         17      0.916      0.882       0.93      0.691      0.811      0.765      0.829      0.537\n",
+            "                  bear        128          1      0.664          1      0.995      0.995      0.701          1      0.995      0.895\n",
+            "                 zebra        128          4      0.864          1      0.995      0.921      0.879          1      0.995      0.804\n",
+            "               giraffe        128          9      0.883      0.889       0.94      0.683      0.845      0.778       0.78      0.463\n",
+            "              backpack        128          6          1       0.59      0.701      0.372          1      0.474       0.52      0.252\n",
+            "              umbrella        128         18      0.654      0.839      0.887       0.52      0.517      0.556      0.427      0.229\n",
+            "               handbag        128         19       0.54      0.211      0.408      0.221      0.796      0.206      0.396      0.196\n",
+            "                   tie        128          7      0.864      0.857      0.857      0.577      0.925      0.857      0.857      0.534\n",
+            "              suitcase        128          4      0.716          1      0.945      0.647      0.767          1      0.945      0.634\n",
+            "               frisbee        128          5      0.708        0.8      0.761      0.643      0.737        0.8      0.761      0.501\n",
+            "                  skis        128          1      0.691          1      0.995      0.796      0.761          1      0.995      0.199\n",
+            "             snowboard        128          7      0.918      0.857      0.904      0.604       0.32      0.286      0.235      0.137\n",
+            "           sports ball        128          6      0.902      0.667      0.701      0.466      0.727        0.5      0.497      0.471\n",
+            "                  kite        128         10      0.586        0.4      0.511      0.231      0.663      0.394      0.417      0.139\n",
+            "          baseball bat        128          4      0.359        0.5      0.401      0.169      0.631        0.5      0.526      0.133\n",
+            "        baseball glove        128          7          1      0.519       0.58      0.327      0.687      0.286      0.455      0.328\n",
+            "            skateboard        128          5      0.729        0.8      0.862      0.631      0.599        0.6      0.604      0.379\n",
+            "         tennis racket        128          7       0.57      0.714      0.645      0.448      0.608      0.714      0.645      0.412\n",
+            "                bottle        128         18      0.469      0.393      0.537      0.357      0.661      0.389      0.543      0.349\n",
+            "            wine glass        128         16      0.677      0.938      0.866      0.441       0.53      0.625       0.67      0.334\n",
+            "                   cup        128         36      0.777      0.722      0.812      0.466      0.725      0.583      0.762      0.467\n",
+            "                  fork        128          6      0.948      0.333      0.425       0.27      0.527      0.167       0.18      0.102\n",
+            "                 knife        128         16      0.757      0.587      0.669      0.458       0.79        0.5      0.552       0.34\n",
+            "                 spoon        128         22       0.74      0.364      0.559      0.269      0.925      0.364      0.513      0.213\n",
+            "                  bowl        128         28      0.766      0.714      0.725      0.559      0.803      0.584      0.665      0.353\n",
+            "                banana        128          1      0.408          1      0.995      0.398      0.539          1      0.995      0.497\n",
+            "              sandwich        128          2          1          0      0.695      0.536          1          0      0.498      0.448\n",
+            "                orange        128          4      0.467          1      0.995      0.693      0.518          1      0.995      0.663\n",
+            "              broccoli        128         11      0.462      0.455      0.383      0.259      0.548      0.455      0.384      0.256\n",
+            "                carrot        128         24      0.631      0.875       0.77      0.533      0.757      0.909      0.853      0.499\n",
+            "               hot dog        128          2      0.555          1      0.995      0.995      0.578          1      0.995      0.796\n",
+            "                 pizza        128          5       0.89        0.8      0.962      0.796          1      0.778      0.962      0.766\n",
+            "                 donut        128         14      0.695          1      0.893      0.772      0.704          1      0.893      0.696\n",
+            "                  cake        128          4      0.826          1      0.995       0.92      0.862          1      0.995      0.846\n",
+            "                 chair        128         35       0.53      0.571      0.613      0.336       0.67        0.6      0.538      0.271\n",
+            "                 couch        128          6      0.972      0.667      0.833      0.627          1       0.62      0.696      0.394\n",
+            "          potted plant        128         14        0.7      0.857      0.883      0.552      0.836      0.857      0.883      0.473\n",
+            "                   bed        128          3      0.979      0.667       0.83      0.366          1          0       0.83      0.373\n",
+            "          dining table        128         13      0.775      0.308      0.505      0.364      0.644      0.231       0.25     0.0804\n",
+            "                toilet        128          2      0.836          1      0.995      0.846      0.887          1      0.995      0.797\n",
+            "                    tv        128          2        0.6          1      0.995      0.846      0.655          1      0.995      0.896\n",
+            "                laptop        128          3      0.822      0.333      0.445      0.307          1          0      0.392       0.12\n",
+            "                 mouse        128          2          1          0          0          0          1          0          0          0\n",
+            "                remote        128          8      0.745        0.5       0.62      0.459      0.821        0.5      0.624      0.449\n",
+            "            cell phone        128          8      0.686      0.375      0.502      0.272      0.488       0.25       0.28      0.132\n",
+            "             microwave        128          3      0.831          1      0.995      0.722      0.867          1      0.995      0.592\n",
+            "                  oven        128          5      0.439        0.4      0.435      0.294      0.823        0.6      0.645      0.418\n",
+            "                  sink        128          6      0.677        0.5      0.565      0.448      0.722        0.5       0.46      0.362\n",
+            "          refrigerator        128          5      0.533        0.8      0.783      0.524      0.558        0.8      0.783      0.527\n",
+            "                  book        128         29      0.732      0.379      0.423      0.196       0.69      0.207       0.38      0.131\n",
+            "                 clock        128          9      0.889      0.778      0.917      0.677      0.908      0.778      0.875      0.604\n",
+            "                  vase        128          2      0.375          1      0.995      0.995      0.455          1      0.995      0.796\n",
+            "              scissors        128          1          1          0     0.0166    0.00166          1          0          0          0\n",
+            "            teddy bear        128         21      0.813      0.829      0.841      0.457      0.826      0.678      0.786      0.422\n",
+            "            toothbrush        128          5      0.806          1      0.995      0.733      0.991          1      0.995      0.628\n",
+            "Results saved to \u001b[1mruns/train-seg/exp\u001b[0m\n"
+          ]
+        }
+      ],
+      "source": [
+        "# Train YOLOv5s on COCO128 for 3 epochs\n",
+        "!python segment/train.py --img 640 --batch 16 --epochs 3 --data coco128-seg.yaml --weights yolov5s-seg.pt --cache"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "15glLzbQx5u0"
+      },
+      "source": [
+        "# 4. Visualize"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "nWOsI5wJR1o3"
+      },
+      "source": [
+        "## Comet Logging and Visualization 🌟 NEW\n",
+        "\n",
+        "[Comet](https://www.comet.com/site/lp/yolov5-with-comet/?utm_source=yolov5&utm_medium=partner&utm_campaign=partner_yolov5_2022&utm_content=yolov5_colab) is now fully integrated with YOLOv5. Track and visualize model metrics in real time, save your hyperparameters, datasets, and model checkpoints, and visualize your model predictions with [Comet Custom Panels](https://www.comet.com/docs/v2/guides/comet-dashboard/code-panels/about-panels/?utm_source=yolov5&utm_medium=partner&utm_campaign=partner_yolov5_2022&utm_content=yolov5_colab)! Comet makes sure you never lose track of your work and makes it easy to share results and collaborate across teams of all sizes!\n",
+        "\n",
+        "Getting started is easy:\n",
+        "```shell\n",
+        "pip install comet_ml  # 1. install\n",
+        "export COMET_API_KEY=<Your API Key>  # 2. paste API key\n",
+        "python train.py --img 640 --epochs 3 --data coco128.yaml --weights yolov5s.pt  # 3. train\n",
+        "```\n",
+        "To learn more about all of the supported Comet features for this integration, check out the [Comet Tutorial](https://docs.ultralytics.com/yolov5/tutorials/comet_logging_integration). If you'd like to learn more about Comet, head over to our [documentation](https://www.comet.com/docs/v2/?utm_source=yolov5&utm_medium=partner&utm_campaign=partner_yolov5_2022&utm_content=yolov5_colab). Get started by trying out the Comet Colab Notebook:\n",
+        "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1RG0WOQyxlDlo5Km8GogJpIEJlg_5lyYO?usp=sharing)\n",
+        "\n",
+        "<a href=\"https://bit.ly/yolov5-readme-comet2\">\n",
+        "<img alt=\"Comet Dashboard\" src=\"https://user-images.githubusercontent.com/26833433/202851203-164e94e1-2238-46dd-91f8-de020e9d6b41.png\" width=\"1280\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "Lay2WsTjNJzP"
+      },
+      "source": [
+        "## ClearML Logging and Automation 🌟 NEW\n",
+        "\n",
+        "[ClearML](https://cutt.ly/yolov5-notebook-clearml) is completely integrated into YOLOv5 to track your experimentation, manage dataset versions and even remotely execute training runs. To enable ClearML (check cells above):\n",
+        "\n",
+        "- `pip install clearml`\n",
+        "- run `clearml-init` to connect to a ClearML server (**deploy your own [open-source server](https://github.com/allegroai/clearml-server)**, or use our [free hosted server](https://cutt.ly/yolov5-notebook-clearml))\n",
+        "\n",
+        "You'll get all the great expected features from an experiment manager: live updates, model upload, experiment comparison etc. but ClearML also tracks uncommitted changes and installed packages for example. Thanks to that ClearML Tasks (which is what we call experiments) are also reproducible on different machines! With only 1 extra line, we can schedule a YOLOv5 training task on a queue to be executed by any number of ClearML Agents (workers).\n",
+        "\n",
+        "You can use ClearML Data to version your dataset and then pass it to YOLOv5 simply using its unique ID. This will help you keep track of your data without adding extra hassle. Explore the [ClearML Tutorial](https://docs.ultralytics.com/yolov5/tutorials/clearml_logging_integration) for details!\n",
+        "\n",
+        "<a href=\"https://cutt.ly/yolov5-notebook-clearml\">\n",
+        "<img alt=\"ClearML Experiment Management UI\" src=\"https://github.com/thepycoder/clearml_screenshots/raw/main/scalars.jpg\" width=\"1280\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "-WPvRbS5Swl6"
+      },
+      "source": [
+        "## Local Logging\n",
+        "\n",
+        "Training results are automatically logged with [Tensorboard](https://www.tensorflow.org/tensorboard) and [CSV](https://github.com/ultralytics/yolov5/pull/4148) loggers to `runs/train`, with a new experiment directory created for each new training as `runs/train/exp2`, `runs/train/exp3`, etc.\n",
+        "\n",
+        "This directory contains train and val statistics, mosaics, labels, predictions and augmentated mosaics, as well as metrics and charts including precision-recall (PR) curves and confusion matrices. \n",
+        "\n",
+        "<img alt=\"Local logging results\" src=\"https://user-images.githubusercontent.com/26833433/183222430-e1abd1b7-782c-4cde-b04d-ad52926bf818.jpg\" width=\"1280\"/>\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "Zelyeqbyt3GD"
+      },
+      "source": [
+        "# Environments\n",
+        "\n",
+        "YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including [CUDA](https://developer.nvidia.com/cuda)/[CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/) and [PyTorch](https://pytorch.org/) preinstalled):\n",
+        "\n",
+        "- **Notebooks** with free GPU: <a href=\"https://bit.ly/yolov5-paperspace-notebook\"><img src=\"https://assets.paperspace.io/img/gradient-badge.svg\" alt=\"Run on Gradient\"></a> <a href=\"https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"></a> <a href=\"https://www.kaggle.com/ultralytics/yolov5\"><img src=\"https://kaggle.com/static/images/open-in-kaggle.svg\" alt=\"Open In Kaggle\"></a>\n",
+        "- **Google Cloud** Deep Learning VM. See [GCP Quickstart Guide](https://docs.ultralytics.com/yolov5/environments/google_cloud_quickstart_tutorial/)\n",
+        "- **Amazon** Deep Learning AMI. See [AWS Quickstart Guide](https://docs.ultralytics.com/yolov5/environments/aws_quickstart_tutorial/)\n",
+        "- **Docker Image**. See [Docker Quickstart Guide](https://docs.ultralytics.com/yolov5/environments/docker_image_quickstart_tutorial/) <a href=\"https://hub.docker.com/r/ultralytics/yolov5\"><img src=\"https://img.shields.io/docker/pulls/ultralytics/yolov5?logo=docker\" alt=\"Docker Pulls\"></a>\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6Qu7Iesl0p54"
+      },
+      "source": [
+        "# Status\n",
+        "\n",
+        "![YOLOv5 CI](https://github.com/ultralytics/yolov5/actions/workflows/ci-testing.yml/badge.svg)\n",
+        "\n",
+        "If this badge is green, all [YOLOv5 GitHub Actions](https://github.com/ultralytics/yolov5/actions) Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training ([train.py](https://github.com/ultralytics/yolov5/blob/master/train.py)), testing ([val.py](https://github.com/ultralytics/yolov5/blob/master/val.py)), inference ([detect.py](https://github.com/ultralytics/yolov5/blob/master/detect.py)) and export ([export.py](https://github.com/ultralytics/yolov5/blob/master/export.py)) on macOS, Windows, and Ubuntu every 24 hours and on every commit.\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "IEijrePND_2I"
+      },
+      "source": [
+        "# Appendix\n",
+        "\n",
+        "Additional content below."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "GMusP4OAxFu6"
+      },
+      "outputs": [],
+      "source": [
+        "# YOLOv5 PyTorch HUB Inference (DetectionModels only)\n",
+        "import torch\n",
+        "\n",
+        "model = torch.hub.load('ultralytics/yolov5', 'yolov5s-seg', force_reload=True, trust_repo=True)  # or yolov5n - yolov5x6 or custom\n",
+        "im = 'https://ultralytics.com/images/zidane.jpg'  # file, Path, PIL.Image, OpenCV, nparray, list\n",
+        "results = model(im)  # inference\n",
+        "results.print()  # or .show(), .save(), .crop(), .pandas(), etc."
+      ]
+    }
+  ],
+  "metadata": {
+    "accelerator": "GPU",
+    "colab": {
+      "name": "YOLOv5 Segmentation Tutorial",
+      "provenance": [],
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3 (ipykernel)",
+      "language": "python",
+      "name": "python3"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.7.12"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

segment/val.py

@@ -0,0 +1,473 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+"""
+Validate a trained YOLOv5 segment model on a segment dataset
+
+Usage:
+    $ bash data/scripts/get_coco.sh --val --segments  # download COCO-segments val split (1G, 5000 images)
+    $ python segment/val.py --weights yolov5s-seg.pt --data coco.yaml --img 640  # validate COCO-segments
+
+Usage - formats:
+    $ python segment/val.py --weights yolov5s-seg.pt                 # PyTorch
+                                      yolov5s-seg.torchscript        # TorchScript
+                                      yolov5s-seg.onnx               # ONNX Runtime or OpenCV DNN with --dnn
+                                      yolov5s-seg_openvino_label     # OpenVINO
+                                      yolov5s-seg.engine             # TensorRT
+                                      yolov5s-seg.mlmodel            # CoreML (macOS-only)
+                                      yolov5s-seg_saved_model        # TensorFlow SavedModel
+                                      yolov5s-seg.pb                 # TensorFlow GraphDef
+                                      yolov5s-seg.tflite             # TensorFlow Lite
+                                      yolov5s-seg_edgetpu.tflite     # TensorFlow Edge TPU
+                                      yolov5s-seg_paddle_model       # PaddlePaddle
+"""
+
+import argparse
+import json
+import os
+import subprocess
+import sys
+from multiprocessing.pool import ThreadPool
+from pathlib import Path
+
+import numpy as np
+import torch
+from tqdm import tqdm
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[1]  # YOLOv5 root directory
+if str(ROOT) not in sys.path:
+    sys.path.append(str(ROOT))  # add ROOT to PATH
+ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative
+
+import torch.nn.functional as F
+
+from models.common import DetectMultiBackend
+from models.yolo import SegmentationModel
+from utils.callbacks import Callbacks
+from utils.general import (LOGGER, NUM_THREADS, TQDM_BAR_FORMAT, Profile, check_dataset, check_img_size,
+                           check_requirements, check_yaml, coco80_to_coco91_class, colorstr, increment_path,
+                           non_max_suppression, print_args, scale_boxes, xywh2xyxy, xyxy2xywh)
+from utils.metrics import ConfusionMatrix, box_iou
+from utils.plots import output_to_target, plot_val_study
+from utils.segment.dataloaders import create_dataloader
+from utils.segment.general import mask_iou, process_mask, process_mask_native, scale_image
+from utils.segment.metrics import Metrics, ap_per_class_box_and_mask
+from utils.segment.plots import plot_images_and_masks
+from utils.torch_utils import de_parallel, select_device, smart_inference_mode
+
+
+def save_one_txt(predn, save_conf, shape, file):
+    # Save one txt result
+    gn = torch.tensor(shape)[[1, 0, 1, 0]]  # normalization gain whwh
+    for *xyxy, conf, cls in predn.tolist():
+        xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
+        line = (cls, *xywh, conf) if save_conf else (cls, *xywh)  # label format
+        with open(file, 'a') as f:
+            f.write(('%g ' * len(line)).rstrip() % line + '\n')
+
+
+def save_one_json(predn, jdict, path, class_map, pred_masks):
+    # Save one JSON result {"image_id": 42, "category_id": 18, "bbox": [258.15, 41.29, 348.26, 243.78], "score": 0.236}
+    from pycocotools.mask import encode
+
+    def single_encode(x):
+        rle = encode(np.asarray(x[:, :, None], order='F', dtype='uint8'))[0]
+        rle['counts'] = rle['counts'].decode('utf-8')
+        return rle
+
+    image_id = int(path.stem) if path.stem.isnumeric() else path.stem
+    box = xyxy2xywh(predn[:, :4])  # xywh
+    box[:, :2] -= box[:, 2:] / 2  # xy center to top-left corner
+    pred_masks = np.transpose(pred_masks, (2, 0, 1))
+    with ThreadPool(NUM_THREADS) as pool:
+        rles = pool.map(single_encode, pred_masks)
+    for i, (p, b) in enumerate(zip(predn.tolist(), box.tolist())):
+        jdict.append({
+            'image_id': image_id,
+            'category_id': class_map[int(p[5])],
+            'bbox': [round(x, 3) for x in b],
+            'score': round(p[4], 5),
+            'segmentation': rles[i]})
+
+
+def process_batch(detections, labels, iouv, pred_masks=None, gt_masks=None, overlap=False, masks=False):
+    """
+    Return correct prediction matrix
+    Arguments:
+        detections (array[N, 6]), x1, y1, x2, y2, conf, class
+        labels (array[M, 5]), class, x1, y1, x2, y2
+    Returns:
+        correct (array[N, 10]), for 10 IoU levels
+    """
+    if masks:
+        if overlap:
+            nl = len(labels)
+            index = torch.arange(nl, device=gt_masks.device).view(nl, 1, 1) + 1
+            gt_masks = gt_masks.repeat(nl, 1, 1)  # shape(1,640,640) -> (n,640,640)
+            gt_masks = torch.where(gt_masks == index, 1.0, 0.0)
+        if gt_masks.shape[1:] != pred_masks.shape[1:]:
+            gt_masks = F.interpolate(gt_masks[None], pred_masks.shape[1:], mode='bilinear', align_corners=False)[0]
+            gt_masks = gt_masks.gt_(0.5)
+        iou = mask_iou(gt_masks.view(gt_masks.shape[0], -1), pred_masks.view(pred_masks.shape[0], -1))
+    else:  # boxes
+        iou = box_iou(labels[:, 1:], detections[:, :4])
+
+    correct = np.zeros((detections.shape[0], iouv.shape[0])).astype(bool)
+    correct_class = labels[:, 0:1] == detections[:, 5]
+    for i in range(len(iouv)):
+        x = torch.where((iou >= iouv[i]) & correct_class)  # IoU > threshold and classes match
+        if x[0].shape[0]:
+            matches = torch.cat((torch.stack(x, 1), iou[x[0], x[1]][:, None]), 1).cpu().numpy()  # [label, detect, iou]
+            if x[0].shape[0] > 1:
+                matches = matches[matches[:, 2].argsort()[::-1]]
+                matches = matches[np.unique(matches[:, 1], return_index=True)[1]]
+                # matches = matches[matches[:, 2].argsort()[::-1]]
+                matches = matches[np.unique(matches[:, 0], return_index=True)[1]]
+            correct[matches[:, 1].astype(int), i] = True
+    return torch.tensor(correct, dtype=torch.bool, device=iouv.device)
+
+
+@smart_inference_mode()
+def run(
+        data,
+        weights=None,  # model.pt path(s)
+        batch_size=32,  # batch size
+        imgsz=640,  # inference size (pixels)
+        conf_thres=0.001,  # confidence threshold
+        iou_thres=0.6,  # NMS IoU threshold
+        max_det=300,  # maximum detections per image
+        task='val',  # train, val, test, speed or study
+        device='',  # cuda device, i.e. 0 or 0,1,2,3 or cpu
+        workers=8,  # max dataloader workers (per RANK in DDP mode)
+        single_cls=False,  # treat as single-class dataset
+        augment=False,  # augmented inference
+        verbose=False,  # verbose output
+        save_txt=False,  # save results to *.txt
+        save_hybrid=False,  # save label+prediction hybrid results to *.txt
+        save_conf=False,  # save confidences in --save-txt labels
+        save_json=False,  # save a COCO-JSON results file
+        project=ROOT / 'runs/val-seg',  # save to project/name
+        name='exp',  # save to project/name
+        exist_ok=False,  # existing project/name ok, do not increment
+        half=True,  # use FP16 half-precision inference
+        dnn=False,  # use OpenCV DNN for ONNX inference
+        model=None,
+        dataloader=None,
+        save_dir=Path(''),
+        plots=True,
+        overlap=False,
+        mask_downsample_ratio=1,
+        compute_loss=None,
+        callbacks=Callbacks(),
+):
+    if save_json:
+        check_requirements('pycocotools>=2.0.6')
+        process = process_mask_native  # more accurate
+    else:
+        process = process_mask  # faster
+
+    # Initialize/load model and set device
+    training = model is not None
+    if training:  # called by train.py
+        device, pt, jit, engine = next(model.parameters()).device, True, False, False  # get model device, PyTorch model
+        half &= device.type != 'cpu'  # half precision only supported on CUDA
+        model.half() if half else model.float()
+        nm = de_parallel(model).model[-1].nm  # number of masks
+    else:  # called directly
+        device = select_device(device, batch_size=batch_size)
+
+        # Directories
+        save_dir = increment_path(Path(project) / name, exist_ok=exist_ok)  # increment run
+        (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir
+
+        # Load model
+        model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
+        stride, pt, jit, engine = model.stride, model.pt, model.jit, model.engine
+        imgsz = check_img_size(imgsz, s=stride)  # check image size
+        half = model.fp16  # FP16 supported on limited backends with CUDA
+        nm = de_parallel(model).model.model[-1].nm if isinstance(model, SegmentationModel) else 32  # number of masks
+        if engine:
+            batch_size = model.batch_size
+        else:
+            device = model.device
+            if not (pt or jit):
+                batch_size = 1  # export.py models default to batch-size 1
+                LOGGER.info(f'Forcing --batch-size 1 square inference (1,3,{imgsz},{imgsz}) for non-PyTorch models')
+
+        # Data
+        data = check_dataset(data)  # check
+
+    # Configure
+    model.eval()
+    cuda = device.type != 'cpu'
+    is_coco = isinstance(data.get('val'), str) and data['val'].endswith(f'coco{os.sep}val2017.txt')  # COCO dataset
+    nc = 1 if single_cls else int(data['nc'])  # number of classes
+    iouv = torch.linspace(0.5, 0.95, 10, device=device)  # iou vector for mAP@0.5:0.95
+    niou = iouv.numel()
+
+    # Dataloader
+    if not training:
+        if pt and not single_cls:  # check --weights are trained on --data
+            ncm = model.model.nc
+            assert ncm == nc, f'{weights} ({ncm} classes) trained on different --data than what you passed ({nc} ' \
+                              f'classes). Pass correct combination of --weights and --data that are trained together.'
+        model.warmup(imgsz=(1 if pt else batch_size, 3, imgsz, imgsz))  # warmup
+        pad, rect = (0.0, False) if task == 'speed' else (0.5, pt)  # square inference for benchmarks
+        task = task if task in ('train', 'val', 'test') else 'val'  # path to train/val/test images
+        dataloader = create_dataloader(data[task],
+                                       imgsz,
+                                       batch_size,
+                                       stride,
+                                       single_cls,
+                                       pad=pad,
+                                       rect=rect,
+                                       workers=workers,
+                                       prefix=colorstr(f'{task}: '),
+                                       overlap_mask=overlap,
+                                       mask_downsample_ratio=mask_downsample_ratio)[0]
+
+    seen = 0
+    confusion_matrix = ConfusionMatrix(nc=nc)
+    names = model.names if hasattr(model, 'names') else model.module.names  # get class names
+    if isinstance(names, (list, tuple)):  # old format
+        names = dict(enumerate(names))
+    class_map = coco80_to_coco91_class() if is_coco else list(range(1000))
+    s = ('%22s' + '%11s' * 10) % ('Class', 'Images', 'Instances', 'Box(P', 'R', 'mAP50', 'mAP50-95)', 'Mask(P', 'R',
+                                  'mAP50', 'mAP50-95)')
+    dt = Profile(), Profile(), Profile()
+    metrics = Metrics()
+    loss = torch.zeros(4, device=device)
+    jdict, stats = [], []
+    # callbacks.run('on_val_start')
+    pbar = tqdm(dataloader, desc=s, bar_format=TQDM_BAR_FORMAT)  # progress bar
+    for batch_i, (im, targets, paths, shapes, masks) in enumerate(pbar):
+        # callbacks.run('on_val_batch_start')
+        with dt[0]:
+            if cuda:
+                im = im.to(device, non_blocking=True)
+                targets = targets.to(device)
+                masks = masks.to(device)
+            masks = masks.float()
+            im = im.half() if half else im.float()  # uint8 to fp16/32
+            im /= 255  # 0 - 255 to 0.0 - 1.0
+            nb, _, height, width = im.shape  # batch size, channels, height, width
+
+        # Inference
+        with dt[1]:
+            preds, protos, train_out = model(im) if compute_loss else (*model(im, augment=augment)[:2], None)
+
+        # Loss
+        if compute_loss:
+            loss += compute_loss((train_out, protos), targets, masks)[1]  # box, obj, cls
+
+        # NMS
+        targets[:, 2:] *= torch.tensor((width, height, width, height), device=device)  # to pixels
+        lb = [targets[targets[:, 0] == i, 1:] for i in range(nb)] if save_hybrid else []  # for autolabelling
+        with dt[2]:
+            preds = non_max_suppression(preds,
+                                        conf_thres,
+                                        iou_thres,
+                                        labels=lb,
+                                        multi_label=True,
+                                        agnostic=single_cls,
+                                        max_det=max_det,
+                                        nm=nm)
+
+        # Metrics
+        plot_masks = []  # masks for plotting
+        for si, (pred, proto) in enumerate(zip(preds, protos)):
+            labels = targets[targets[:, 0] == si, 1:]
+            nl, npr = labels.shape[0], pred.shape[0]  # number of labels, predictions
+            path, shape = Path(paths[si]), shapes[si][0]
+            correct_masks = torch.zeros(npr, niou, dtype=torch.bool, device=device)  # init
+            correct_bboxes = torch.zeros(npr, niou, dtype=torch.bool, device=device)  # init
+            seen += 1
+
+            if npr == 0:
+                if nl:
+                    stats.append((correct_masks, correct_bboxes, *torch.zeros((2, 0), device=device), labels[:, 0]))
+                    if plots:
+                        confusion_matrix.process_batch(detections=None, labels=labels[:, 0])
+                continue
+
+            # Masks
+            midx = [si] if overlap else targets[:, 0] == si
+            gt_masks = masks[midx]
+            pred_masks = process(proto, pred[:, 6:], pred[:, :4], shape=im[si].shape[1:])
+
+            # Predictions
+            if single_cls:
+                pred[:, 5] = 0
+            predn = pred.clone()
+            scale_boxes(im[si].shape[1:], predn[:, :4], shape, shapes[si][1])  # native-space pred
+
+            # Evaluate
+            if nl:
+                tbox = xywh2xyxy(labels[:, 1:5])  # target boxes
+                scale_boxes(im[si].shape[1:], tbox, shape, shapes[si][1])  # native-space labels
+                labelsn = torch.cat((labels[:, 0:1], tbox), 1)  # native-space labels
+                correct_bboxes = process_batch(predn, labelsn, iouv)
+                correct_masks = process_batch(predn, labelsn, iouv, pred_masks, gt_masks, overlap=overlap, masks=True)
+                if plots:
+                    confusion_matrix.process_batch(predn, labelsn)
+            stats.append((correct_masks, correct_bboxes, pred[:, 4], pred[:, 5], labels[:, 0]))  # (conf, pcls, tcls)
+
+            pred_masks = torch.as_tensor(pred_masks, dtype=torch.uint8)
+            if plots and batch_i < 3:
+                plot_masks.append(pred_masks[:15])  # filter top 15 to plot
+
+            # Save/log
+            if save_txt:
+                save_one_txt(predn, save_conf, shape, file=save_dir / 'labels' / f'{path.stem}.txt')
+            if save_json:
+                pred_masks = scale_image(im[si].shape[1:],
+                                         pred_masks.permute(1, 2, 0).contiguous().cpu().numpy(), shape, shapes[si][1])
+                save_one_json(predn, jdict, path, class_map, pred_masks)  # append to COCO-JSON dictionary
+            # callbacks.run('on_val_image_end', pred, predn, path, names, im[si])
+
+        # Plot images
+        if plots and batch_i < 3:
+            if len(plot_masks):
+                plot_masks = torch.cat(plot_masks, dim=0)
+            plot_images_and_masks(im, targets, masks, paths, save_dir / f'val_batch{batch_i}_labels.jpg', names)
+            plot_images_and_masks(im, output_to_target(preds, max_det=15), plot_masks, paths,
+                                  save_dir / f'val_batch{batch_i}_pred.jpg', names)  # pred
+
+        # callbacks.run('on_val_batch_end')
+
+    # Compute metrics
+    stats = [torch.cat(x, 0).cpu().numpy() for x in zip(*stats)]  # to numpy
+    if len(stats) and stats[0].any():
+        results = ap_per_class_box_and_mask(*stats, plot=plots, save_dir=save_dir, names=names)
+        metrics.update(results)
+    nt = np.bincount(stats[4].astype(int), minlength=nc)  # number of targets per class
+
+    # Print results
+    pf = '%22s' + '%11i' * 2 + '%11.3g' * 8  # print format
+    LOGGER.info(pf % ('all', seen, nt.sum(), *metrics.mean_results()))
+    if nt.sum() == 0:
+        LOGGER.warning(f'WARNING ⚠️ no labels found in {task} set, can not compute metrics without labels')
+
+    # Print results per class
+    if (verbose or (nc < 50 and not training)) and nc > 1 and len(stats):
+        for i, c in enumerate(metrics.ap_class_index):
+            LOGGER.info(pf % (names[c], seen, nt[c], *metrics.class_result(i)))
+
+    # Print speeds
+    t = tuple(x.t / seen * 1E3 for x in dt)  # speeds per image
+    if not training:
+        shape = (batch_size, 3, imgsz, imgsz)
+        LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {shape}' % t)
+
+    # Plots
+    if plots:
+        confusion_matrix.plot(save_dir=save_dir, names=list(names.values()))
+    # callbacks.run('on_val_end')
+
+    mp_bbox, mr_bbox, map50_bbox, map_bbox, mp_mask, mr_mask, map50_mask, map_mask = metrics.mean_results()
+
+    # Save JSON
+    if save_json and len(jdict):
+        w = Path(weights[0] if isinstance(weights, list) else weights).stem if weights is not None else ''  # weights
+        anno_json = str(Path('../datasets/coco/annotations/instances_val2017.json'))  # annotations
+        pred_json = str(save_dir / f'{w}_predictions.json')  # predictions
+        LOGGER.info(f'\nEvaluating pycocotools mAP... saving {pred_json}...')
+        with open(pred_json, 'w') as f:
+            json.dump(jdict, f)
+
+        try:  # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb
+            from pycocotools.coco import COCO
+            from pycocotools.cocoeval import COCOeval
+
+            anno = COCO(anno_json)  # init annotations api
+            pred = anno.loadRes(pred_json)  # init predictions api
+            results = []
+            for eval in COCOeval(anno, pred, 'bbox'), COCOeval(anno, pred, 'segm'):
+                if is_coco:
+                    eval.params.imgIds = [int(Path(x).stem) for x in dataloader.dataset.im_files]  # img ID to evaluate
+                eval.evaluate()
+                eval.accumulate()
+                eval.summarize()
+                results.extend(eval.stats[:2])  # update results (mAP@0.5:0.95, mAP@0.5)
+            map_bbox, map50_bbox, map_mask, map50_mask = results
+        except Exception as e:
+            LOGGER.info(f'pycocotools unable to run: {e}')
+
+    # Return results
+    model.float()  # for training
+    if not training:
+        s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
+        LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
+    final_metric = mp_bbox, mr_bbox, map50_bbox, map_bbox, mp_mask, mr_mask, map50_mask, map_mask
+    return (*final_metric, *(loss.cpu() / len(dataloader)).tolist()), metrics.get_maps(nc), t
+
+
+def parse_opt():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--data', type=str, default=ROOT / 'data/coco128-seg.yaml', help='dataset.yaml path')
+    parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'yolov5s-seg.pt', help='model path(s)')
+    parser.add_argument('--batch-size', type=int, default=32, help='batch size')
+    parser.add_argument('--imgsz', '--img', '--img-size', type=int, default=640, help='inference size (pixels)')
+    parser.add_argument('--conf-thres', type=float, default=0.001, help='confidence threshold')
+    parser.add_argument('--iou-thres', type=float, default=0.6, help='NMS IoU threshold')
+    parser.add_argument('--max-det', type=int, default=300, help='maximum detections per image')
+    parser.add_argument('--task', default='val', help='train, val, test, speed or study')
+    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    parser.add_argument('--workers', type=int, default=8, help='max dataloader workers (per RANK in DDP mode)')
+    parser.add_argument('--single-cls', action='store_true', help='treat as single-class dataset')
+    parser.add_argument('--augment', action='store_true', help='augmented inference')
+    parser.add_argument('--verbose', action='store_true', help='report mAP by class')
+    parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
+    parser.add_argument('--save-hybrid', action='store_true', help='save label+prediction hybrid results to *.txt')
+    parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
+    parser.add_argument('--save-json', action='store_true', help='save a COCO-JSON results file')
+    parser.add_argument('--project', default=ROOT / 'runs/val-seg', help='save results to project/name')
+    parser.add_argument('--name', default='exp', help='save to project/name')
+    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
+    parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')
+    parser.add_argument('--dnn', action='store_true', help='use OpenCV DNN for ONNX inference')
+    opt = parser.parse_args()
+    opt.data = check_yaml(opt.data)  # check YAML
+    # opt.save_json |= opt.data.endswith('coco.yaml')
+    opt.save_txt |= opt.save_hybrid
+    print_args(vars(opt))
+    return opt
+
+
+def main(opt):
+    check_requirements(ROOT / 'requirements.txt', exclude=('tensorboard', 'thop'))
+
+    if opt.task in ('train', 'val', 'test'):  # run normally
+        if opt.conf_thres > 0.001:  # https://github.com/ultralytics/yolov5/issues/1466
+            LOGGER.warning(f'WARNING ⚠️ confidence threshold {opt.conf_thres} > 0.001 produces invalid results')
+        if opt.save_hybrid:
+            LOGGER.warning('WARNING ⚠️ --save-hybrid returns high mAP from hybrid labels, not from predictions alone')
+        run(**vars(opt))
+
+    else:
+        weights = opt.weights if isinstance(opt.weights, list) else [opt.weights]
+        opt.half = torch.cuda.is_available() and opt.device != 'cpu'  # FP16 for fastest results
+        if opt.task == 'speed':  # speed benchmarks
+            # python val.py --task speed --data coco.yaml --batch 1 --weights yolov5n.pt yolov5s.pt...
+            opt.conf_thres, opt.iou_thres, opt.save_json = 0.25, 0.45, False
+            for opt.weights in weights:
+                run(**vars(opt), plots=False)
+
+        elif opt.task == 'study':  # speed vs mAP benchmarks
+            # python val.py --task study --data coco.yaml --iou 0.7 --weights yolov5n.pt yolov5s.pt...
+            for opt.weights in weights:
+                f = f'study_{Path(opt.data).stem}_{Path(opt.weights).stem}.txt'  # filename to save to
+                x, y = list(range(256, 1536 + 128, 128)), []  # x axis (image sizes), y axis
+                for opt.imgsz in x:  # img-size
+                    LOGGER.info(f'\nRunning {f} --imgsz {opt.imgsz}...')
+                    r, _, t = run(**vars(opt), plots=False)
+                    y.append(r + t)  # results and times
+                np.savetxt(f, y, fmt='%10.4g')  # save
+            subprocess.run(['zip', '-r', 'study.zip', 'study_*.txt'])
+            plot_val_study(x=x)  # plot
+        else:
+            raise NotImplementedError(f'--task {opt.task} not in ("train", "val", "test", "speed", "study")')
+
+
+if __name__ == '__main__':
+    opt = parse_opt()
+    main(opt)

track_.py

@@ -0,0 +1,402 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+"""
+Run YOLOv5 detection inference on images, videos, directories, globs, YouTube, webcam, streams, etc.
+
+Usage - sources:
+    $ python detect.py --weights yolov5s.pt --source 0                               # webcam
+                                                     img.jpg                         # image
+                                                     vid.mp4                         # video
+                                                     screen                          # screenshot
+                                                     path/                           # directory
+                                                     list.txt                        # list of images
+                                                     list.streams                    # list of streams
+                                                     'path/*.jpg'                    # glob
+                                                     'https://youtu.be/Zgi9g1ksQHc'  # YouTube
+                                                     'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream
+
+Usage - formats:
+    $ python detect.py --weights yolov5s.pt                 # PyTorch
+                                 yolov5s.torchscript        # TorchScript
+                                 yolov5s.onnx               # ONNX Runtime or OpenCV DNN with --dnn
+                                 yolov5s_openvino_model     # OpenVINO
+                                 yolov5s.engine             # TensorRT
+                                 yolov5s.mlmodel            # CoreML (macOS-only)
+                                 yolov5s_saved_model        # TensorFlow SavedModel
+                                 yolov5s.pb                 # TensorFlow GraphDef
+                                 yolov5s.tflite             # TensorFlow Lite
+                                 yolov5s_edgetpu.tflite     # TensorFlow Edge TPU
+                                 yolov5s_paddle_model       # PaddlePaddle
+"""
+
+import argparse
+import csv
+import os
+import platform
+import sys
+from pathlib import Path
+import glob
+import numpy as np
+import pickle
+import torch
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[0]  # YOLOv5 root directory
+if str(ROOT) not in sys.path:
+    sys.path.append(str(ROOT))  # add ROOT to PATH
+ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative
+
+from models.common import DetectMultiBackend
+from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadScreenshots, LoadStreams
+from utils.general import (LOGGER, Profile, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2,
+                           increment_path, non_max_suppression, print_args, scale_boxes, strip_optimizer, xyxy2xywh)
+from utils.torch_utils import select_device, smart_inference_mode
+
+'''集成跟踪模块，输出跟踪结果文件 .npy'''
+# from ultralytics.engine.results import Boxes    # Results
+# from ultralytics.utils import IterableSimpleNamespace, yaml_load
+from tracking.utils.plotting import Annotator, colors
+from tracking.utils import Boxes, IterableSimpleNamespace, yaml_load, boxes_add_fid
+from tracking.trackers import BOTSORT, BYTETracker
+from tracking.utils.showtrack import drawtracks
+
+
+def init_trackers(tracker_yaml = None, bs=1):
+    """
+    Initialize trackers for object tracking during prediction.
+    """   
+    # 需要将配置文件中的cmc_method改为gmc_method
+    # tracker_yaml = r"D:\DeepLearning\ultralytics\ultralytics\tracker\cfg\botsort.yaml"   
+    
+    tracker_yaml = r"./tracking/trackers/cfg/botsort.yaml"
+    
+    TRACKER_MAP = {'bytetrack': BYTETracker, 'botsort': BOTSORT}
+    
+    cfg = IterableSimpleNamespace(**yaml_load(tracker_yaml))
+    trackers = []
+    for _ in range(bs):
+        tracker = TRACKER_MAP[cfg.tracker_type](args=cfg, frame_rate=30)
+        trackers.append(tracker)
+    
+    return trackers
+
+
+@smart_inference_mode()
+def run(
+        weights=ROOT / 'yolov5s.pt',  # model path or triton URL
+        source=ROOT / 'data/images',  # file/dir/URL/glob/screen/0(webcam)
+        data=ROOT / 'data/coco128.yaml',  # dataset.yaml path
+        imgsz=(640, 640),  # inference size (height, width)
+        conf_thres=0.25,  # confidence threshold
+        iou_thres=0.45,  # NMS IOU threshold
+        max_det=1000,  # maximum detections per image
+        device='',  # cuda device, i.e. 0 or 0,1,2,3 or cpu
+        view_img=False,  # show results
+        save_txt=False,  # save results to *.txt
+        save_csv=False,  # save results in CSV format
+        save_conf=False,  # save confidences in --save-txt labels
+        save_crop=False,  # save cropped prediction boxes
+        nosave=False,  # do not save images/videos
+        classes=None,  # filter by class: --class 0, or --class 0 2 3
+        agnostic_nms=False,  # class-agnostic NMS
+        augment=False,  # augmented inference
+        visualize=False,  # visualize features
+        update=False,  # update all models
+        project=ROOT / 'runs/detect',  # save results to project/name
+        name='exp',  # save results to project/name
+        exist_ok=False,  # existing project/name ok, do not increment
+        line_thickness=3,  # bounding box thickness (pixels)
+        hide_labels=False,  # hide labels
+        hide_conf=False,  # hide confidencesL
+        half=False,  # use FP16 half-precision inference
+        dnn=False,  # use OpenCV DNN for ONNX inference
+        vid_stride=1,  # video frame-rate stride
+):
+    source = str(source)
+    save_img = not nosave and not source.endswith('.txt')  # save inference images
+    is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
+    is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
+    webcam = source.isnumeric() or source.endswith('.streams') or (is_url and not is_file)
+    screenshot = source.lower().startswith('screen')
+    if is_url and is_file:
+        source = check_file(source)  # download
+    
+    save_dir = Path(project) / Path(source).stem
+    if save_dir.exists():
+        print(Path(source).stem)
+        # return
+        
+        save_dir = increment_path(Path(project) / name, exist_ok=exist_ok)  # increment run
+        (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir
+    else:
+        save_dir.mkdir(parents=True, exist_ok=True) 
+        
+    # Load model
+    device = select_device(device)
+    model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
+    stride, names, pt = model.stride, model.names, model.pt
+    imgsz = check_img_size(imgsz, s=stride)  # check image size
+     
+    # Dataloader
+    bs = 1  # batch_size
+    
+    dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride)    
+    vid_path, vid_writer = [None] * bs, [None] * bs
+   
+    
+    # Run inference
+    model.warmup(imgsz=(1 if pt or model.triton else bs, 3, *imgsz))  # warmup
+    seen, windows, dt = 0, [], (Profile(), Profile(), Profile())
+
+    
+    ## ================================================================================== writed by WQG
+    tracker = init_trackers(bs)[0]
+    vid_path_track, vid_writer_track = [None] * bs, [None] * bs
+    tboxes = []
+    vboxes = []
+    
+    f_i = 1
+    for path, im, im0s, vid_cap, s in dataset:
+        if f_i == 1: 
+            f_i == 0
+            imgshow = im0s.copy()
+        
+        ## ============================= tracking 功能只处理视频，writed by WQG
+        if dataset.mode == 'image':
+            continue
+
+        with dt[0]:
+            im = torch.from_numpy(im).to(model.device)
+            im = im.half() if model.fp16 else im.float()  # uint8 to fp16/32
+            im /= 255  # 0 - 255 to 0.0 - 1.0
+            if len(im.shape) == 3:
+                im = im[None]  # expand for batch dim
+
+        # Inference
+        with dt[1]:
+            visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
+            pred = model(im, augment=augment, visualize=visualize)
+
+        # NMS
+        with dt[2]:
+            pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
+
+        # Second-stage classifier (optional)
+        # pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)
+
+        # Define the path for the CSV file
+        csv_path = save_dir / 'predictions.csv'
+
+        # Create or append to the CSV file
+        def write_to_csv(image_name, prediction, confidence):
+            data = {'Image Name': image_name, 'Prediction': prediction, 'Confidence': confidence}
+            with open(csv_path, mode='a', newline='') as f:
+                writer = csv.DictWriter(f, fieldnames=data.keys())
+                if not csv_path.is_file():
+                    writer.writeheader()
+                writer.writerow(data)
+
+        # Process predictions
+        for i, det in enumerate(pred):  # per image
+            seen += 1
+            if webcam:  # batch_size >= 1
+                p, im0, frame = path[i], im0s[i].copy(), dataset.count
+                s += f'{i}: '
+            else:
+                p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0)
+
+            p = Path(p)  # to Path
+            save_path = str(save_dir / p.name)  # im.jpg
+
+            s += '%gx%g ' % im.shape[2:]  # print string
+            
+            annotator = Annotator(im0, line_width=line_thickness, example=str(names))
+            if len(det): 
+                # Rescale boxes from img_size to im0 size
+                det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], im0.shape).round()
+                
+                vboxes.append((det.cpu().numpy(), im0, frame)) 
+                ## ================================================================ writed by WQG
+                det_tracking = Boxes(det, im0.shape).cpu().numpy()
+                tracks = tracker.update(det_tracking, im0)
+                
+                if len(tracks) > 0:
+                    det = torch.as_tensor(tracks[:, :-2])
+                    tboxes.append((det, frame))
+                else:
+                    idmark = -1 * np.ones([det.shape[0], 1])
+                    det = np.concatenate([det[:,:4], idmark, det[:, 4:]], axis=1)
+
+                for *xyxy, id, conf, cls in reversed(det):
+                    name = ('' if id==-1 else f'id:{int(id)} ') + names[int(cls)]                   
+                    label = None if hide_labels else (name if hide_conf else f'{name} {conf:.2f}')
+                    
+                    if id >=0 and cls==0:
+                        color = colors(int(cls), True)
+                    elif id >=0 and cls!=0:
+                        color = colors(int(id), True)
+                    else:
+                        color = colors(19, True)     # 19为调色板的最后一个元素
+           
+                    annotator.box_label(xyxy, label, color=color)
+
+            # Save results (image and video with tracking)
+            im0 = annotator.result()
+            if save_img:
+                save_path_img, ext = os.path.splitext(save_path)
+                imgpath = save_path_img + f"_{dataset.frame}.png"
+                cv2.imwrite(Path(imgpath), im0)
+                
+                if vid_path[i] != save_path:  # new video
+                    vid_path[i] = save_path
+                    if isinstance(vid_writer[i], cv2.VideoWriter):
+                        vid_writer[i].release()  # release previous video writer
+                    if vid_cap:  # video
+                        fps = vid_cap.get(cv2.CAP_PROP_FPS)
+                        w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+                        h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+                    else:  # stream
+                        fps, w, h = 30, im0.shape[1], im0.shape[0]
+                    save_path = str(Path(save_path).with_suffix('.mp4'))  # force *.mp4 suffix on results videos
+                    vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
+                vid_writer[i].write(im0)
+
+        # Print time (inference-only)
+        LOGGER.info(f"{s}{'' if len(det) else '(no detections), '}{dt[1].dt * 1E3:.1f}ms")
+
+    
+    ## ======================================================================== written by WQG
+    ## tboxes: list, [(det, frame_index)]
+    ## bboxes: Array, [x, y, w, h, track_id, score, cls, frame_index]
+
+    filename = os.path.split(save_path_img)[-1]
+    file, ext = os.path.splitext(filename)
+
+    bboxes = boxes_add_fid(tboxes)  
+    
+    imgshow = drawtracks(bboxes, file=filename)    
+    
+    showpath_1 = save_path_img + "_show.png"
+    cv2.imwrite(Path(showpath_1), imgshow)
+
+    ##================================================== save .npy
+    with open(f'./tracking/vboxes/{file}.pkl', 'wb') as file:
+        pickle.dump(vboxes, file)
+    
+    
+    boxes_dir = Path('./runs/boxes/')
+    if not boxes_dir.exists():
+        boxes_dir.mkdir(parents=True, exist_ok=True)
+    bboxes_path = boxes_dir.joinpath(filename + ".npy") 
+    np.save(bboxes_path, bboxes)
+ 
+
+    # Print results
+    t = tuple(x.t / seen * 1E3 for x in dt)  # speeds per image
+    LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t)
+    if save_txt or save_img:
+        s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
+        LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
+    if update:
+        strip_optimizer(weights[0])  # update model (to fix SourceChangeWarning)
+
+
+def parse_opt():
+    modelpath = ROOT / 'ckpts/best_158734_cls11_noaug10.pt'       # 'ckpts/best_15000_0908.pt',  'ckpts/yolov5s.pt', 'ckpts/best_20000_cls30.pt'
+    
+    # datapath = r"D:/datasets/ym/videos/标记视频/"   # ROOT/'data/videos',  ROOT/'data/images'   images    
+    datapath = r"D:\datasets\ym\highvalue\videos"
+    
+    # datapath = r"D:/dcheng/videos/"
+    # modelpath = ROOT / 'ckpts/yolov5s.pt' 
+    
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--weights', nargs='+', type=str, default=modelpath, help='model path or triton URL')   # 'yolov5s.pt', best_15000_0908.pt
+    parser.add_argument('--source', type=str, default=datapath, help='file/dir/URL/glob/screen/0(webcam)')    # images, videos
+    parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='(optional) dataset.yaml path')
+    parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')
+    parser.add_argument('--conf-thres', type=float, default=0.25, help='confidence threshold')
+    parser.add_argument('--iou-thres', type=float, default=0.45, help='NMS IoU threshold')
+    parser.add_argument('--max-det', type=int, default=1000, help='maximum detections per image')
+    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    parser.add_argument('--view-img', action='store_true', help='show results')
+    parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
+    parser.add_argument('--save-csv', action='store_true', help='save results in CSV format')
+    parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
+    parser.add_argument('--save-crop', action='store_true', help='save cropped prediction boxes')
+    parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
+    parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --classes 0, or --classes 0 2 3')
+    parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
+    parser.add_argument('--augment', action='store_true', help='augmented inference')
+    parser.add_argument('--visualize', action='store_true', help='visualize features')
+    parser.add_argument('--update', action='store_true', help='update all models')
+    parser.add_argument('--project', default=ROOT / 'runs/detect', help='save results to project/name')
+    parser.add_argument('--name', default='exp', help='save results to project/name')
+    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
+    parser.add_argument('--line-thickness', default=3, type=int, help='bounding box thickness (pixels)')
+    parser.add_argument('--hide-labels', default=False, action='store_true', help='hide labels')
+    parser.add_argument('--hide-conf', default=False, action='store_true', help='hide confidences')
+    parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')
+    parser.add_argument('--dnn', action='store_true', help='use OpenCV DNN for ONNX inference')
+    parser.add_argument('--vid-stride', type=int, default=1, help='video frame-rate stride')
+    opt = parser.parse_args()
+    opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1  # expand
+    print_args(vars(opt))
+    return opt
+
+def main_loop_folders(opt):
+    path1 = r"D:\datasets\ym\videos\标记视频" 
+    path2 = r"D:\datasets\ym\永辉双摄视频\退购_前摄\videos"
+    path3 = r"D:\datasets\ym\永辉双摄视频\退购_后摄\videos"
+    path4 = r"D:\datasets\ym\永辉双摄视频\加购_前摄\videos"
+    path5 = r"D:\datasets\ym\永辉双摄视频\加购_后摄\videos"
+    paths = [path1]   # [path1, path2, path3, path4, path5]
+    
+    check_requirements(ROOT / 'requirements.txt', exclude=('tensorboard', 'thop'))
+    optdict = vars(opt)
+    k = 0
+    for p in paths:
+        files = []
+        if os.path.isdir(p):
+            files.extend(sorted(glob.glob(os.path.join(p, '*.*'))))
+            for file in files:
+                # file = r"D:\datasets\ym\videos\标记视频\加购_100.mp4"
+                
+                optdict["source"] = file
+                run(**optdict)
+                
+                # k += 1
+                # if k == 100:
+                #     break
+        elif os.path.isfile(p):
+            run(**optdict)
+        
+
+
+
+def main(opt):
+    check_requirements(ROOT / 'requirements.txt', exclude=('tensorboard', 'thop'))
+    # files.extend(sorted(glob.glob(os.path.join(p, '*.*'))))
+
+    optdict = vars(opt)
+    p = optdict["source"]
+    
+    files = []
+    k = 0
+    if os.path.isdir(p):
+        files.extend(sorted(glob.glob(os.path.join(p, '*.*'))))
+        
+        for file in files:
+            optdict["source"] = file
+            run(**optdict)
+            
+            k += 1
+            if k == 100:
+                break
+            
+    elif os.path.isfile(p):
+        run(**vars(opt))
+
+
+if __name__ == '__main__':
+    opt = parse_opt()
+    main_loop_folders(opt)

track_reid.py

@@ -0,0 +1,556 @@
+# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
+"""
+Run YOLOv5 detection inference on images, videos, directories, globs, YouTube, webcam, streams, etc.
+
+Usage - sources:
+    $ python detect.py --weights yolov5s.pt --source 0                               # webcam
+                                                     img.jpg                         # image
+                                                     vid.mp4                         # video
+                                                     screen                          # screenshot
+                                                     path/                           # directory
+                                                     list.txt                        # list of images
+                                                     list.streams                    # list of streams
+                                                     'path/*.jpg'                    # glob
+                                                     'https://youtu.be/Zgi9g1ksQHc'  # YouTube
+                                                     'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream
+
+Usage - formats:
+    $ python detect.py --weights yolov5s.pt                 # PyTorch
+                                 yolov5s.torchscript        # TorchScript
+                                 yolov5s.onnx               # ONNX Runtime or OpenCV DNN with --dnn
+                                 yolov5s_openvino_model     # OpenVINO
+                                 yolov5s.engine             # TensorRT
+                                 yolov5s.mlmodel            # CoreML (macOS-only)
+                                 yolov5s_saved_model        # TensorFlow SavedModel
+                                 yolov5s.pb                 # TensorFlow GraphDef
+                                 yolov5s.tflite             # TensorFlow Lite
+                                 yolov5s_edgetpu.tflite     # TensorFlow Edge TPU
+                                 yolov5s_paddle_model       # PaddlePaddle
+"""
+
+import argparse
+import csv
+import os
+import platform
+import sys
+from pathlib import Path
+import glob
+import numpy as np
+import pickle
+import torch
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[0]  # YOLOv5 root directory
+if str(ROOT) not in sys.path:
+    sys.path.append(str(ROOT))  # add ROOT to PATH
+ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative
+
+from models.common import DetectMultiBackend
+from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadScreenshots, LoadStreams
+from utils.general import (LOGGER, Profile, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2,
+                           increment_path, non_max_suppression, print_args, scale_boxes, strip_optimizer, xyxy2xywh)
+from utils.torch_utils import select_device, smart_inference_mode
+
+'''集成跟踪模块，输出跟踪结果文件 .npy'''
+# from ultralytics.engine.results import Boxes    # Results
+# from ultralytics.utils import IterableSimpleNamespace, yaml_load
+from tracking.utils.plotting import Annotator, colors
+from tracking.utils import Boxes, IterableSimpleNamespace, yaml_load, boxes_add_fid
+from tracking.trackers import BOTSORT, BYTETracker
+from tracking.utils.showtrack import drawtracks
+from hands.hand_inference import hand_pose
+
+from tracking.trackers.reid.reid_interface import ReIDInterface 
+from tracking.trackers.reid.config import config as ReIDConfig
+ReIDEncoder = ReIDInterface(ReIDConfig)
+
+# tracker_yaml = r"./tracking/trackers/cfg/botsort.yaml"
+
+def inference_image(image, detections):
+    H, W, _ = np.shape(image)
+    imgs = []
+    batch_patches = []
+    patches = []
+    for d in range(np.size(detections, 0)):
+        tlbr = detections[d, :4].astype(np.int_)
+        tlbr[0] = max(0, tlbr[0])
+        tlbr[1] = max(0, tlbr[1])
+        tlbr[2] = min(W - 1, tlbr[2])
+        tlbr[3] = min(H - 1, tlbr[3])
+        img1 = image[tlbr[1]:tlbr[3], tlbr[0]:tlbr[2], :]
+
+        img = img1[:, :, ::-1].copy()    # the model expects RGB inputs
+        patch = ReIDEncoder.transform(img)
+        
+        imgs.append(img1)
+        # patch = patch.to(device=self.device).half()
+        if str(ReIDEncoder.device) != "cpu":
+            patch = patch.to(device=ReIDEncoder.device).half()
+        else:
+            patch = patch.to(device=ReIDEncoder.device)
+        
+        patches.append(patch)
+        if (d + 1) % ReIDEncoder.batch_size == 0:
+            patches = torch.stack(patches, dim=0)
+            batch_patches.append(patches)
+            patches = []
+
+    if len(patches):
+        patches = torch.stack(patches, dim=0)
+        batch_patches.append(patches)
+
+    features = np.zeros((0, ReIDEncoder.embedding_size))
+    for patches in batch_patches:
+        pred = ReIDEncoder.model(patches)
+        pred[torch.isinf(pred)] = 1.0
+        feat = pred.cpu().data.numpy()
+        features = np.vstack((features, feat))
+
+    return imgs, features
+
+
+
+
+
+def init_trackers(tracker_yaml = None, bs=1):
+    """
+    Initialize trackers for object tracking during prediction.
+    """      
+    # tracker_yaml = r"./tracking/trackers/cfg/botsort.yaml"
+    
+    TRACKER_MAP = {'bytetrack': BYTETracker, 'botsort': BOTSORT}
+    
+    cfg = IterableSimpleNamespace(**yaml_load(tracker_yaml))
+    trackers = []
+    for _ in range(bs):
+        tracker = TRACKER_MAP[cfg.tracker_type](args=cfg, frame_rate=30)
+        trackers.append(tracker)
+    
+    return trackers
+
+
+@smart_inference_mode()
+def run(
+        weights=ROOT / 'yolov5s.pt',  # model path or triton URL
+        source=ROOT / 'data/images',  # file/dir/URL/glob/screen/0(webcam)
+        
+        project=ROOT / 'runs/detect',  # save results to project/name
+        name='exp',  # save results to project/name
+        
+        tracker_yaml = "./tracking/trackers/cfg/botsort.yaml",
+        imgsz=(640, 640),  # inference size (height, width)
+        conf_thres=0.25,  # confidence threshold
+        iou_thres=0.45,  # NMS IOU threshold
+        max_det=1000,  # maximum detections per image
+        device='',  # cuda device, i.e. 0 or 0,1,2,3 or cpu
+        view_img=False,  # show results
+        save_txt=False,  # save results to *.txt
+        save_csv=False,  # save results in CSV format
+        save_conf=False,  # save confidences in --save-txt labels
+        save_crop=False,  # save cropped prediction boxes
+        nosave=False,  # do not save images/videos
+        classes=None,  # filter by class: --class 0, or --class 0 2 3
+        agnostic_nms=False,  # class-agnostic NMS
+        augment=False,  # augmented inference
+        visualize=False,  # visualize features
+        update=False,  # update all models
+        exist_ok=False,  # existing project/name ok, do not increment
+        line_thickness=3,  # bounding box thickness (pixels)
+        hide_labels=False,  # hide labels
+        hide_conf=False,  # hide confidencesL
+        half=False,  # use FP16 half-precision inference
+        dnn=False,  # use OpenCV DNN for ONNX inference
+        vid_stride=1,  # video frame-rate stride
+        data=ROOT / 'data/coco128.yaml',  # dataset.yaml path
+):
+    source = str(source)
+    # filename = os.path.split(source)[-1]
+    
+    save_img = not nosave and not source.endswith('.txt')  # save inference images
+    is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
+    is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
+    webcam = source.isnumeric() or source.endswith('.streams') or (is_url and not is_file)
+    screenshot = source.lower().startswith('screen')
+    if is_url and is_file:
+        source = check_file(source)  # download
+    
+    save_dir = Path(project) / Path(source).stem
+    if save_dir.exists():
+        print(Path(source).stem)
+        # return
+        
+        save_dir = increment_path(Path(project) / name, exist_ok=exist_ok)  # increment run
+        (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir
+    else:
+        save_dir.mkdir(parents=True, exist_ok=True) 
+        
+    # Load model
+    device = select_device(device)
+    model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
+    stride, names, pt = model.stride, model.names, model.pt
+    imgsz = check_img_size(imgsz, s=stride)  # check image size
+     
+    # Dataloader
+    bs = 1  # batch_size
+    
+    dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride)    
+    vid_path, vid_writer = [None] * bs, [None] * bs
+   
+    
+    # Run inference
+    model.warmup(imgsz=(1 if pt or model.triton else bs, 3, *imgsz))  # warmup
+    seen, dt = 0, (Profile(), Profile(), Profile())
+    
+    tracker = init_trackers(tracker_yaml, bs)[0]
+    
+    handpose = hand_pose()
+    handlocals_dict = {}
+    
+    boxes_and_imgs = []
+    track_boxes = np.empty((0, 9), dtype = np.float32)
+    det_boxes = np.empty((0, 9), dtype = np.float32)
+    
+    
+    features_dict = {}
+    TracksDict = {}
+    for path, im, im0s, vid_cap, s in dataset:
+        if save_img and 'imgshow' not in locals().keys():
+            imgshow = im0s.copy() 
+        
+        ## ============================= tracking 功能只处理视频，writed by WQG
+        if dataset.mode == 'image':
+            continue
+
+        with dt[0]:
+            im = torch.from_numpy(im).to(model.device)
+            im = im.half() if model.fp16 else im.float()  # uint8 to fp16/32
+            im /= 255  # 0 - 255 to 0.0 - 1.0
+            if len(im.shape) == 3:
+                im = im[None]  # expand for batch dim
+
+        # Inference
+        with dt[1]:
+            visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
+            pred = model(im, augment=augment, visualize=visualize)
+
+        # NMS
+        with dt[2]:
+            pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
+
+        # Process predictions
+        for i, det in enumerate(pred):  # per image
+            seen += 1
+            if webcam:  # batch_size >= 1
+                p, im0, frame = path[i], im0s[i].copy(), dataset.count
+                s += f'{i}: '
+            else:
+                p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0)
+            
+            
+            
+            p = Path(p)  # to Path
+            save_path = str(save_dir / p.name)  # im.jpg
+            s += '%gx%g ' % im.shape[2:]  # print string
+            
+            # im0_ant = im0.copy()
+            annotator = Annotator(im0.copy(), line_width=line_thickness, example=str(names))
+            
+            nd = len(det)
+            if nd: 
+                # Rescale boxes from img_size to im0 size
+                det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], im0.shape).round()
+                
+                det = det.cpu().numpy()
+                det = np.concatenate([det[:, :4], np.arange(nd).reshape(-1, 1), det[:, 4:]], axis=-1) 
+                
+                '''FeatFlag为相对于上一帧boxes，当前boxes是否为静止的标志。'''
+                # def static_estimate(box1, box2, TH1=8, TH2=12):
+                #     dij_abs = max(np.abs(box1 - box2))
+                #     dij_euc = max([np.linalg.norm((box1[:2] - box2[:2])), 
+                #                    np.linalg.norm((box1[2:4] - box2[2:4]))
+                #                    ])
+                #     if dij_abs < TH1 and dij_euc < TH2:
+                #         return True
+                #     else:
+                #         return False
+                # FeatFlag = [-1] * nd  
+                # if len(boxes_and_imgs):
+                #     detj = boxes_and_imgs[-1][0]
+                #     frmj = boxes_and_imgs[-1][-1]  
+                #     for ii in range(nd):
+                #         ## flag 中保存的是box索引
+                #         condt1 = frame-frmj==1
+                #         flag = [idx for jj, idx in enumerate(detj[:, 4]) if condt1 and static_estimate(det[ii, :4], detj[jj, :4])]
+                #         if len(flag) == 1:
+                #             FeatFlag[ii] = flag[0]
+                # boxes_and_imgs.append((det, im0, frame)) 
+
+                ## ================================================================ writed by WQG
+                
+                '''tracks: [x1, y1, x2, y2, track_id, score, cls, frame_index, box_index]
+                            0   1   2   3      4        5     6       7           8
+                          这里，frame_index 也可以用视频的 帧ID 代替, box_index 保持不变
+                '''
+
+                det_tracking = Boxes(det, im0.shape).cpu().numpy()
+                tracks = tracker.update(det_tracking, im0)
+                if len(tracks) == 0:
+                    continue
+                tracks[:, 7] = dataset.frame
+                
+                '''================== 1. 存储 dets/subimgs/features Dict ============='''
+                imgs, features = inference_image(im0, tracks)
+                
+                imgdict = {}
+                boxdict = {}
+                featdict = {}
+                for ii, bid in enumerate(tracks[:, 8]):
+                    imgdict.update({int(bid): imgs[ii]})                    # [f"img_{int(bid)}"] = imgs[i]
+                    boxdict.update({int(bid): tracks[ii, :]})               # [f"box_{int(bid)}"] = tracks[i, :]
+                    featdict.update({int(bid): features[ii, :]})            # [f"feat_{int(bid)}"] = features[i, :]
+                TracksDict[f"frame_{int(dataset.frame)}"] = {"imgs":imgdict, "boxes":boxdict, "feats":featdict}
+                
+                track_boxes = np.concatenate([track_boxes, tracks], axis=0)
+                    
+            
+                '''================== 2. 提取手势位置 ==================='''
+                # idx_0 = tracks[:, 6].astype(np.int_) == 0
+                # hn = 0
+                # for j, index in enumerate(idx_0):
+                #     if index:        
+                #         track = tracks[j, :]
+                #         hand_local, imgshow = handpose.get_hand_local(track, im0)
+                #         handlocals_dict.update({int(track[7]): {int(track[8]): hand_local}})
+                        
+                #         # '''yoloV5和手势检测的召回率并不一直，用hand_local代替tracks中手部的(x1, y1, x2, y2)，会使得两种坐标方式混淆'''
+                #         # if hand_local: tracks[j, :4] = hand_local
+                        
+                #         hn += 1 
+                #         cv2.imwrite(f"D:\DeepLearning\yolov5\hands\images\{Path(source).stem}_{int(track[7])}_{hn}.png", imgshow)
+
+                for *xyxy, id, conf, cls, fid, bid in reversed(tracks):
+                    name = ('' if id==-1 else f'id:{int(id)} ') + names[int(cls)]                   
+                    label = None if hide_labels else (name if hide_conf else f'{name} {conf:.2f}')
+                    
+                    if id >=0 and cls==0:
+                        color = colors(int(cls), True)
+                    elif id >=0 and cls!=0:
+                        color = colors(int(id), True)
+                    else:
+                        color = colors(19, True)     # 19为调色板的最后一个元素
+           
+                    annotator.box_label(xyxy, label, color=color)
+
+            # Save results (image and video with tracking)
+            im0 = annotator.result()
+            save_path_img, ext = os.path.splitext(save_path)
+            if save_img:
+                if dataset.mode == 'image':
+                    imgpath = save_path_img + f"_{dataset}.png"
+                else:
+                    imgpath = save_path_img + f"_{dataset.frame}.png"
+                    
+                cv2.imwrite(Path(imgpath), im0)
+                
+                if vid_path[i] != save_path:  # new video
+                    vid_path[i] = save_path
+                    if isinstance(vid_writer[i], cv2.VideoWriter):
+                        vid_writer[i].release()  # release previous video writer
+                    if vid_cap:  # video
+                        fps = vid_cap.get(cv2.CAP_PROP_FPS)
+                        w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+                        h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+                    else:  # stream
+                        fps, w, h = 30, im0.shape[1], im0.shape[0]
+                    save_path = str(Path(save_path).with_suffix('.mp4'))  # force *.mp4 suffix on results videos
+                    vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
+                vid_writer[i].write(im0)
+
+        # Print time (inference-only)
+        LOGGER.info(f"{s}{'' if len(det) else '(no detections), '}{dt[1].dt * 1E3:.1f}ms")
+
+    
+    ## ======================================================================== written by WQG
+    ## track_boxes: Array, [x1, y1, x2, y2, track_id, score, cls, frame_index, box_id]
+    TracksDict.update({"TrackBoxes": track_boxes})
+    
+    
+    '''上面保存了检测结果是视频和图像，以下还保存五种类型的数据'''
+    filename = os.path.split(save_path_img)[-1]
+ 
+    '''======================== 1. save in './run/detect/' ===================='''
+    if source.find("front") >= 0:
+        carttemp = cv2.imread("./tracking/shopcart/cart_tempt/board_ftmp_line.png")
+    else:
+        carttemp = cv2.imread("./tracking/shopcart/cart_tempt/edgeline.png")
+    imgshow = drawtracks(track_boxes, carttemp)    
+    showpath_1 = save_path_img + "_show.png"
+    cv2.imwrite(Path(showpath_1), imgshow)
+
+    '''======================== 2. save dets/subimgs/features Dict =================='''
+    trackdicts_dir = Path('./tracking/data/trackdicts/')
+    if not trackdicts_dir.exists():
+        trackdicts_dir.mkdir(parents=True, exist_ok=True)
+    trackdicts_dir = trackdicts_dir.joinpath(f'{filename}.pkl')
+    with open(trackdicts_dir, 'wb') as file:
+        pickle.dump(TracksDict, file)
+
+        
+    '''======================== 3. save hand_local data =================='''
+    # handlocal_dir = Path('./tracking/data/handlocal/')
+    # if not handlocal_dir.exists():
+    #     handlocal_dir.mkdir(parents=True, exist_ok=True)
+    # handlocal_path = handlocal_dir.joinpath(f'{filename}.pkl')
+    # with open(handlocal_path, 'wb') as file:
+    #     pickle.dump(handlocals_dict, file)
+        
+
+    # Print results
+    t = tuple(x.t / seen * 1E3 for x in dt)  # speeds per image
+    LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t)
+    if save_txt or save_img:
+        s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
+        LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
+    if update:
+        strip_optimizer(weights[0])  # update model (to fix SourceChangeWarning)
+
+
+def parse_opt():
+    modelpath = ROOT / 'ckpts/best_yolov5m_250000.pt'       # 'ckpts/best_15000_0908.pt',  'ckpts/yolov5s.pt', 'ckpts/best_20000_cls30.pt'
+    
+    '''datapath为视频文件目录或视频文件'''
+    datapath = r"D:/datasets/ym/videos/标记视频/"   # ROOT/'data/videos',  ROOT/'data/images'   images    
+    # datapath = r"D:\datasets\ym\highvalue\videos"
+    # datapath = r"D:/dcheng/videos/"
+    # modelpath = ROOT / 'ckpts/yolov5s.pt' 
+    
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--weights', nargs='+', type=str, default=modelpath, help='model path or triton URL')   # 'yolov5s.pt', best_15000_0908.pt
+    parser.add_argument('--source', type=str, default=datapath, help='file/dir/URL/glob/screen/0(webcam)')    # images, videos
+    parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='(optional) dataset.yaml path')
+    parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')
+    parser.add_argument('--conf-thres', type=float, default=0.25, help='confidence threshold')
+    parser.add_argument('--iou-thres', type=float, default=0.45, help='NMS IoU threshold')
+    parser.add_argument('--max-det', type=int, default=1000, help='maximum detections per image')
+    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    parser.add_argument('--view-img', action='store_true', help='show results')
+    parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
+    parser.add_argument('--save-csv', action='store_true', help='save results in CSV format')
+    parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
+    parser.add_argument('--save-crop', action='store_true', help='save cropped prediction boxes')
+    parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
+    parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --classes 0, or --classes 0 2 3')
+    parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
+    parser.add_argument('--augment', action='store_true', help='augmented inference')
+    parser.add_argument('--visualize', action='store_true', help='visualize features')
+    parser.add_argument('--update', action='store_true', help='update all models')
+    parser.add_argument('--project', default=ROOT / 'runs/detect', help='save results to project/name')
+    parser.add_argument('--name', default='exp', help='save results to project/name')
+    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
+    parser.add_argument('--line-thickness', default=3, type=int, help='bounding box thickness (pixels)')
+    parser.add_argument('--hide-labels', default=False, action='store_true', help='hide labels')
+    parser.add_argument('--hide-conf', default=False, action='store_true', help='hide confidences')
+    parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')
+    parser.add_argument('--dnn', action='store_true', help='use OpenCV DNN for ONNX inference')
+    parser.add_argument('--vid-stride', type=int, default=1, help='video frame-rate stride')
+    opt = parser.parse_args()
+    opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1  # expand
+    print_args(vars(opt))
+    return opt
+        
+def find_files_in_nested_dirs(root_dir):
+    all_files = []
+    extensions = ['.mp4']
+    for dirpath, dirnames, filenames in os.walk(root_dir):
+        for filename in filenames:
+            file, ext = os.path.splitext(filename)
+            if ext in extensions:
+                all_files.append(os.path.join(dirpath, filename))
+    return all_files
+            
+print('=======')
+
+def main(opt):
+    check_requirements(ROOT / 'requirements.txt', exclude=('tensorboard', 'thop'))
+       
+    p = r"D:\datasets\ym\永辉测试数据_202404\20240402"
+    
+    optdict = vars(opt)
+    files = []
+    k = 0
+    if os.path.isdir(p):
+        files.extend(sorted(glob.glob(os.path.join(p, '*.*'))))   
+        for file in files:
+            optdict["source"] = file
+            run(**optdict)
+            
+            k += 1
+            if k == 2:
+                break         
+    elif os.path.isfile(p):
+        run(**vars(opt))
+        
+def main_loop(opt):
+    check_requirements(ROOT / 'requirements.txt', exclude=('tensorboard', 'thop'))
+    
+    optdict = vars(opt)   
+    
+    # p = r"D:\datasets\ym\永辉测试数据_比对" 
+    # p = r"D:\datasets\ym\广告板遮挡测试\8"
+    p = r"D:\datasets\ym\videos\标记视频"
+    # p = r"D:\datasets\ym\实验室测试"
+    
+    k = 0
+    if os.path.isdir(p):
+        files = find_files_in_nested_dirs(p)
+        
+        # files = [#r"D:\datasets\ym\videos\标记视频\test_20240402-173935_6920152400975_back_174037372.mp4",
+                  # r"D:\datasets\ym\videos\标记视频\test_20240402-173935_6920152400975_front_174037379.mp4"]
+        
+        # files = [r"D:\datasets\ym\广告板遮挡测试\8\2500441577966_20240508-175946_front_addGood_70f75407b7ae_155_17788571404.mp4"]
+        for file in files:
+            optdict["source"] = file
+            run(**optdict)
+            
+            k += 1
+            if k == 3:
+                break
+    elif os.path.isfile(p):
+        optdict["source"] = p
+        run(**vars(opt))
+
+
+
+
+if __name__ == '__main__':
+    opt = parse_opt()
+    
+    # main(opt)
+    main_loop(opt)
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    

tracking/dotrack/dotracks.py

@@ -0,0 +1,466 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Mon Mar  4 18:16:01 2024
+
+@author: ym
+"""
+import numpy as np
+import cv2
+from pathlib import Path
+from scipy.spatial.distance import cdist
+from utils.mergetrack import track_equal_track
+curpath = Path(__file__).resolve().parents[0]
+
+curpath = Path(curpath)
+
+class MoveState:
+    """商品运动状态标志"""
+    Static = 0
+    DownWard = 1
+    UpWard = 2
+    FreeMove = 3
+    Unknown = -1
+    
+class  ShoppingCart:
+    
+    def __init__(self, bboxes):
+        self.bboxes = bboxes
+        self.loadrate = self.load_rate()
+
+    def load_rate(self):
+        bboxes = self.bboxes
+
+        fid = min(bboxes[:, 7])
+        idx = bboxes[:, 7] == fid
+        boxes = bboxes[idx]
+        
+        temp = np.zeros(self.incart.shape, np.uint8)
+        for i in range(boxes.shape[0]):
+            x1, y1, x2, y2, tid = boxes[i, 0:5]
+            cv2.rectangle(temp, (int(x1), int(y1)), (int(x2), int(y2)), 255, cv2.FILLED)
+        
+        '''1. and 滤除购物车边框外的干扰'''
+        loadstate = cv2.bitwise_and(self.incart, temp)
+        
+        '''2. xor 得到购物车内内被填充的区域'''
+        # loadstate = cv2.bitwise_xor(self.incart, temp1)
+        
+        num_loadstate = cv2.countNonZero(loadstate)
+        num_incart = cv2.countNonZero(self.incart)
+        loadrate = num_loadstate / (num_incart+0.01)
+        
+        # edgeline = cv2.imread("./shopcart/cart_tempt/edgeline.png", cv2.IMREAD_GRAYSCALE)
+        # cv2.imwrite(f"./test/temp.png", cv2.add(temp, edgeline))
+        # cv2.imwrite(f"./test/incart.png", cv2.add(self.incart, edgeline))
+        # cv2.imwrite(f"./test/loadstate.png", cv2.add(loadstate, edgeline))
+
+        return loadrate
+
+    @property    
+    def incart(self):
+        img = cv2.imread(str(curpath/'cart_tempt/back_incart.png'), cv2.IMREAD_GRAYSCALE)
+        ret, binary = cv2.threshold(img, 250, 255, cv2.THRESH_BINARY)
+        
+        return binary
+        
+    @property    
+    def outcart(self):
+        img = cv2.imread(str(curpath/'cart_tempt/back_outcart.png'), cv2.IMREAD_GRAYSCALE)
+        ret, binary = cv2.threshold(img, 250, 255, cv2.THRESH_BINARY)
+        
+        return binary
+    
+    @property    
+    def cartedge(self):
+        img = cv2.imread(str(curpath/'cart_tempt/back_cartedge.png'), cv2.IMREAD_GRAYSCALE)
+        ret, binary = cv2.threshold(img, 250, 255, cv2.THRESH_BINARY)
+        
+        return binary
+    
+class Track:
+    '''抽象基类，不能实例化对象'''
+    def __init__(self, boxes, imgshape=(1024, 1280)):
+        '''
+        boxes: [x1, y1, x2, y2, track_id, score, cls, frame_index, box_index] 
+                0   1   2   3      4        5     6       7           8     
+        '''
+        # 不满足以下条件时会如何？
+        assert len(set(boxes[:, 4].astype(int))) == 1, "For a Track, track_id more than 1"
+        assert len(set(boxes[:, 6].astype(int))) == 1, "For a Track, class number more than 1"
+        
+        self.boxes = boxes
+        self.tid = int(boxes[0, 4])
+        self.cls = int(boxes[0, 6])
+        self.frnum = boxes.shape[0]
+        self.imgBorder = False
+        self.imgshape = imgshape
+        self.state = MoveState.Unknown
+        
+        '''轨迹开始帧、结束帧 ID'''
+        self.start_fid = int(np.min(boxes[:, 7]))
+        self.end_fid = int(np.max(boxes[:, 7]))
+        
+        
+        
+        '''5个关键点（中心点、左上点、右上点、左下点、右下点 ）坐标'''
+        self.compute_cornpoints()
+        
+        '''5个关键点轨迹特征，可以在子类中实现，降低顺序处理时的计算量'''
+        self.compute_cornpts_feats()
+
+
+        mw, mh = np.mean(boxes[:, 2]-boxes[:, 0]), np.mean((boxes[:, 3]-boxes[:, 1]))
+        self.mwh = np.mean((mw, mh))
+        self.Area = mw * mh
+        
+        ''' 
+          最后一帧与第一帧间的位移：
+            vshift: 正值为向下，负值为向上
+            hshift: 负值为向购物车边框两边移动，正值为物品向中心移动
+        '''
+        self.vshift = self.cornpoints[-1, 1] - self.cornpoints[0, 1]   # 纵向位移
+        self.hshift = abs(self.cornpoints[0, 0] - self.imgshape[0]/2) - \
+                      abs(self.cornpoints[-1, 0]  - self.imgshape[0]/2)   
+                      
+        '''手部状态分析'''
+        self.HAND_STATIC_THRESH = 100
+        if self.cls == 0:
+            self.extract_hand_features()
+        
+        
+    def compute_cornpoints(self):
+        '''
+        cornpoints 共10项，分别是个点的坐标值（x, y）
+            (center, top_left, top_right, bottom_left, bottom_right)
+        '''
+        boxes = self.boxes
+        cornpoints = np.zeros((self.frnum, 10))
+        cornpoints[:,0] = (boxes[:, 0] + boxes[:, 2]) / 2
+        cornpoints[:,1] = (boxes[:, 1] + boxes[:, 3]) / 2
+        cornpoints[:,2], cornpoints[:,3] = boxes[:, 0], boxes[:, 1]
+        cornpoints[:,4], cornpoints[:,5] = boxes[:, 2], boxes[:, 1]
+        cornpoints[:,6], cornpoints[:,7] = boxes[:, 0], boxes[:, 3]
+        cornpoints[:,8], cornpoints[:,9] = boxes[:, 2], boxes[:, 3]
+
+        self.cornpoints = cornpoints
+    def compute_cornpts_feats(self):
+        '''
+        '''
+        trajectory = []
+        trajlens = []
+        trajdist = []
+        trajrects = []
+        for k in range(5):
+            # diff_xy2 = np.power(np.diff(self.cornpoints[:, 2*k:2*(k+1)], axis = 0), 2)
+            # trajlen = np.sum(np.sqrt(np.sum(diff_xy2, axis = 1)))
+            
+            X = self.cornpoints[:, 2*k:2*(k+1)]
+            
+            traj = np.linalg.norm(np.diff(X, axis=0), axis=1)
+            trajectory.append(traj)
+            
+            trajlen = np.sum(traj)
+            trajlens.append(trajlen)
+            
+            ptdist = np.max(cdist(X, X))
+            trajdist.append(ptdist)
+            
+            '''最小外接矩形：
+                   rect[0]: 中心(x, y)
+                   rect[1]: (w, h)
+                   rect[0]: 旋转角度 (-90°, 0]  
+            '''  
+            rect = cv2.minAreaRect(X.astype(np.int64))
+            trajrects.append(rect)
+        
+        self.trajectory = trajectory
+        self.trajlens = trajlens
+        self.trajdist = trajdist
+        self.trajrects = trajrects
+    
+
+        
+    def trajfeature(self):       
+        '''
+        分两种情况计算轨迹特征（检测框边界不在图像边界范围内，在图像边界范围内）：
+          -最小长度轨迹：trajmin
+          -最小轨迹长度：trajlen_min
+          -最小轨迹欧氏距离：trajdist_max
+        '''
+        idx1 = self.trajlens.index(max(self.trajlens))
+        trajmax = self.trajectory[idx1]
+        trajlen_max = self.trajlens[idx1]
+        trajdist_max = self.trajdist[idx1]
+        if not self.isCornpoint:
+            idx2 = self.trajlens.index(min(self.trajlens))            
+            trajmin = self.trajectory[idx2]
+            trajlen_min = self.trajlens[idx2]
+            trajdist_min = self.trajdist[idx2]
+        else:
+            trajmin = self.trajectory[0]
+            trajlen_min = self.trajlens[0]
+            trajdist_min = self.trajdist[0]
+    
+        
+        '''最小轨迹长度/最大轨迹长度，越小，代表运动幅度越小'''
+        trajlen_rate = trajlen_min/(trajlen_max+0.0001)    
+        
+        '''最小轨迹欧氏距离/目标框尺度均值'''
+        trajdist_rate = trajdist_min/(self.mwh+0.0001)
+        
+        
+        
+        self.trajmin = trajmin
+        self.trajmax = trajmax
+        self.feature = [trajlen_min, trajlen_max, 
+                        trajdist_min,  trajdist_max,
+                        trajlen_rate, trajdist_rate]
+        
+    def compute_static_fids(self, det_y, STATIC_THRESH = 8):
+        '''
+        前摄时，y一般选择为 box 的 y1 坐标，且需限定商品在购物车内。
+        inputs：
+            y：1D array，
+        parameters：
+            STATIC_THRESH：轨迹处于静止状态的阈值。
+        outputs：
+            输出为差分值小于 STATIC_THRESH 的y中元素的（start, end）索引
+            ranges = [(x1, y1), 
+                      (x1, y1), 
+                      ...]
+        '''
+        # print(f"The ID is: {self.tid}")
+        
+        # det_y = np.diff(y, axis=0)
+        ranges, rangex = [], []
+        
+        static_indices = np.where(np.abs(det_y) < STATIC_THRESH)[0]
+        
+        if len(static_indices) == 0:
+            rangex.append((0, len(det_y)))
+            return ranges, rangex
+        
+        start_index = static_indices[0]
+        
+        for i in range(1, len(static_indices)):
+            if static_indices[i] != static_indices[i-1] + 1:
+                ranges.append((start_index, static_indices[i-1] + 1))
+                start_index = static_indices[i]
+        ranges.append((start_index, static_indices[-1] + 1))
+        
+        if len(ranges) == 0:
+            rangex.append((0, len(det_y)))
+            return ranges, rangex
+        
+        idx1, idx2 = ranges[0][0], ranges[-1][1]
+        
+        if idx1 != 0:
+            rangex.append((0, idx1))
+
+        # 轨迹的最后阶段是运动状态
+        for k in range(1, len(ranges)):
+            index1 = ranges[k-1][1]
+            index2 = ranges[k][0]
+            rangex.append((index1, index2))
+            
+        if idx2 != len(det_y):
+            rangex.append((idx2, len(det_y)))
+            
+        return ranges, rangex
+    
+    
+    def extract_hand_features(self):              
+        assert self.cls == 0, "The class of traj must be HAND!"
+        
+        self.isHandStatic = False
+        
+        x0 = (self.boxes[:, 0] + self.boxes[:, 2]) / 2
+        y0 = (self.boxes[:, 1] + self.boxes[:, 3]) / 2
+        
+        handXY = np.stack((x0, y0), axis=-1)
+        # handMaxY0 = np.max(y0)
+        
+        handCenter = np.array([(max(x0)+min(x0))/2, (max(y0)+min(y0))/2])
+        
+        handMaxDist = np.max(np.linalg.norm(handXY - handCenter))
+        
+        if handMaxDist < self.HAND_STATIC_THRESH:
+            self.isHandStatic = True
+            
+            return
+
+
+
+    
+class doTracks:
+    def __init__(self, bboxes, TracksDict):
+        '''fundamental property'''
+        self.bboxes = bboxes
+        self.TracksDict = TracksDict
+        self.frameID = np.unique(bboxes[:, 7].astype(int))
+        self.trackID = np.unique(bboxes[:, 4].astype(int))
+        self.lboxes = self.array2list()  
+        
+        '''对 self.tracks 中的元素进行分类，将 track 归入相应列表中'''
+        self.Hands = []
+        self.Kids = []
+        self.Static = []
+        self.Residual = []    
+        self.DownWard = []    # subset of self.Residual
+        self.UpWard = []      # subset of self.Residual
+        self.FreeMove = []    # subset of self.Residual
+
+    
+    def array2list(self):
+        '''
+            将 bboxes 变换为 track 列表
+            bboxes: [x1, y1, x2, y2, track_id, score, cls, frame_index, box_index]
+        Return：
+            lboxes：列表，列表中元素具有同一 track_id，x1y1x2y2 格式
+                    [x1, y1, x2, y2, track_id, score, cls, frame_index, box_index]        
+        '''
+        track_ids = self.bboxes[:, 4].astype(int)
+        lboxes = []
+        for t_id in self.trackID: 
+            # print(f"The ID is: {t_id}")
+            idx = np.where(track_ids == t_id)[0]
+            box = self.bboxes[idx, :]     
+
+            lboxes.append(box)
+        
+        return lboxes
+    
+    def classify(self):
+        
+        tracks = self.tracks
+        
+
+        # 提取手的frame_id，并和动目标的frame_id 进行关联
+        hand_tracks = [t for t in tracks if t.cls==0]
+        self.Hands.extend(hand_tracks)
+        tracks = self.sub_tracks(tracks, hand_tracks)
+        
+        
+        
+        # 提取小孩的track，并计算状态：left, right, incart
+        kid_tracks = [t for t in tracks if t.cls==9]
+        kid_states = [self.kid_state(t) for t in kid_tracks]
+        self.Kids = [x for x in zip(kid_tracks, kid_states)]
+        
+        tracks = self.sub_tracks(tracks, kid_tracks)
+
+
+        static_tracks = [t for t in tracks if t.frnum>1 and t.is_static()] 
+        self.Static.extend(static_tracks)
+        
+        
+        '''剔除静止目标后的 tracks'''
+        tracks = self.sub_tracks(tracks, static_tracks)
+        
+        return tracks
+        
+    
+        
+    
+        
+       
+
+    def similarity(self):
+        nt = len(self.tracks)
+        similar_dict = {}
+        if nt >= 2:
+            for i in range(nt):
+                for j in range(i, nt):
+                    tracka = self.tracks[i]
+                    trackb = self.tracks[j]
+                    similar = self.feat_similarity(tracka, trackb)
+                    similar_dict.update({(tracka.tid, trackb.tid): similar})
+        return similar_dict
+    
+    
+    def feat_similarity(self, tracka, trackb, metric='cosine'):
+        boxes_a, boxes_b = tracka.boxes, trackb.boxes
+        na, nb = tracka.boxes.shape[0], trackb.boxes.shape[0]
+        feata, featb = [], []
+        for i in range(na):
+            fid, bid = tracka.boxes[i, 7:9]
+            feata.append(self.features_dict[fid][bid])
+        for i in range(nb):
+            fid, bid = trackb.boxes[i, 7:9]
+            featb.append(self.features_dict[fid][bid])
+        
+        feata = np.asarray(feata, dtype=np.float32)
+        featb = np.asarray(featb, dtype=np.float32)
+        similarity_matrix = 1-np.maximum(0.0, cdist(feata, featb, metric))
+        
+        feata_m = np.mean(feata, axis =0)[None,:]
+        featb_m = np.mean(featb, axis =0)[None,:]
+        simi_ab = 1 - cdist(feata_m, featb_m, metric)
+        print(f'tid {int(boxes_a[0, 4])} vs {int(boxes_b[0, 4])}: {simi_ab[0][0]}')
+        
+        # return np.max(similarity_matrix)   
+        return simi_ab
+    
+    def merge_tracks_loop(self, alist):
+        na, nb = len(alist), 0
+        while na!=nb:
+            na = len(alist)
+            alist = self.merge_tracks(alist)   #func is from subclass
+            nb = len(alist)
+        return alist
+    
+    def base_merge_tracks(self, Residual):
+        """
+        对不同id，但可能是同一商品的目标进行归并
+        """ 
+        mergedTracks = []
+        alist = [t for t in Residual]
+        while alist:
+            atrack = alist[0]
+            cur_list = []
+            cur_list.append(atrack)
+            alist.pop(0)
+            
+            blist = [b for b in alist]
+            alist = []
+            for btrack in blist:
+                if track_equal_track(atrack, btrack, self.TracksDict):
+                    cur_list.append(btrack)
+                else:
+                    alist.append(btrack)
+                    
+            mergedTracks.append(cur_list)
+            
+        return mergedTracks
+    
+    
+    @staticmethod
+    def join_tracks(tlista, tlistb):
+        """Combine two lists of stracks into a single one."""
+        exists = {}
+        res = []
+        for t in tlista:
+            exists[t.tid] = 1
+            res.append(t)
+        for t in tlistb:
+            tid = t.tid
+            if not exists.get(tid, 0):
+                exists[tid] = 1
+                res.append(t)
+        return res
+
+    @staticmethod
+    def sub_tracks(tlista, tlistb):
+        track_ids_b = {t.tid for t in tlistb}
+        return [t for t in tlista if t.tid not in track_ids_b]
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    

tracking/dotrack/dotracks_back.py

@@ -0,0 +1,179 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Mon Mar  4 18:36:31 2024
+
+@author: ym
+"""
+import numpy as np
+from utils.mergetrack import track_equal_track
+from scipy.spatial.distance import cdist
+from .dotracks import doTracks, ShoppingCart
+from .track_back import backTrack
+
+
+class doBackTracks(doTracks):
+    def __init__(self, bboxes, TracksDict):
+        
+        super().__init__(bboxes, TracksDict)
+        
+        self.tracks = [backTrack(b) for b in self.lboxes]
+        
+        # self.similar_dict = self.similarity()
+        
+        
+        self.shopcart = ShoppingCart(bboxes)
+
+# =============================================================================
+#     def array2list(self):
+#         '''           0, 1,   2,  3,     4,      5,    6,      7,          8
+#             bboxes: [x1, y1, x2, y2, track_id, score, cls, frame_index, box_index]
+#             lboxes：[x1, y1, x2, y2, track_id, score, cls, frame_index, box_index] 
+#         '''
+# 
+#         track_ids = set(self.bboxes[:, 4])
+#         lboxes = []
+#         for t_id in track_ids:
+#             idx = np.where(self.bboxes[:, 4] == t_id)[0]
+#             box = self.bboxes[idx, :]
+#             
+#             x = (box[:, 0] + box[:, 2]) / 2
+#             y = (box[:, 1] + box[:, 3]) / 2
+#             
+#             # box: [x, y, w, h, track_id, score, cls, frame_index]
+#             box[:, 2] = box[:, 2] - box[:, 0]    
+#             box[:, 3] = box[:, 3] - box[:, 1]
+#             box[:, 0] = x
+#             box[:, 1] = y
+#       
+#             lboxes.append(box)
+# 
+#         
+#         return lboxes
+# =============================================================================
+
+            
+    
+    def classify(self):
+        '''
+        功能：对 tracks 中元素分类
+        
+        '''
+        tracks = super().classify()
+        
+        # tracks = self.tracks
+        # shopcart = self.shopcart
+
+        # # 提取手的frame_id，并和动目标的frame_id 进行关联
+        # hand_tracks = [t for t in tracks if t.cls==0]
+        # self.Hands.extend(hand_tracks)
+        # tracks = self.sub_tracks(tracks, hand_tracks)
+        
+        
+        
+        # # 提取小孩的track，并计算状态：left, right, incart
+        # kid_tracks = [t for t in tracks if t.cls==9]
+        # kid_states = [self.kid_state(t) for t in kid_tracks]
+        # self.Kids = [x for x in zip(kid_tracks, kid_states)]
+        
+        # tracks = self.sub_tracks(tracks, kid_tracks)
+
+
+        # static_tracks = [t for t in tracks if t.frnum>1 and t.is_static()] 
+        # self.Static.extend(static_tracks)
+        
+        
+        # '''剔除静止目标后的 tracks'''
+        # tracks = self.sub_tracks(tracks, static_tracks)
+        
+        
+        
+        '''购物框边界外具有运动状态的干扰目标'''
+        out_trcak = [t for t in tracks if t.is_OutTrack()]
+
+        tracks = self.sub_tracks(tracks, out_trcak)
+
+        
+        '''轨迹循环归并'''
+        # merged_tracks = self.merge_tracks(tracks)
+        merged_tracks = self.merge_tracks_loop(tracks)
+        tracks = [t for t in merged_tracks if t.frnum > 1]
+
+        self.Residual = tracks
+
+
+        
+    def merge_tracks(self, Residual):
+        """
+        对不同id，但可能是同一商品的目标进行归并
+        """ 
+        mergedTracks = self.base_merge_tracks(Residual)
+        
+        oldtracks, newtracks = [], []
+        for tracklist in mergedTracks:
+            if len(tracklist) > 1:
+                boxes = np.empty((0, 9), dtype=np.float32)
+                for i, track in enumerate(tracklist):
+                    if i==0: ntid, ncls=track.boxes[0, 4], track.boxes[0, 6]
+                    iboxes = track.boxes.copy()
+                    
+                    iboxes[:, 4], iboxes[:, 6] = ntid, ncls
+                    boxes = np.concatenate((boxes, iboxes), axis=0)
+                    
+                    oldtracks.append(track)
+                    
+                fid_indices = np.argsort(boxes[:, 7])
+                boxes_fid = boxes[fid_indices]    
+                    
+                newtracks.append(backTrack(boxes_fid))
+            elif len(tracklist) == 1:
+                oldtracks.append(tracklist[0])
+                newtracks.append(tracklist[0])
+                
+
+        redu = self.sub_tracks(Residual, oldtracks)
+        merged = self.join_tracks(redu, newtracks)
+
+        return merged      
+        
+    def kid_state(self, track):
+        
+        left_dist = track.cornpoints[:, 2]
+        right_dist = 1024 - track.cornpoints[:, 4]
+        
+        if np.sum(left_dist<30)/track.frnum>0.8 and np.sum(right_dist>512)/track.frnum>0.7:
+            kidstate = "left"
+        elif np.sum(left_dist>512)/track.frnum>0.7 and np.sum(right_dist<30)/track.frnum>0.8:
+            kidstate = "right"
+        else:
+            kidstate = "incart"
+        
+        return kidstate
+    
+    
+
+    def is_associate_with_hand(self):
+        """
+        分析商品和手之间的关联性
+        """
+        pass 
+    
+    
+    
+
+      
+       
+
+    def isuptrack(self, track):
+        Flag = False
+        
+        return Flag
+    
+    def isdowntrack(self, track):
+        Flag = False
+        
+        return Flag
+    
+    def isfreetrack(self, track):
+        Flag = False
+        
+        return Flag

tracking/dotrack/dotracks_front.py

@@ -0,0 +1,184 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Mon Mar  4 18:38:20 2024
+
+@author: ym
+"""
+import numpy as np
+from utils.mergetrack import track_equal_track
+from .dotracks import doTracks
+from .track_front import frontTrack
+
+class doFrontTracks(doTracks):
+    def __init__(self, bboxes, TracksDict):
+        super().__init__(bboxes, TracksDict)
+        
+        self.tracks = [frontTrack(b) for b in self.lboxes]
+
+    def classify(self):
+        '''功能：对 tracks 中元素分类 '''
+        
+        tracks = self.tracks
+
+        '''提取手的 tracks'''
+        hand_tracks = [t for t in tracks if t.cls==0]
+        
+                
+        self.Hands.extend(hand_tracks)
+        tracks = self.sub_tracks(tracks, hand_tracks)
+        
+        
+        
+        '''提取小孩的 tracks'''
+        kid_tracks = [t for t in tracks if t.cls==9]        
+        tracks = self.sub_tracks(tracks, kid_tracks)
+
+
+        '''静态 tracks'''        
+        static_tracks = [t for t in tracks if t.frnum>1 and t.is_static()] 
+
+        
+        '''剔除静止目标后的 tracks'''
+        tracks = self.sub_tracks(tracks, static_tracks)
+         
+        '''轨迹循环归并'''
+        merged_tracks = self.merge_tracks_loop(tracks)
+        
+        tracks = [t for t in merged_tracks if t.frnum > 1]
+
+        for gtrack in tracks:
+            # print(f"Goods ID:{gtrack.tid}")
+            for htrack in hand_tracks:
+                if self.is_associate_with_hand(htrack, gtrack):
+                    gtrack.hands.append(htrack)
+                    
+        freemoved_tracks = [t for t in tracks if t.is_free_move()]
+        
+        tracks = self.sub_tracks(tracks, freemoved_tracks)
+                    
+
+        self.Residual = tracks
+  
+    def is_associate_with_hand(self, htrack, gtrack):
+        '''手部 Track、商品 Track 建立关联的依据：
+            a. 运动帧的帧索引有交集
+            b. 帧索引交集部分iou均大于0
+        '''
+        
+        assert htrack.cls==0 and gtrack.cls!=0 and gtrack.cls!=9, 'Track cls is Error!'
+        
+        hboxes = np.empty(shape=(0, 9), dtype = np.float)
+        gboxes = np.empty(shape=(0, 9), dtype = np.float)
+        
+        # start, end 为索引值，需要 start:(end+1)
+        for start, end in htrack.dynamic_y2:
+            hboxes = np.concatenate((hboxes, htrack.boxes[start:end+1, :]), axis=0)    
+        for start, end in gtrack.dynamic_y1:
+            gboxes = np.concatenate((gboxes, gtrack.boxes[start:end+1, :]), axis=0)
+        
+        hfids, gfids = hboxes[:, 7], gboxes[:, 7]
+        fids = set(hfids).intersection(set(gfids))
+        
+        if len(fids)==0:
+            return False
+        
+        
+        # print(f"Goods ID: {gtrack.tid}, Hand ID: {htrack.tid}")
+        ious = []
+        for f in fids:
+            h = np.where(hfids==f)[0][0]
+            g = np.where(gfids==f)[0][0]
+            
+            x11, y11, x12, y12 = hboxes[h, 0:4]
+            x21, y21, x22, y22 = gboxes[g, 0:4]
+            
+            x1, y1 = max((x11, x21)), max((y11, y21))
+            x2, y2 = min((x12, x22)), min((y12, y22))
+            
+            union = (x2 - x1).clip(0) * (y2 - y1).clip(0)
+            area1 = (x12 - x11) * (y12 - y11)
+            area2 = (x22 - x21) * (y22 - y21)
+            
+            iou = union / (area1 + area2 - union + 1e-6)
+            
+            if iou>0: 
+                ious.append(iou)
+        
+        return len(ious)
+    
+    
+    
+    def merge_tracks(self, Residual):
+        """
+        对不同id，但可能是同一商品的目标进行归并
+        """ 
+# =============================================================================
+#         mergedTracks = []
+#         alist = [t for t in Residual]
+#         while alist:
+#             atrack = alist[0]
+#             cur_list = []
+#             cur_list.append(atrack)
+#             alist.pop(0)
+#             
+#             blist = [b for b in alist]
+#             alist = []
+#             for btrack in blist:
+#                 if track_equal_track(atrack, btrack, self.TracksDict):
+#                     cur_list.append(btrack)
+#                 else:
+#                     alist.append(btrack)
+#                     
+#             mergedTracks.append(cur_list)
+# =============================================================================
+        mergedTracks = self.base_merge_tracks(Residual)
+        
+        oldtracks, newtracks = [], []
+        for tracklist in mergedTracks:
+            if len(tracklist) > 1:
+                boxes = np.empty((0, 9), dtype=np.float32)
+                for i, track in enumerate(tracklist):
+                    if i==0: ntid, ncls=track.boxes[0, 4], track.boxes[0, 6]
+                    iboxes = track.boxes.copy()
+                    iboxes[:, 4], iboxes[:, 6] = ntid, ncls
+                    boxes = np.concatenate((boxes, iboxes), axis=0)
+                    oldtracks.append(track)
+                
+                fid_indices = np.argsort(boxes[:, 7])
+                boxes_fid = boxes[fid_indices]
+                
+                newtracks.append(frontTrack(boxes_fid))
+            elif len(tracklist) == 1:
+                oldtracks.append(tracklist[0])
+                newtracks.append(tracklist[0])
+                
+
+        redu = self.sub_tracks(Residual, oldtracks)
+        merged = self.join_tracks(redu, newtracks)
+
+        return merged
+            
+        
+    
+        
+# =============================================================================
+#     def array2list(self):
+#         '''
+#             将 bboxes 变换为 track 列表
+#             bboxes: [x1, y1, x2, y2, track_id, score, cls, frame_index, box_index]
+#         Return：
+#             lboxes：列表，列表中元素具有同一 track_id，x1y1x2y2 格式
+#                     [x1, y1, x2, y2, track_id, score, cls, frame_index, box_index]        
+#         '''
+#         track_ids = set(self.bboxes[:, 4])
+#         lboxes = []
+#         for t_id in track_ids: 
+#             # print(f"The ID is: {t_id}")
+#             idx = np.where(self.bboxes[:, 4] == t_id)[0]
+#             box = self.bboxes[idx, :]     
+# 
+#             lboxes.append(box)
+#         
+#         return lboxes
+# =============================================================================
+    

tracking/dotrack/track_back.py

@@ -0,0 +1,329 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Mon Mar  4 18:28:47 2024
+
+@author: ym
+"""
+import cv2
+import numpy as np
+from scipy.spatial.distance import cdist
+from sklearn.decomposition import PCA
+from .dotracks import MoveState, Track
+
+
+class backTrack(Track):
+    # boxes: [x1, y1, x2, y2, track_id, score, cls, frame_index, box_index]
+    #         0,  1,  2,  3,    4,       5,    6,      7,         8
+    def __init__(self, boxes, imgshape=(1024, 1280)):
+        
+        super().__init__(boxes, imgshape)
+               
+        '''该函数依赖项: self.cornpoints'''
+        self.isCornpoint = self.isimgborder()
+        
+        '''该函数依赖项: self.isCornpoint，不能在父类中初始化'''
+        self.trajfeature()
+        
+
+        '''静止点帧索引'''
+        self.static_index = self.compute_static_fids()
+        
+        '''运动点帧索引(运动帧两端的静止帧索引)'''
+        self.moving_index = self.compute_dynamic_fids()
+        
+        self.static_dynamic_fids = self.compute_static_dynamic_fids()
+        
+        '''该函数依赖项: self.cornpoints，定义 4 个商品位置变量：
+            self.Cent_isIncart, self.LB_isIncart, self.RB_isIncart
+            self.posState = self.Cent_isIncart+self.LB_isIncart+self.RB_isIncart'''    
+        self.PositionState()
+
+        '''self.feature_ious = (incart_iou, outcart_iou, cartboarder_iou, maxbox_iou, minbox_iou)
+           self.incartrates = incartrates'''
+        self.compute_ious_feat()
+        
+        # self.PCA()
+    
+    
+    
+    def isimgborder(self, BoundPixel=10, BoundThresh=0.3):
+    
+        x1, y1 = self.cornpoints[:,2], self.cornpoints[:,3],
+        x2, y2 = self.cornpoints[:,8], self.cornpoints[:,9]
+
+        cont1 = sum(abs(x1)<BoundPixel) / self.frnum > BoundThresh
+        cont2 = sum(abs(y1)<BoundPixel) / self.frnum > BoundThresh
+        cont3 = sum(abs(x2-self.imgshape[0])<BoundPixel) / self.frnum > BoundThresh
+        cont4 = sum(abs(y2-self.imgshape[1])<BoundPixel) / self.frnum > BoundThresh
+
+        cont = cont1 or cont2 or cont3 or cont4
+        isCornpoint = False
+        if cont:
+            isCornpoint = True
+        
+        return isCornpoint
+
+
+    def PositionState(self, camerType="back"):
+        '''
+        camerType: back, 后置摄像头
+                   front, 前置摄像头
+        '''
+        if camerType=="front":
+            incart = cv2.imread("./shopcart/cart_tempt/incart.png", cv2.IMREAD_GRAYSCALE)
+        else:
+            incart = cv2.imread("./shopcart/cart_tempt/incart_ftmp.png", cv2.IMREAD_GRAYSCALE)
+
+        xc, yc = self.cornpoints[:,0].clip(0,self.imgshape[0]-1).astype(np.int64), self.cornpoints[:,1].clip(0,self.imgshape[1]-1).astype(np.int64)
+        x1, y1 = self.cornpoints[:,6].clip(0,self.imgshape[0]-1).astype(np.int64), self.cornpoints[:,7].clip(0,self.imgshape[1]-1).astype(np.int64)
+        x2, y2 = self.cornpoints[:,8].clip(0,self.imgshape[0]-1).astype(np.int64), self.cornpoints[:,9].clip(0,self.imgshape[1]-1).astype(np.int64)
+        
+        # print(self.tid)
+        Cent_inCartnum = np.count_nonzero(incart[(yc, xc)])
+        LB_inCartnum = np.count_nonzero(incart[(y1, x1)])
+        RB_inCartnum = np.count_nonzero(incart[(y2, x2)])
+        
+        self.Cent_isIncart = False
+        self.LB_isIncart = False
+        self.RB_isIncart = False
+        if Cent_inCartnum: self.Cent_isIncart = True
+        if LB_inCartnum: self.LB_isIncart = True
+        if RB_inCartnum: self.RB_isIncart = True
+        
+        self.posState = self.Cent_isIncart+self.LB_isIncart+self.RB_isIncart
+        
+        
+        
+    def PCA(self):
+        self.pca = PCA()
+        
+        X = self.cornpoints[:, 0:2]
+        self.pca.fit(X)
+        
+
+    
+
+
+    def compute_ious_feat(self):
+        '''输出：
+            self.feature_ious = (incart_iou, outcart_iou, cartboarder_iou, maxbox_iou, minbox_iou)
+            self.incartrates = incartrates，
+        其中：        
+            boxes流：track中所有boxes形成的轨迹图，可分为三部分：incart, outcart, cartboarder
+            incart_iou, outcart_iou, cartboarder_iou：各部分和 boxes流的 iou。
+            incart_iou = 0，track在购物车外，
+            outcart_iou = 0，track在购物车内，也可能是通过左下角、右下角置入购物车，
+            maxbox_iou, minbox_iou：track中最大、最小 box 和boxes流的iou，二者差值越小，越接近 1，表明track的运动型越小。
+            incartrates: 各box和incart的iou时序，由小变大，反应的是置入过程，由大变小，反应的是取出过程
+        '''
+        incart = cv2.imread("./shopcart/cart_tempt/incart.png", cv2.IMREAD_GRAYSCALE)
+        outcart = cv2.imread("./shopcart/cart_tempt/outcart.png", cv2.IMREAD_GRAYSCALE)
+        cartboarder = cv2.imread("./shopcart/cart_tempt/cartboarder.png", cv2.IMREAD_GRAYSCALE)
+        
+        incartrates = []
+        temp = np.zeros(incart.shape, np.uint8)
+        maxarea, minarea = 0, self.imgshape[0]*self.imgshape[1]
+        for i in range(self.frnum):
+            # x, y, w, h = self.boxes[i, 0:4]
+            
+            x = (self.boxes[i, 2] + self.boxes[i, 0]) / 2
+            w = (self.boxes[i, 2] - self.boxes[i, 0]) / 2
+            y = (self.boxes[i, 3] + self.boxes[i, 1]) / 2
+            h = (self.boxes[i, 3] - self.boxes[i, 1]) / 2
+            
+            
+            if w*h > maxarea: maxarea = w*h
+            if w*h < minarea: minarea = w*h
+            cv2.rectangle(temp, (int(x-w/2), int(y-h/2)), (int(x+w/2), int(y+h/2)), 255, cv2.FILLED)
+            
+            temp1 = np.zeros(incart.shape, np.uint8)
+            cv2.rectangle(temp1, (int(x-w/2), int(y-h/2)), (int(x+w/2), int(y+h/2)), 255, cv2.FILLED)
+            temp2 = cv2.bitwise_and(incart, temp1)
+            inrate = cv2.countNonZero(temp1)/(w*h)
+            incartrates.append(inrate)
+
+        isincart = cv2.bitwise_and(incart, temp)
+        isoutcart = cv2.bitwise_and(outcart, temp)
+        iscartboarder = cv2.bitwise_and(cartboarder, temp)
+        
+        num_temp = cv2.countNonZero(temp)
+        num_incart = cv2.countNonZero(isincart)
+        num_outcart = cv2.countNonZero(isoutcart)
+        num_cartboarder = cv2.countNonZero(iscartboarder)
+
+        incart_iou = num_incart/num_temp
+        outcart_iou = num_outcart/num_temp
+        cartboarder_iou = num_cartboarder/num_temp
+        maxbox_iou = maxarea/num_temp
+        minbox_iou = minarea/num_temp
+        
+        self.feature_ious = (incart_iou, outcart_iou, cartboarder_iou, maxbox_iou, minbox_iou)
+        self.incartrates = incartrates
+        
+
+ 
+    
+    def compute_static_fids(self, thresh1 = 12, thresh2 = 3):
+        '''
+        计算 track 的轨迹中相对处于静止状态的轨迹点的（start_frame_id, end_frame_id）
+        thresh1: 相邻两帧目标中心点是否静止的的阈值，以像素为单位，
+        thresh2: 连续捕捉到目标处于静止状态的帧数,当 thresh2 = 3时,至少连续 4个点,
+                 产生3个相邻点差值均小于 thresh1 时，判定为连续静止.
+          处理过程中利用了插值技术，因此start、end并非 self.boxes 中对应的帧索引
+        '''
+        
+        BoundPixel = 8
+        x1, y1 = self.cornpoints[:,2], self.cornpoints[:,3],
+        x2, y2 = self.cornpoints[:,8], self.cornpoints[:,9]
+        cont1 = sum(abs(x1)<BoundPixel) > 3
+        # cont2 = sum(abs(y1)<BoundPixel)  > 3
+        cont3 = sum(abs(x2-self.imgshape[0])<BoundPixel) > 3
+        # cont4 = sum(abs(y2-self.imgshape[1])<BoundPixel) > 3
+        cont = not(cont1 or cont3)
+        
+        ## ============== 下一步，启用中心点，选择具有最小运动幅度的角点作为参考点
+        static_index = []    
+        if self.frnum>=2 and cont:
+            x1 = self.boxes[1:,7]
+            x2 = [i for i in range(int(min(x1)), int(max(x1)+1))]
+            dist_adjc = np.interp(x2, x1, self.trajmin)
+        
+        
+            # dist_adjc = self.trajmin
+            
+            static_thresh = (dist_adjc < thresh1)[:, None].astype(np.uint8)
+            static_cnts, _ = cv2.findContours(static_thresh, cv2.RETR_LIST, cv2.CHAIN_APPROX_NONE)
+        
+            for cnt in static_cnts:
+                _, start, _, num = cv2.boundingRect(cnt)      
+                end = start + num
+                if num < thresh2:
+                    continue 
+                static_index.append((start, end))
+             
+        static_index = np.array(static_index)
+        if static_index.size:
+            indx = np.argsort(static_index[:, 0])
+            static_index = static_index[indx]
+        
+        return static_index
+            
+    def compute_dynamic_fids(self, thresh1 = 12, thresh2 = 3):
+        '''
+        计算 track 的轨迹中运动轨迹点的（start_frame_id, end_frame_id）
+        thresh1: 相邻两帧目标中心点是否运动的阈值，以像素为单位，
+        thresh2: 连续捕捉到目标连续运动的帧数
+        目标：
+            1. 计算轨迹方向
+            2. 计算和手部运动的关联性
+        '''
+        moving_index = []
+        if self.frnum>=2:
+            x1 = self.boxes[1:,7]
+            x2 = [i for i in range(int(min(x1)), int(max(x1)+1))]
+            dist_adjc = np.interp(x2, x1, self.trajmin)
+
+            moving_thresh = (dist_adjc >= thresh1)[:, None].astype(np.uint8)
+            moving_cnts, _ = cv2.findContours(moving_thresh, cv2.RETR_LIST, cv2.CHAIN_APPROX_NONE)
+
+            for cnt in moving_cnts:
+                _, start, _, num = cv2.boundingRect(cnt)      
+                if num < thresh2:
+                    continue
+                end = start + num
+                moving_index.append((start, end))
+            
+# =============================================================================
+#         '''========= 输出帧id，不太合适 ========='''
+#         moving_fids = []
+#         for i in range(len(moving_index)):
+#             i1, i2 = moving_index[i]
+#             fid1, fid2 = boxes[i1, 7], boxes[i2, 7]
+#             moving_fids.append([fid1, fid2])
+#         moving_fids = np.array(moving_fids)
+# =============================================================================
+        moving_index = np.array(moving_index)
+        if moving_index.size:
+            indx = np.argsort(moving_index[:, 0])
+            moving_index = moving_index[indx]
+        
+        return moving_index     
+    
+    def compute_static_dynamic_fids(self):
+        static_dynamic_fids = []
+        for traj in self.trajectory:
+            static, dynamic = self.compute_static_fids(traj)
+            
+            static_dynamic_fids.append((static, dynamic))
+            
+        return static_dynamic_fids
+    
+    
+    
+    
+    
+    def is_static(self):
+        
+        '''静态情况 1: 目标关键点最小相对运动轨迹 < 0.2, 指标值偏大
+           feature = [trajlen_min, trajlen_max, 
+                      trajdist_min,  trajdist_max,
+                      trajlen_rate, trajdist_rate]
+        '''
+        
+        condt1 = self.feature[5] < 0.2 or self.feature[3] < 120
+        
+        '''静态情况 2: 目标初始状态为静止，适当放宽关键点最小相对运动轨迹 < 0.5'''
+        condt2 = self.static_index.size > 0 \
+                 and self.static_index[0, 0] <= 2 \
+                 and self.feature[5] < 0.5
+        
+        '''静态情况 3: 目标初始状态和最终状态均为静止'''
+        condt3 = self.static_index.shape[0] >= 2 \
+                 and self.static_index[0, 0] <= 2 \
+                 and self.static_index[-1, 1] >= self.frnum-3 \
+        
+        condt = condt1 or condt2 or condt3
+        
+        return condt
+              
+# =============================================================================
+#         track1 = [t for t in tracks if t.feature[5] < 0.2
+#                                     or t.feature[3] < 120
+#                                     ] 
+# 
+#         track2 = [t for t in tracks if t.static_index.size > 0
+#                                    and t.static_index[0, 0] <= 2                      
+#                                    and t.feature[5] < 0.5]
+# 
+#         track3 = [t for t in tracks if t.static_index.shape[0] >= 2
+#                                    and t.static_index[0, 0] <= 2
+#                                    and t.static_index[-1, 1] >= t.frnum-3]
+#         
+#         track12 = self.join_tracks(track1, track2) 
+#         
+#         '''提取静止状态的 track'''
+#         static_tracks = self.join_tracks(track12, track3)
+#         self.Static.extend(static_tracks)
+#         
+# ============================================================================= 
+    
+    def is_OutTrack(self):     
+        if self.posState <= 1:
+            isout = True
+        else:
+            isout = False  
+        return isout
+    
+    
+    
+    
+    def compute_distance(self):
+        pass
+    
+    
+    def move_start_fid(self):
+        pass
+    
+    
+    def move_end_fid(self):
+        pass

tracking/dotrack/track_front.py

@@ -0,0 +1,271 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Mon Mar  4 18:33:01 2024
+
+@author: ym
+"""
+import numpy as np
+from sklearn.cluster import KMeans
+from .dotracks import MoveState, Track
+
+
+class frontTrack(Track):
+    # boxes: [x1, y1, x2, y2, track_id, score, cls, frame_index, box_index]
+    #         0,  1,  2,  3,    4,        5,    6,      7,         8
+    def __init__(self, boxes, imgshape=(1024, 1280)):
+        
+        super().__init__(boxes, imgshape)
+        self.hands = []
+        
+        
+        '''5个关键点（中心点、左上点、右上点、左下点、右下点 ）轨迹特征'''
+        # self.compute_cornpts_feats()
+        
+        
+        self.CART_HIGH_THRESH1 = imgshape[1]/2.98
+        
+
+        # if self.tid==10:
+        #     print(f"ID: {self.tid}")
+        
+        '''y1、y2静止状态区间，值是 boxes 中对 axis=0 的索引，不是帧索引'''
+        det_y1 = np.diff(boxes[:, 1], axis=0)
+        det_y2 = np.diff(boxes[:, 3], axis=0)
+        self.static_y1, self.dynamic_y1 = self.compute_static_fids(det_y1)
+        self.static_y2, self.dynamic_y2 = self.compute_static_fids(det_y2)
+        
+        self.isCornpoint = self.is_left_or_right_cornpoint()
+        self.isBotmpoint = self.is_bottom_cornpoint()
+        
+        '''该函数依赖项: self.isCornpoint，不能在父类中初始化'''
+        self.trajfeature()
+        
+        
+        '''手部状态分析'''
+        self.HAND_STATIC_THRESH = 100
+        self.CART_POSIT_0 = 430
+        self.CART_POSIT_1 = 620
+        
+        
+        
+
+    def is_left_or_right_cornpoint(self):
+        ''' 基于 all(boxes)，
+         boxes左下角点和图像左下角点重叠 或
+         boxes右下角点和图像左下角点重叠
+        '''
+        x1, y1 = self.boxes[:, 0], self.boxes[:, 1]
+        x2, y2 = self.boxes[:, 2], self.boxes[:, 3]
+        
+        # Left-Bottom cornpoint
+        condt1 = all(x1 < 5) and all(y2 > self.imgshape[1]-5)
+        
+        # Right-Bottom cornpoint
+        condt2 = all(x2 > self.imgshape[0]-5) and all(y2 > self.imgshape[1]-5)
+        
+        condt = condt1 or condt2    
+        
+        return condt
+    
+    def is_edge_cornpoint(self):
+        '''基于 all(boxes)，boxes是否和图像左右边缘重叠'''
+        x1, x2 = self.boxes[:, 0], self.boxes[:, 2]
+        condt = all(x1 < 3) or all(x2 > self.imgshape[0]-3)
+        
+        return condt
+
+    def is_bottom_cornpoint(self):
+        '''基于 all(boxes)，boxes是否和图像下边缘重叠'''
+        condt = all(self.boxes[:, 3] > self.imgshape[1]-20)
+        
+        return condt
+    
+    # def is_OutTrack(self):     
+    #     isout = False
+    #     if self.posState <= 1:
+    #         isout = True       
+    #     return isout
+    
+ 
+# =============================================================================
+#     def compute_static_fids(self, det_y, STATIC_THRESH = 8):
+#         '''
+#         前摄时，y一般选择为 box 的 y1 坐标，且需限定商品在购物车内。
+#         inputs：
+#             y：1D array，
+#         parameters：
+#             STATIC_THRESH：轨迹处于静止状态的阈值。
+#         outputs：
+#             输出为差分值小于 STATIC_THRESH 的y中元素的（start, end）索引
+#             ranges = [(x1, y1), 
+#                       (x1, y1), 
+#                       ...]
+#         '''
+#         # print(f"The ID is: {self.tid}")
+#         
+#         # det_y = np.diff(y, axis=0)
+#         ranges, rangex = [], []
+#         
+#         static_indices = np.where(np.abs(det_y) < STATIC_THRESH)[0]
+#         
+#         if len(static_indices) == 0:
+#             rangex.append((0, len(det_y)))
+#             return ranges, rangex
+#         
+#         start_index = static_indices[0]
+#         
+#         for i in range(1, len(static_indices)):
+#             if static_indices[i] != static_indices[i-1] + 1:
+#                 ranges.append((start_index, static_indices[i-1] + 1))
+#                 start_index = static_indices[i]
+#         ranges.append((start_index, static_indices[-1] + 1))
+#         
+#         if len(ranges) == 0:
+#             rangex.append((0, len(det_y)))
+#             return ranges, rangex
+#         
+#         idx1, idx2 = ranges[0][0], ranges[-1][1]
+#         
+#         if idx1 != 0:
+#             rangex.append((0, idx1))
+# 
+#         # 轨迹的最后阶段是运动状态
+#         for k in range(1, len(ranges)):
+#             index1 = ranges[k-1][1]
+#             index2 = ranges[k][0]
+#             rangex.append((index1, index2))
+#             
+#         if idx2 != len(det_y):
+#             rangex.append((idx2, len(det_y)))
+#             
+#         return ranges, rangex
+#     
+# =============================================================================
+
+
+
+    def is_static(self):
+        assert self.frnum > 1, "boxes number must greater than 1"
+        # print(f"The ID is: {self.tid}")
+        
+        # 手部和小孩目标不考虑
+        if self.cls == 0 or self.cls == 9: 
+            return False
+        
+        # boxes 全部 y2=1280
+        if self.isBotmpoint:
+            return True
+        
+        boxes = self.boxes
+        y0 = (boxes[:, 1]+boxes[:, 3])/2        
+        
+        ## 纵轴矢量和
+        sum_y0 = y0[-1] - y0[0]
+        sum_y1 = boxes[-1, 1]-boxes[0, 1]
+        sum_y2 = boxes[-1, 3]-boxes[0, 3]
+        
+        # 一些需要考虑的特殊情况
+        isbottom = max(boxes[:, 3]) > 1280-3
+        istop = min(boxes[:, 1]) < 3
+        isincart = min(y0) > self.CART_HIGH_THRESH1
+        uncert = abs(sum_y1)<100 and abs(sum_y2)<100
+        
+        '''初始条件：商品中心点始终在购物车内、'''
+        condt0 = max((boxes[:, 1]+boxes[:, 3])/2) > self.CART_HIGH_THRESH1 
+        
+        '''条件1：轨迹运动纵向和（y1 或 y2）描述商品轨迹长度，存在情况：
+            (1). 检测框可能与图像上下边缘重合，
+            (2). 上边或下边存在跳动
+        '''
+        if isbottom and istop:
+            condt1 = abs(sum_y0) < 300
+        elif isbottom:   # y2在底部，用y1表征运动
+            condt1 = sum_y1 > -120 and abs(sum_y0)<80 # 有底部点，方向向上阈值小于100
+        elif istop:      # y1在顶部，用y2表征运动
+            condt1 = abs(sum_y2) < 100
+        else:
+            condt1 = (abs(sum_y1) < 30 or abs(sum_y2)<30)
+            
+        '''条件2：轨迹的开始和结束阶段均处于静止状态, 利用静止状态区间判断，用 y1
+                  a. 商品在购物车内，
+                  b. 检测框的起始阶段和结束阶段均为静止状态
+                  c. 静止帧长度 > 3'''
+        
+        condt2 = False
+        if len(self.static_y1)>=2: 
+            condt_s0 = self.static_y1[0][0]==0 and self.static_y1[0][1] - self.static_y1[0][0] >= 3
+            condt_s1 = self.static_y1[-1][1]==self.frnum-1 and self.static_y1[-1][1] - self.static_y1[-1][0] >= 3 
+            condt2 = condt_s0 and condt_s1 and isincart
+
+
+        condt = condt0 and (condt1 or condt2)
+        
+        return condt
+    
+    
+    
+            
+        
+        
+    
+    
+    
+    
+    def is_upward(self):
+        '''判断商品是否取出，'''
+        print(f"The ID is: {self.tid}")
+        
+    def is_free_move(self):
+        if self.frnum == 1:
+            return True
+        # print(f"The ID is: {self.tid}")
+        
+        
+        y0 = (self.boxes[:, 1] + self.boxes[:, 3]) / 2 
+        det_y0 = np.diff(y0, axis=0)
+        sum_y0 = y0[-1] - y0[0]
+        
+        '''情况1：中心点向下 '''
+        ## 初始条件：商品第一次检测到在购物车内
+        condt0 = y0[0] > self.CART_HIGH_THRESH1
+        
+        condt_a = False
+        ## 条件1：商品初始为静止状态，静止条件应严格一些
+        condt11, condt12 = False, False
+        if len(self.static_y1)>0:
+            condt11 = self.static_y1[0][0]==0 and self.static_y1[0][1] - self.static_y1[0][0] >= 5
+        if len(self.static_y2)>0:   
+            condt12 = self.static_y2[0][0]==0 and self.static_y2[0][1] - self.static_y2[0][0] >= 5        
+        
+        # 条件2：商品中心发生向下移动
+        condt2 =  y0[-1] > y0[0]
+        
+        # 综合判断a
+        condt_a = condt0 and (condt11 or condt12) and condt2
+
+        '''情况2：中心点向上 '''
+        ## 商品中心点向上移动，但没有关联的Hand轨迹，也不是左右边界点
+        condt_b =  condt0 and len(self.hands)==0 and  y0[-1] < y0[0] and (not self.is_edge_cornpoint())
+
+
+        '''情况3: 商品在购物车内，但运动方向无序'''
+        ## 中心点在购物车内，纵向轨迹和小于轨迹差中绝对值最大的两个值的和，说明运动没有主方向
+        condt_c = False
+        if self.frnum > 3:
+            condt_c = all(y0>self.CART_HIGH_THRESH1) and \
+                (abs(sum_y0) < sum(np.sort(np.abs(det_y0))[::-1][:2])-1)
+        
+        condt = (condt_a or condt_b or condt_c) and self.cls!=0  
+        
+        return condt
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    

tracking/goodmatch.py

@@ -0,0 +1,773 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Tue Apr 16 11:51:07 2024
+
+@author: ym
+"""
+import cv2
+import os
+import numpy as np
+# import time
+import pickle
+import json
+# import matplotlib.pyplot as plt
+import pandas as pd 
+import shutil
+import random
+import math
+
+from scipy.spatial.distance import cdist
+import matplotlib.pyplot as plt
+
+from pathlib import Path
+from utils.gen import Profile
+from dotrack.dotracks_back import doBackTracks
+from dotrack.dotracks_front import doFrontTracks 
+from utils.drawtracks import plot_frameID_y2, draw_all_trajectories
+
+# from utils.drawtracks import draw5points, drawTrack, drawtracefeat, drawFeatures
+# from datetime import datetime
+
+from utils.mergetrack import readDict
+
+
+
+def get_img_filename(imgpath = r'./matching/images/' ):
+    imgexts = ['.png', '.jpg', '.jpeg']
+    ImgFileList = []
+    for root, dirs, files in os.walk(imgpath):
+        ImgList = []
+        for file in files:
+            _, ext = os.path.splitext(file)
+            if ext in imgexts:
+                ImgFileList.append(os.path.join(root, file))
+    
+    return ImgFileList
+
+
+def calculate_similarity_track(similarmode = 'other'):
+    '''
+    similarmode:
+        'mean'
+        'other'
+    
+    '''
+
+    ContrastDict = np.load('./matching/featdata/imgs_feats_data_refined.pkl', allow_pickle=True)
+    print(f"The Num of imgsample: {len(ContrastDict)}")   
+
+    ''''================= 构造空字典 MatchObjDict ================='''
+    def splitkey(key):
+        videoname = key.split('_')
+        BarCode = videoname[0]
+        SampleTime = videoname[1].split('-')[1]
+        CameraType = videoname[2]
+        ActionType = videoname[3]
+        TrackID = '_'.join(key.split('_')[7:])
+        
+        return BarCode, SampleTime, CameraType, ActionType, TrackID
+
+    MatchObjList = []
+    CameraList = []
+    for key in ContrastDict.keys():
+        BarCode, SampleTime, CameraType, ActionType, FeatureID = splitkey(key)
+        
+        MatchObjList.append('_'.join([BarCode, SampleTime, ActionType]))
+        CameraList.append(CameraType)
+    
+    # MatchObjSet = set(MatchObjList)
+    # CameraSet = set(CameraList)
+    
+    
+    objects = list(set(MatchObjList))
+    cameras = list(set(CameraList))
+    assert len(cameras) == 2, "The num of cameras is error!"
+    
+    MatchObjDict = {}
+    for obj in objects:
+        CameraDict = {}
+        for camera in cameras:
+            CameraDict[camera] = {}
+
+        MatchObjDict[obj] = CameraDict
+        
+    
+    
+    for key, value in ContrastDict.items():
+        BarCode, SampleTime, CameraType, ActionType, FeatureID = splitkey(key)
+        
+        MatchObj = '_'.join([BarCode, SampleTime, ActionType])
+        
+        vdict = {}
+        if FeatureID not in MatchObjDict[MatchObj][CameraType]:
+            vdict[FeatureID] = value['feature']
+            MatchObjDict[MatchObj][CameraType].update(vdict)
+            
+    print(f"The Num of MatchObjDict: {len(MatchObjDict)}")
+    
+    # MatchKeys = [key for key in MatchObjDict.keys()]
+    num = len(objects)
+    GtMatrix = np.zeros((num, num), dtype=np.float32)
+    Similarity = np.zeros((num, num), dtype=np.float32)
+    InterMatrix = np.zeros((num, num), dtype=np.float32)   # 类间
+    IntraMatrix = np.zeros((num, num), dtype=np.float32)   # 类内
+    
+    '''生成GT矩阵: GtMatrix, IntraMatrix, InterMatrix'''
+    for i, obi in enumerate(objects):
+        barcode_i = obi.split('_')[0]
+        for j, obj in enumerate(objects):
+            barcode_j = obj.split('_')[0]
+            if barcode_i == barcode_j:
+                GtMatrix[i, j] = 1
+                if i!=j: IntraMatrix[i, j] = 1
+            else:
+                GtMatrix[i, j] = 0
+                InterMatrix[i, j] = 1   
+
+    
+    '''生成相似度矩阵: Similarity '''
+    
+    ObjFeatList = []
+    for i, obi in enumerate(objects):
+        obidict = MatchObjDict[obi]
+        camlist = []
+        for camera in obidict.keys():
+            featlist = []
+            for fid in obidict[camera].keys():
+                featlist.append(MatchObjDict[obi][camera][fid])
+            
+            camlist.append(featlist)
+        
+        ObjFeatList.append(camlist)
+        
+    Similarity_1 = Similarity.copy()
+    for i in range(len(objects)):
+        obi = ObjFeatList[i]
+        for j in range(len(objects)):
+            obj = ObjFeatList[j] 
+            simival = []
+            for ii in range(len(obi)):
+                if len(obi[ii])==0: continue
+                feat_ii = np.asarray(obi[ii])
+                
+                for jj in range(len(obj)):
+                    if len(obj[jj])==0: continue
+                    feat_jj = np.asarray(obj[jj])
+                    
+                    if similarmode == 'mean':
+                        featii = np.mean(feat_ii, axis=0)
+                        featjj = np.mean(feat_jj, axis=0)
+                        try:
+                            matrix = 1- np.maximum(0.0, cdist(featii[None, :], featjj[None, :], 'cosine'))
+                        except Exception as e:
+                            print(f'error is {e.__class__.__name__}')
+                            
+                    else:
+                        matrix = 1- np.maximum(0.0, cdist(feat_ii, feat_jj, 'cosine'))    
+                    simival.append(np.max(matrix))
+            if len(simival)==0: continue
+            
+            Similarity[i, j] = max(simival)
+                
+             # feat_i = np.empty((0, 256), dtype = np.float32)
+             # feat_j = np.empty((0, 256), dtype = np.float32)
+             # for ii in range(len(obi)):
+             #     feat_ii = np.asarray(obi[ii])
+             #     feat_i = np.concatenate((feat_i, feat_ii), axis=0)
+             # for jj in range(len(obj)):
+             #     feat_jj = np.asarray(obi[jj])
+             #     feat_j = np.concatenate((feat_j, feat_jj), axis=0)
+                 
+             # if similarmode == 'mean':
+             #     feati = np.mean(feat_i, axis=0)
+             #     featj = np.mean(feat_j, axis=0)
+             #     matrix = 1- np.maximum(0.0, cdist(feati[None, :], featj[None, :], 'cosine')) 
+             # else: 
+             #     matrix = 1- np.maximum(0.0, cdist(feat_i, feat_j, 'cosine'))
+                 
+             # Similarity_1[i, j] = np.max(matrix)
+                
+                
+    SimiDict = {'keys': objects, 'GtMatrix': GtMatrix, 'Similarity': Similarity,
+                  'IntraMatrix':IntraMatrix, 'InterMatrix':InterMatrix}
+    with open(r"./matching/featdata/MatchDict_track.pkl", "wb") as f:
+        pickle.dump(SimiDict, f)
+    
+    # SimiDict_1 = {'keys': objects, 'GtMatrix': GtMatrix, 'Similarity':Similarity_1, 
+    #               'IntraMatrix':IntraMatrix, 'InterMatrix':InterMatrix}    
+    # with open(r"./matching/featdata/MatchDict_track_1.pkl", "wb") as f:
+    #     pickle.dump(SimiDict_1, f)
+    
+    df_GtMatrix = pd.DataFrame(data=GtMatrix, columns = objects, index = objects)
+    df_GtMatrix.to_csv('./matching/featdata/GtMatrix_track.csv',index=True)  
+
+    df_similarity = pd.DataFrame(data=Similarity, columns = objects, index = objects)
+    df_similarity.to_csv('./matching/featdata/Similarity_track.csv',index=True)
+    
+    # df_similarity_1 = pd.DataFrame(data=Similarity_1, columns = objects, index = objects)
+    # df_similarity_1.to_csv('./matching/featdata/Similarity_track_1.csv',index=True)
+
+    print("Done!!!!")
+
+# SimilarMode = ['mean', 'max']
+def calculate_similarity(similarmode = 'mean'):  
+    ContrastDict = np.load('./matching/featdata/imgs_feats_data_noplane.pkl', allow_pickle=True)
+    print(f"The Num of imgsample: {len(ContrastDict)}")
+    
+    FrontBackMerged = True
+    TracKeys = {}
+    for key, value in ContrastDict.items():    
+        feature = value['feature']
+        videoname = key.split('_')[:7]
+        BarCode = videoname[0]
+        SampleTime = videoname[1].split('-')[1]
+        CameraType = videoname[2]
+        ActionType = videoname[3]
+        TrackID = key.split('_')[7]
+        
+        if FrontBackMerged:
+            TracKey = '_'.join([BarCode, SampleTime, ActionType])
+        else:
+            TracKey = '_'.join([BarCode, SampleTime, CameraType, ActionType])
+
+        if TracKey in TracKeys:
+            TracKeys[TracKey].append(feature)
+        else:
+            TracKeys[TracKey] = []
+            TracKeys[TracKey].append(feature)
+  
+    '''===== 生成GT矩阵: Similarity、GtMatrix、IntraMatrix、InterMatrix ====='''
+    num = len(TracKeys)
+    keys = [key for key in TracKeys.keys()]
+    
+    GtMatrix = np.zeros((num, num), dtype=np.float32)
+    Similarity = np.zeros((num, num), dtype=np.float32)
+    
+    InterMatrix = np.zeros((num, num), dtype=np.float32)   # 类间
+    IntraMatrix = np.zeros((num, num), dtype=np.float32)   # 类内
+
+    for i, key_i in enumerate(keys):
+        barcode_i = key_i.split('_')[0]
+        feat_i = np.asarray(TracKeys[key_i], dtype=np.float32)
+        for j, key_j in enumerate(keys):
+            barcode_j = key_j.split('_')[0]
+            feat_j = np.asarray(TracKeys[key_j], dtype=np.float32)
+            
+            if similarmode == 'mean':
+                feati = np.mean(feat_i, axis=0)
+                featj = np.mean(feat_j, axis=0)
+                matrix = 1- np.maximum(0.0, cdist(feati[None, :], featj[None, :], 'cosine')) 
+            else: 
+                matrix = 1- np.maximum(0.0, cdist(feat_i, feat_j, 'cosine'))   
+            Similarity[i, j] = np.max(matrix)
+            
+            if barcode_i == barcode_j:
+                GtMatrix[i, j] = 1
+                if i!=j: IntraMatrix[i, j] = 1
+            else:
+                GtMatrix[i, j] = 0
+                InterMatrix[i, j] = 1
+                
+    
+                
+# =============================================================================
+#     '''生成相似度矩阵: Similarity '''
+#     for i, key_i in enumerate(keys):
+#         feat_i = np.asarray(TracKeys[key_i], dtype=np.float32)
+#         for j, key_j in enumerate(keys):
+#             feat_j = np.asarray(TracKeys[key_j], dtype=np.float32)
+#             
+#             if similarmode == 'mean':
+#                 feati = np.mean(feat_i, axis=0)
+#                 featj = np.mean(feat_j, axis=0)
+#                 matrix = 1- np.maximum(0.0, cdist(feati[None, :], featj[None, :], 'cosine')) 
+#             else: 
+#                 matrix = 1- np.maximum(0.0, cdist(feat_i, feat_j, 'cosine'))   
+#             Similarity[i, j] = np.max(matrix)
+# =============================================================================
+    
+    MatchDict = {'keys': keys, 'GtMatrix':GtMatrix, 'Similarity':Similarity, 
+                 'IntraMatrix':IntraMatrix, 'InterMatrix':InterMatrix}
+    with open(r"./matching/featdata/MatchDict_noplane.pkl", "wb") as f:
+        pickle.dump(MatchDict, f) 
+
+    df_GtMatrix = pd.DataFrame(data=GtMatrix, columns = keys, index = keys)
+    df_GtMatrix.to_csv('./matching/featdata/GtMatrix_noplane.csv',index=True)  
+
+    df_similarity = pd.DataFrame(data=Similarity, columns = keys, index = keys)
+    df_similarity.to_csv('./matching/featdata/Similarity_noplane.csv',index=True)
+
+
+def sortN_matching(filename = r'./matching/featdata/MatchDict.pkl'):        
+    SimilarDict = np.load(filename, allow_pickle=True) 
+    
+    '''********** keys的顺序与Similarity中行列值索引一一对应 **********'''
+    keys = SimilarDict['keys']
+    Similarity = SimilarDict['Similarity']
+    
+    '''1. 将时间根据 Barcode 归并，并确保每个 Barcode 下至少两个事件'''
+    BarcodeDict1 = {}
+    for i, key in enumerate(keys):
+        barcode = key.split('_')[0]
+        
+        if barcode not in BarcodeDict1.keys():
+            BarcodeDict1[barcode] = []
+        BarcodeDict1[barcode].append(i)
+        
+        
+    BarcodeDict = {}
+    BarcodeList = []
+    for barcode, value in BarcodeDict1.items():
+        if len(value) < 2: continue
+        BarcodeDict[barcode] = value
+        BarcodeList.append(barcode)
+        
+    BarcodeList = list(set(BarcodeList))
+
+    '''实验参数设定
+        N: 任意选取的 Barcode 数
+        R：重复实验次数，每次从同一 Barcode 下随机选取2个事件，分别归入加购、退购集合
+        Thresh：相似度阈值
+        
+    '''
+    N = 10
+    if N > len(BarcodeList): 
+        N = math.ceil(len(BarcodeList)/2)
+    R = 20
+    Thresh = np.linspace(0.1, 1, 100)
+    # Thresh = np.linspace(0.601, 0.7, 100)
+    
+    Recall, Precision = [], []
+    for th in Thresh:
+        recall = np.zeros((1, R), dtype=np.float32)
+        precision = np.zeros((1, R), dtype=np.float32)
+        
+        for rep in range(R):
+            BarcodeSelect = random.sample(BarcodeList, N)
+
+            AddDict = {}
+            TakeoutDict = {}
+            for barcode in BarcodeSelect:
+                barlist = BarcodeDict[barcode]
+                if len(barlist) < 2:continue
+                
+                selected = random.sample(barlist, 2)
+                
+                AddDict[barcode] = selected[0]
+                TakeoutDict[barcode] = selected[1]
+            
+            OrderMatrix = np.zeros((N, N), dtype=np.float32)
+            GTMatrix = np.zeros((N, N), dtype=np.float32)
+            
+            MatchMatrix_1 = np.zeros((N, N), dtype=np.float32)
+            MatchMatrix_2 = np.zeros((N, N), dtype=np.float32)
+            
+            i = 0
+            for keyi in BarcodeSelect:
+                ii = TakeoutDict[keyi]
+                j = 0
+                for keyj in BarcodeSelect:
+                    jj = AddDict[keyj]
+                    
+                    OrderMatrix[i, j] = Similarity[int(ii), int(jj)]
+                    
+                    if keyi == keyj:
+                        GTMatrix[i, j] = 1
+                    
+                    j += 1
+                i += 1
+            
+            max_indices  = np.argmax(OrderMatrix, axis = 1)
+            for i in range(N):
+                MatchMatrix_1[i, max_indices[i]] = 1
+                
+                similar = OrderMatrix[i, max_indices[i]] 
+                if similar > th:
+                    MatchMatrix_2[i, max_indices[i]] = 1
+                
+                    
+            GT_indices = np.where(GTMatrix == 1)
+            
+            FNTP = MatchMatrix_2[GT_indices]
+            pred_indices = np.where(MatchMatrix_2 == 1)
+            
+            
+            
+            TP = np.sum(FNTP==1)
+            FN = np.sum(FNTP==0)
+            FPTP = GTMatrix[pred_indices]
+            
+            FP = np.sum(FPTP == 0)
+            # assert TP == np.sum(FPTP == 0), "Please Check Errors!!!"
+            
+            recall[0, rep] = TP/(TP+FN)
+            precision[0, rep] = TP/(TP+FP+1e-3) # 阈值太大时可能TP、FP都为0，
+            
+        Recall.append(recall)
+        Precision.append(precision)
+        
+        
+    
+    Recall = np.asarray(Recall).reshape([len(Thresh),-1])
+    Precision = np.asarray(Precision).reshape([len(Thresh),-1]) 
+    
+    reclmean = np.sum(Recall, axis=1) / (np.count_nonzero(Recall, axis=1) + 1e-3)
+    precmean = np.sum(Precision, axis=1) / (np.count_nonzero(Precision, axis=1) + 1e-3)
+    
+    print("Done!!!!!")
+    
+    # th1, recl = [c[0] for c in Recall], [c[1] for c in Recall]
+    # th2, prep = [c[0] for c in Precision], [c[1] for c in Precision]
+    
+    recl = [r for r in reclmean]
+    prep = [p for p in precmean]
+
+
+    '''================= Precision & Recall ================='''
+    fig, ax = plt.subplots()
+    ax.plot(Thresh, recl, 'g', label='Recall = TP/(TP+FN)')
+    ax.plot(Thresh, prep, 'r', label='PrecisePos = TP/(TP+FP)')
+    # ax.set_xlim([0, 1])
+    # ax.set_ylim([0, 1])
+    ax.grid(True)
+    ax.set_title('Precision & Recall')     
+    ax.legend()
+    plt.show() 
+        
+        
+        
+def match_evaluate(filename = r'./matching/featdata/MatchDict.pkl'):        
+    SimiDict = np.load(filename, allow_pickle=True) 
+    
+    keys = SimiDict['keys']
+    GtMatrix = SimiDict['GtMatrix']
+    Similarity = SimiDict['Similarity']
+    
+    IntraMatrix = SimiDict['IntraMatrix']
+    InterMatrix = SimiDict['InterMatrix']
+    
+    
+    BarcodeList = []
+    for key in keys:
+        BarcodeList.append(key.split('_')[0])  
+    BarcodeList = list(set(BarcodeList))    
+
+
+    IntraRows, IntraCols = np.nonzero(IntraMatrix) 
+    InterRows, InterCols = np.nonzero(InterMatrix)
+    IntraN, InterN = len(IntraRows), len(InterRows)
+    assert IntraN <= InterN, "类内大于类间数，样本不平衡"
+    
+    InterNSelect =  IntraN  
+    Thresh = np.linspace(0.1, 1, 100)
+    # Thresh = np.linspace(0.2, 0.4, 11)
+    Correct = []
+    PrecisePos = []
+    PreciseNeg = []
+    Recall = []
+    CorrectMatries = []
+    for th in Thresh:
+        MatchMatrix = Similarity > th
+        CorrectMatrix = MatchMatrix == GtMatrix
+        
+        CorrectMatries.append(CorrectMatrix)
+        
+        nn = np.random.permutation(np.arange(InterN))[:InterNSelect]
+        InterRowsSelect, InterColsSelect = InterRows[nn], InterCols[nn]
+        
+        IntraCorrMatrix = CorrectMatrix[IntraRows, IntraCols]
+        InterCorrMatrix = CorrectMatrix[InterRowsSelect, InterColsSelect]
+        
+        TP = np.sum(IntraCorrMatrix)
+        TN = np.sum(InterCorrMatrix)
+        FN = IntraN - TP
+        FP = InterNSelect - TN
+        
+        if TP+FP > 0:
+            PrecisePos.append((th, TP/(TP+FP)))
+        if TN+FN > 0:
+            PreciseNeg.append((th, TN/(TN+FN)))
+        if TP+FN > 0:
+            Recall.append((th, TP/(TP+FN)))
+            
+        if TP+TN+FP+FN > 0:  
+            Correct.append((th, (TP+TN)/(TP+TN+FP+FN)))
+        # print(f'Th: {th}')    
+        # print(f'TP:{TP}, FP:{FP}, TN:{TN}, FN:{FN}')
+        
+
+    CorrectMatries = np.asarray(CorrectMatries)
+    
+    '''====================== 分析错误原因 =========================='''
+    '''
+    keys两种构成方式，其中的元素来自于：MatchingDict
+        BarCode, SampleTime, ActionType #不考虑摄像头类型（前后摄）
+        BarCode, SampleTime, CameraType, ActionType# 考虑摄像头类型（前后摄）
+    为了便于显示，在图像文件名中，将 ActionType 进行了缩写，匹配时取 [:3]
+        "addGood"    --------> "add"
+        "returnGood" --------> "return"
+    '''
+    ##============= 获取图像存储位置,可以通过 keys 检索到对应的图像文件
+    imgpath = r'./matching/images/' 
+    ImgFileList = get_img_filename(imgpath)
+    
+    rowx, colx = np.where(CorrectMatries[66,:,:] == False)
+    rows, cols = [], []
+    for i in range(len(rowx)):
+        ri, ci = rowx[i], colx[i]
+        if ci > ri:
+            rows.append(ri)
+            cols.append(ci)
+    
+    
+    KeysError = [(keys[rows[i]], keys[cols[i]]) for i in range(len(rows))] 
+    SimiScore = [Similarity[rows[i], cols[i]]  for i in range(len(rows))]
+    
+    
+    for i, keykey in enumerate(KeysError):
+        key1, key2 = keykey
+        sscore = SimiScore[i]
+
+        kt1, kt2 = key1.split('_'), key2.split('_')
+        
+        if len(kt1)==3 and len(kt2)==3:
+            file1 = [f for f in ImgFileList if kt1[0] in f and kt1[1] in f and kt1[2][:3] in f]   
+            file2 = [f for f in ImgFileList if kt2[0] in f and kt2[1] in f and kt2[2][:3] in f]
+        
+        elif len(kt1)==4 and len(kt1)==4:
+            file1 = [f for f in ImgFileList if kt1[0] in f and kt1[1] in f and kt1[2] in f and kt1[3][:3] in f]
+            file2 = [f for f in ImgFileList if kt2[0] in f and kt2[1] in f and kt2[2] in f and kt2[3][:3] in f]
+        else:
+            pass
+        
+        if len(file1)==0 or len(file2)==0:
+            continue
+        
+        if kt1[0] == kt2[0]:
+            gt = "same"
+        else:
+            gt = "diff"
+        
+        path = Path(f'./matching/results/{i}_{gt}_{sscore:.2f}')
+        if path.exists() and path.is_dir():
+            shutil.rmtree(path)
+        path1, path2 = path.joinpath(key1), path.joinpath(key2)
+        
+        path1.mkdir(parents=True, exist_ok=True)
+        path2.mkdir(parents=True, exist_ok=True)
+        for file in file1:
+            shutil.copy2(file, path1)
+        for file in file2:
+            shutil.copy2(file, path2)
+        
+        if i==99:
+            break
+
+    th1, corr = [c[0] for c in Correct], [c[1] for c in Correct]
+    th2, recl = [c[0] for c in Recall], [c[1] for c in Recall]
+    th3, prep = [c[0] for c in PrecisePos], [c[1] for c in PrecisePos]
+    th4, pren = [c[0] for c in PreciseNeg], [c[1] for c in PreciseNeg]
+    
+    '''================= Correct ==================='''
+    fig, ax = plt.subplots()
+    ax.plot(th1, corr, 'b', label='Correct = (TP+TN)/(TP+TN+FP+FN)')
+    max_corr = max(corr)
+    max_index = corr.index(max_corr)
+    max_thresh = th1[max_index]
+    ax.plot([0, max_thresh], [max_corr, max_corr], 'r--')
+    ax.plot([max_thresh, max_thresh], [0, max_corr], 'r--')
+    ax.set_xlim([0, 1])
+    ax.set_ylim([0, 1])
+    ax.grid(True)
+    ax.set_title('Correct')
+    ax.legend()
+    plt.show()
+    
+    
+    '''================= PrecisePos & PreciseNeg & Recall ================='''
+    fig, ax = plt.subplots()
+    ax.plot(th2, recl, 'g', label='Recall = TP/(TP+FN)')
+    ax.plot(th3, prep, 'c', label='PrecisePos = TP/(TP+FP)')
+    ax.plot(th4, pren, 'm', label='PreciseNeg = TN/(TN+FN)')
+    
+    ax.set_xlim([0, 1])
+    ax.set_ylim([0, 1])
+    ax.grid(True)
+    ax.set_title('PrecisePos & PreciseNeg')     
+    ax.legend()
+    plt.show()            
+    
+
+def have_tracked():   
+    featdir = r"./data/trackfeats"
+    trackdir = r"./data/tracks"
+    
+# =============================================================================
+#     FileList = []
+#     with open(r'./matching/视频分类/单.txt', 'r') as file:
+#         lines = file.readlines()
+#         for line in lines:
+#             file = line.split('.')[0]
+#             FileList.append(file)
+#     FileList = list(set(FileList))
+# =============================================================================
+    
+    MatchingDict = {}
+    k, gt = 0, Profile()
+    for filename in os.listdir(featdir):
+        file, ext = os.path.splitext(filename)
+        
+        # if file not in FileList: continue
+        if file.find('20240508')<0: continue
+        if file.find('17327712807')<0: continue
+    
+        trackpath = os.path.join(trackdir, file + ".npy")
+        featpath = os.path.join(featdir, filename)
+        
+        bboxes = np.load(trackpath)
+        features_dict = np.load(featpath, allow_pickle=True)
+        with gt:
+            if filename.find("front") >= 0:
+                vts = doFrontTracks(bboxes, features_dict)
+                vts.classify()
+                
+                plt = plot_frameID_y2(vts)
+                
+                savedir = save_dir.joinpath(f'{file}_y2.png') 
+                
+                plt.savefig(savedir)  
+                plt.close()
+            elif filename.find("back") >= 0:
+                vts = doBackTracks(bboxes, features_dict)
+                vts.classify()
+                
+                edgeline = cv2.imread("./shopcart/cart_tempt/edgeline.png")
+                draw_all_trajectories(vts, edgeline, save_dir, filename)
+        print(file+f" need time: {gt.dt:.2f}s")
+        
+        elements = file.split('_')
+        assert len(elements) == 7, f"{filename} fields num: {len(elements)}"
+        BarCode = elements[0]
+        
+        ## ====================================== 只用于在images文件夹下保存图片
+        SampleTime = elements[1].split('-')[1]
+        CameraType = elements[2]
+        if elements[3]=="addGood":
+            ActionType = "add"
+        elif elements[3]=="returnGood":
+            ActionType = "return"
+        else:
+            ActionType = "x"
+        
+        subimg_dir = Path(f'./matching/images/{BarCode}_{SampleTime}_{ActionType}/')
+        if not subimg_dir.exists():
+            subimg_dir.mkdir(parents=True, exist_ok=True)
+        
+        # boxes: [x1, y1, x2, y2, track_id, score, cls, frame_index, box_index]
+        #         0,  1,  2,  3,    4,        5,    6,      7,         8 
+        for track in vts.Residual:
+            boxes = track.boxes
+            for i in range(boxes.shape[0]):
+                box = boxes[i, :]
+                tid, fid, bid = int(box[4]), int(box[7]), int(box[8])
+                
+                feat_dict = features_dict[fid]
+                feature = feat_dict[bid]
+                img = feat_dict[f'{bid}_img']
+                
+                sub_img_file = subimg_dir.joinpath(f"{BarCode}_{SampleTime}_{CameraType}_{ActionType}_{tid}_{fid}_{bid}.png")
+                cv2.imwrite(str(sub_img_file), img)
+
+                condict = {f"{file}_{tid}_{fid}_{bid}": {'img': img, 'feature': feature}}
+                
+                MatchingDict.update(condict)
+        # k += 1
+        # if k == 100:
+        #     break
+                
+    featpath = Path('./matching/featdata/')
+    if not featpath.exists():
+        featpath.mkdir(parents=True, exist_ok=True)
+    
+    featdata = featpath.joinpath('imgs_feats_data_noplane.pkl')
+    with open(featdata, 'wb') as file:
+        pickle.dump(MatchingDict, file)
+
+def imgsample_cleaning():
+    ContrastDict = np.load('./matching/featdata/imgs_feats_data.pkl', allow_pickle=True)
+    print(f"The Num of imgsample: {len(ContrastDict)}")
+    
+    
+    MatchingDict_refined = {}
+    for filename, value in ContrastDict.items():
+        elements = filename.split('_')
+        
+          
+        tid = elements[7]
+        fid = elements[8]
+        bid = elements[9]
+        
+        BarCode = elements[0]
+        SampleTime = elements[1].split('-')[1]
+        CameraType = elements[2]
+        if elements[3]=="addGood":
+            ActionType = "add"
+        elif elements[3]=="returnGood":
+            ActionType = "return"
+        else:
+            ActionType = "x"
+        refimgdir = f'.\matching\images_refined\{BarCode}_{SampleTime}_{ActionType}'
+        
+        file = '_'.join(elements[0:7]) 
+        if os.path.exists(refimgdir) and os.path.isdir(refimgdir):
+            imgpath = os.path.join(refimgdir, f"{BarCode}_{SampleTime}_{CameraType}_{ActionType}_{tid}_{fid}_{bid}.png")
+            if os.path.isfile(imgpath):
+                condict = {f"{file}_{tid}_{fid}_{bid}": value}
+                
+                MatchingDict_refined.update(condict)
+                
+    featpath = Path('./matching/featdata/')
+    if not featpath.exists():
+        featpath.mkdir(parents=True, exist_ok=True)
+    
+    featdata = featpath.joinpath('imgs_feats_data_refined.pkl')
+    with open(featdata, 'wb') as file:
+        pickle.dump(MatchingDict_refined, file)   
+        
+        print(f"The Num of ContrastDict: {len(ContrastDict)}")
+        print(f"The Num of MatchingDict_refined: {len(MatchingDict_refined)}")
+        print(f"The Num of cleaned img: {len(ContrastDict)} - {len(MatchingDict_refined)}")
+        
+
+def main():
+    '''1. 提取运动商品轨迹'''
+    # have_tracked()
+    
+    '''2. 清除一次事件中包含多件商品的事件'''
+    # imgsample_cleaning()
+    
+    '''3.1 计算事件间相似度: 将 front、back 的所有 track 特征合并'''
+    # calculate_similarity()
+    
+    '''3.2 计算事件间相似度: 考虑前后摄的不同组合，或 track 间的不同组合'''
+    # calculate_similarity_track()
+    
+    
+    '''4.1 事件间匹配的总体性能评估'''
+    filename = r'./matching/featdata/MatchDict_plane.pkl'
+    match_evaluate(filename)
+    
+    filename = r'./matching/featdata/MatchDict_noplane.pkl'
+    match_evaluate(filename)
+    
+    '''4.2 模拟实际场景，任选N件作为一组作为加购，取出其中一件时的性能评估'''
+    # filename = r'./matching/featdata/MatchDict_refined.pkl'
+    # sortN_matching(filename)
+    
+               
+if __name__ == "__main__":
+    save_dir = Path(f'./result/') 
+    main()
+
+
+                

tracking/matching/视频分类/单.txt

@@ -0,0 +1,807 @@
+230537101280010007_20240411-144918_back_addGood_70f75407b7ae_570_17788571404.mp4
+230537101280010007_20240411-144918_front_addGood_70f75407b7ae_570_17788571404.mp4
+230537101280010007_20240411-144945_back_returnGood_70f75407b7ae_565_17788571404.mp4
+230537101280010007_20240411-144945_front_returnGood_70f75407b7ae_565_17788571404.mp4
+230538001280010009_20240411-144924_back_addGood_70f754088050_550_17327712807.mp4
+230538001280010009_20240411-144924_front_addGood_70f754088050_550_17327712807.mp4
+230538001280010009_20240411-144934_back_returnGood_70f754088050_550_17327712807.mp4
+230538001280010009_20240411-144934_front_returnGood_70f754088050_550_17327712807.mp4
+2500456001326_20240411-145321_back_addGood_70f75407b7ae_155_17788571404.mp4
+2500456001326_20240411-145321_front_addGood_70f75407b7ae_155_17788571404.mp4
+2500456001326_20240411-145327_back_returnGood_70f75407b7ae_155_17788571404.mp4
+2500456001326_20240411-145327_front_returnGood_70f75407b7ae_155_17788571404.mp4
+2500456001326_20240411-145330_back_addGood_70f754088050_155_17327712807.mp4
+2500456001326_20240411-145330_front_addGood_70f754088050_155_17327712807.mp4
+2500456001326_20240411-145338_back_returnGood_70f754088050_155_17327712807.mp4
+2500456001326_20240411-145338_front_returnGood_70f754088050_155_17327712807.mp4
+2500458675341_20240411-144658_back_addGood_70f75407b7ae_140_17788571404.mp4
+2500458675341_20240411-144658_front_addGood_70f75407b7ae_140_17788571404.mp4
+2500458675341_20240411-144707_back_returnGood_70f75407b7ae_140_17788571404.mp4
+2500458675341_20240411-144707_front_returnGood_70f75407b7ae_140_17788571404.mp4
+2500458675341_20240411-144711_back_addGood_70f754088050_135_17327712807.mp4
+2500458675341_20240411-144711_front_addGood_70f754088050_135_17327712807.mp4
+2500458675341_20240411-144718_back_returnGood_70f754088050_135_17327712807.mp4
+2500458675341_20240411-144718_front_returnGood_70f754088050_135_17327712807.mp4
+2500463464671_20240411-145041_back_addGood_70f75407b7ae_805_17788571404.mp4
+2500463464671_20240411-145041_front_addGood_70f75407b7ae_805_17788571404.mp4
+2500463464671_20240411-145042_back_addGood_70f754088050_815_17327712807.mp4
+2500463464671_20240411-145042_front_addGood_70f754088050_815_17327712807.mp4
+2500463464671_20240411-145049_back_returnGood_70f754088050_815_17327712807.mp4
+2500463464671_20240411-145049_front_returnGood_70f754088050_815_17327712807.mp4
+2500463464671_20240411-145053_back_returnGood_70f75407b7ae_810_17788571404.mp4
+2500463464671_20240411-145053_front_returnGood_70f75407b7ae_810_17788571404.mp4
+6901070613142_20240411-142722_back_addGood_70f754088050_240_17327712807.mp4
+6901070613142_20240411-142722_front_addGood_70f754088050_240_17327712807.mp4
+6901070613142_20240411-142725_back_addGood_70f75407b7ae_240_17788571404.mp4
+6901070613142_20240411-142725_front_addGood_70f75407b7ae_240_17788571404.mp4
+6901070613142_20240411-142730_back_returnGood_70f754088050_240_17327712807.mp4
+6901070613142_20240411-142730_front_returnGood_70f754088050_240_17327712807.mp4
+6901070613142_20240411-142734_back_returnGood_70f75407b7ae_240_17788571404.mp4
+6901070613142_20240411-142734_front_returnGood_70f75407b7ae_240_17788571404.mp4
+6901668053893_20240411-143608_back_addGood_70f75407b7ae_70_17788571404.mp4
+6901668053893_20240411-143608_back_addGood_70f754088050_70_17327712807.mp4
+6901668053893_20240411-143608_front_addGood_70f75407b7ae_70_17788571404.mp4
+6901668053893_20240411-143608_front_addGood_70f754088050_70_17327712807.mp4
+6901668053893_20240411-143616_back_returnGood_70f754088050_70_17327712807.mp4
+6901668053893_20240411-143616_front_returnGood_70f754088050_70_17327712807.mp4
+6901668053893_20240411-143617_back_returnGood_70f75407b7ae_70_17788571404.mp4
+6901668053893_20240411-143617_front_returnGood_70f75407b7ae_70_17788571404.mp4
+6902007010249_20240411-142528_back_addGood_70f75407b7ae_755_17788571404.mp4
+6902007010249_20240411-142528_back_addGood_70f754088050_755_17327712807.mp4
+6902007010249_20240411-142528_front_addGood_70f75407b7ae_755_17788571404.mp4
+6902007010249_20240411-142528_front_addGood_70f754088050_755_17327712807.mp4
+6902007010249_20240411-142535_back_returnGood_70f75407b7ae_755_17788571404.mp4
+6902007010249_20240411-142535_front_returnGood_70f75407b7ae_755_17788571404.mp4
+6902007010249_20240411-142541_back_returnGood_70f754088050_755_17327712807.mp4
+6902007010249_20240411-142541_front_returnGood_70f754088050_755_17327712807.mp4
+6902022135514_20240411-142819_back_addGood_70f75407b7ae_3180_17788571404.mp4
+6902022135514_20240411-142819_front_addGood_70f75407b7ae_3180_17788571404.mp4
+6902022135514_20240411-142828_back_addGood_70f754088050_3185_17327712807.mp4
+6902022135514_20240411-142828_front_addGood_70f754088050_3185_17327712807.mp4
+6902022135514_20240411-142830_back_returnGood_70f75407b7ae_3180_17788571404.mp4
+6902022135514_20240411-142830_front_returnGood_70f75407b7ae_3180_17788571404.mp4
+6902022135514_20240411-142840_back_returnGood_70f754088050_3185_17327712807.mp4
+6902022135514_20240411-142840_front_returnGood_70f754088050_3185_17327712807.mp4
+6902265114369_20240411-142331_back_addGood_70f75407b7ae_715_17788571404.mp4
+6902265114369_20240411-142331_front_addGood_70f75407b7ae_715_17788571404.mp4
+6902265114369_20240411-142338_back_returnGood_70f75407b7ae_720_17788571404.mp4
+6902265114369_20240411-142338_front_returnGood_70f75407b7ae_720_17788571404.mp4
+6902265114369_20240411-142355_back_addGood_70f754088050_720_17327712807.mp4
+6902265114369_20240411-142355_front_addGood_70f754088050_720_17327712807.mp4
+6902265114369_20240411-142403_back_returnGood_70f754088050_715_17327712807.mp4
+6902265114369_20240411-142403_front_returnGood_70f754088050_715_17327712807.mp4
+6902265908012_20240411-142446_back_addGood_70f75407b7ae_1150_17788571404.mp4
+6902265908012_20240411-142446_front_addGood_70f75407b7ae_1150_17788571404.mp4
+6902265908012_20240411-142447_back_addGood_70f754088050_1150_17327712807.mp4
+6902265908012_20240411-142447_front_addGood_70f754088050_1150_17327712807.mp4
+6902265908012_20240411-142456_back_returnGood_70f75407b7ae_1150_17788571404.mp4
+6902265908012_20240411-142456_front_returnGood_70f75407b7ae_1150_17788571404.mp4
+6902265908012_20240411-142459_back_returnGood_70f754088050_1150_17327712807.mp4
+6902265908012_20240411-142459_front_returnGood_70f754088050_1150_17327712807.mp4
+69025143_20240411-163325_back_addGood_70f75407b7ae_3385_17788571404.mp4
+69025143_20240411-163325_front_addGood_70f75407b7ae_3385_17788571404.mp4
+69025143_20240411-163352_back_returnGood_70f75407b7ae_3390_17788571404.mp4
+69025143_20240411-163352_front_returnGood_70f75407b7ae_3390_17788571404.mp4
+69025143_20240411-163417_back_addGood_70f754088050_3380_17327712807.mp4
+69025143_20240411-163417_front_addGood_70f754088050_3380_17327712807.mp4
+69025143_20240411-163428_back_returnGood_70f754088050_3380_17327712807.mp4
+69025143_20240411-163428_front_returnGood_70f754088050_3380_17327712807.mp4
+6902538007367_20240411-144030_back_addGood_70f754088050_660_17327712807.mp4
+6902538007367_20240411-144030_front_addGood_70f754088050_660_17327712807.mp4
+6902538007367_20240411-144031_back_addGood_70f75407b7ae_660_17788571404.mp4
+6902538007367_20240411-144031_front_addGood_70f75407b7ae_660_17788571404.mp4
+6902538007367_20240411-144037_back_returnGood_70f75407b7ae_660_17788571404.mp4
+6902538007367_20240411-144037_front_returnGood_70f75407b7ae_660_17788571404.mp4
+6902538007367_20240411-144040_back_returnGood_70f754088050_660_17327712807.mp4
+6902538007367_20240411-144040_front_returnGood_70f754088050_660_17327712807.mp4
+69028571_20240411-163728_back_addGood_70f75407b7ae_1845_17788571404.mp4
+69028571_20240411-163728_front_addGood_70f75407b7ae_1845_17788571404.mp4
+69028571_20240411-163739_back_returnGood_70f75407b7ae_1845_17788571404.mp4
+69028571_20240411-163739_front_returnGood_70f75407b7ae_1845_17788571404.mp4
+69028571_20240411-163853_back_addGood_70f754088050_1840_17327712807.mp4
+69028571_20240411-163853_front_addGood_70f754088050_1840_17327712807.mp4
+69028571_20240411-163904_back_returnGood_70f754088050_1840_17327712807.mp4
+69028571_20240411-163904_front_returnGood_70f754088050_1840_17327712807.mp4
+6907992103952_20240411-142013_back_addGood_70f75407b7ae_190_17788571404.mp4
+6907992103952_20240411-142013_front_addGood_70f75407b7ae_190_17788571404.mp4
+6907992103952_20240411-142021_back_returnGood_70f75407b7ae_190_17788571404.mp4
+6907992103952_20240411-142021_front_returnGood_70f75407b7ae_190_17788571404.mp4
+6907992103952_20240411-142029_back_addGood_70f754088050_190_17327712807.mp4
+6907992103952_20240411-142029_front_addGood_70f754088050_190_17327712807.mp4
+6907992103952_20240411-142036_back_returnGood_70f754088050_190_17327712807.mp4
+6907992103952_20240411-142036_front_returnGood_70f754088050_190_17327712807.mp4
+6907992104157_20240411-141633_back_addGood_70f754088050_1120_17327712807.mp4
+6907992104157_20240411-141633_front_addGood_70f754088050_1120_17327712807.mp4
+6907992104157_20240411-141637_back_addGood_70f75407b7ae_1120_17788571404.mp4
+6907992104157_20240411-141637_front_addGood_70f75407b7ae_1120_17788571404.mp4
+6907992104157_20240411-141646_back_returnGood_70f75407b7ae_1120_17788571404.mp4
+6907992104157_20240411-141646_back_returnGood_70f754088050_1120_17327712807.mp4
+6907992104157_20240411-141646_front_returnGood_70f75407b7ae_1120_17788571404.mp4
+6907992104157_20240411-141646_front_returnGood_70f754088050_1120_17327712807.mp4
+6907992105765_20240411-142214_back_addGood_70f754088050_1860_17327712807.mp4
+6907992105765_20240411-142214_front_addGood_70f754088050_1860_17327712807.mp4
+6907992105765_20240411-142220_back_addGood_70f75407b7ae_1855_17788571404.mp4
+6907992105765_20240411-142220_front_addGood_70f75407b7ae_1855_17788571404.mp4
+6907992105765_20240411-142228_back_returnGood_70f754088050_1860_17327712807.mp4
+6907992105765_20240411-142228_front_returnGood_70f754088050_1860_17327712807.mp4
+6907992105765_20240411-142230_back_returnGood_70f75407b7ae_1855_17788571404.mp4
+6907992105765_20240411-142230_front_returnGood_70f75407b7ae_1855_17788571404.mp4
+6907992106113_20240411-142100_back_addGood_70f754088050_3085_17327712807.mp4
+6907992106113_20240411-142100_front_addGood_70f754088050_3085_17327712807.mp4
+6907992106113_20240411-142133_back_returnGood_70f754088050_3085_17327712807.mp4
+6907992106113_20240411-142133_front_returnGood_70f754088050_3085_17327712807.mp4
+6907992106113_20240411-142149_back_addGood_70f75407b7ae_3085_17788571404.mp4
+6907992106113_20240411-142149_front_addGood_70f75407b7ae_3085_17788571404.mp4
+6907992106113_20240411-142157_back_returnGood_70f75407b7ae_3080_17788571404.mp4
+6907992106113_20240411-142157_front_returnGood_70f75407b7ae_3080_17788571404.mp4
+6907992106205_20240411-141741_back_addGood_70f75407b7ae_795_17788571404.mp4
+6907992106205_20240411-141741_front_addGood_70f75407b7ae_795_17788571404.mp4
+6907992106205_20240411-141750_back_returnGood_70f75407b7ae_795_17788571404.mp4
+6907992106205_20240411-141750_front_returnGood_70f75407b7ae_795_17788571404.mp4
+6907992106205_20240411-141806_back_addGood_70f754088050_795_17327712807.mp4
+6907992106205_20240411-141806_front_addGood_70f754088050_795_17327712807.mp4
+6907992106205_20240411-141815_back_returnGood_70f754088050_795_17327712807.mp4
+6907992106205_20240411-141815_front_returnGood_70f754088050_795_17327712807.mp4
+6907992106311_20240411-141711_back_addGood_70f754088050_880_17327712807.mp4
+6907992106311_20240411-141711_front_addGood_70f754088050_880_17327712807.mp4
+6907992106311_20240411-141713_back_addGood_70f75407b7ae_885_17788571404.mp4
+6907992106311_20240411-141713_front_addGood_70f75407b7ae_885_17788571404.mp4
+6907992106311_20240411-141721_back_returnGood_70f75407b7ae_885_17788571404.mp4
+6907992106311_20240411-141721_front_returnGood_70f75407b7ae_885_17788571404.mp4
+6907992106311_20240411-141726_back_returnGood_70f754088050_880_17327712807.mp4
+6907992106311_20240411-141726_front_returnGood_70f754088050_880_17327712807.mp4
+6914973602908_20240411-162105_back_returnGood_70f75407b7ae_5_17788571404.mp4
+6914973602908_20240411-162105_front_returnGood_70f75407b7ae_5_17788571404.mp4
+6914973602908_20240411-162113_back_returnGood_70f75407b7ae_740_17788571404.mp4
+6914973602908_20240411-162113_front_returnGood_70f75407b7ae_740_17788571404.mp4
+6914973602908_20240411-162420_back_addGood_70f754088050_740_17327712807.mp4
+6914973602908_20240411-162420_front_addGood_70f754088050_740_17327712807.mp4
+6914973602908_20240411-162434_back_returnGood_70f754088050_740_17327712807.mp4
+6914973602908_20240411-162434_front_returnGood_70f754088050_740_17327712807.mp4
+6914973606340_20240411-161927_back_addGood_70f75407b7ae_350_17788571404.mp4
+6914973606340_20240411-161927_front_addGood_70f75407b7ae_350_17788571404.mp4
+6914973606340_20240411-161936_back_returnGood_70f75407b7ae_355_17788571404.mp4
+6914973606340_20240411-161936_front_returnGood_70f75407b7ae_355_17788571404.mp4
+6914973606340_20240411-162001_back_addGood_70f754088050_5_17327712807.mp4
+6914973606340_20240411-162001_front_addGood_70f754088050_5_17327712807.mp4
+6914973606340_20240411-162009_back_returnGood_70f754088050_355_17327712807.mp4
+6914973606340_20240411-162009_front_returnGood_70f754088050_355_17327712807.mp4
+6920152400630_20240411-144222_back_addGood_70f75407b7ae_580_17788571404.mp4
+6920152400630_20240411-144222_front_addGood_70f75407b7ae_580_17788571404.mp4
+6920152400630_20240411-144223_back_addGood_70f754088050_570_17327712807.mp4
+6920152400630_20240411-144223_front_addGood_70f754088050_570_17327712807.mp4
+6920152400630_20240411-144228_back_returnGood_70f75407b7ae_575_17788571404.mp4
+6920152400630_20240411-144228_front_returnGood_70f75407b7ae_575_17788571404.mp4
+6920152400630_20240411-144236_back_returnGood_70f754088050_570_17327712807.mp4
+6920152400630_20240411-144236_front_returnGood_70f754088050_570_17327712807.mp4
+6920174757101_20240411-143201_back_addGood_70f75407b7ae_1305_17788571404.mp4
+6920174757101_20240411-143201_front_addGood_70f75407b7ae_1305_17788571404.mp4
+6920174757101_20240411-143202_back_addGood_70f754088050_1305_17327712807.mp4
+6920174757101_20240411-143202_front_addGood_70f754088050_1305_17327712807.mp4
+6920174757101_20240411-143208_back_returnGood_70f75407b7ae_1305_17788571404.mp4
+6920174757101_20240411-143208_front_returnGood_70f75407b7ae_1305_17788571404.mp4
+6920174757101_20240411-143211_back_returnGood_70f754088050_1305_17327712807.mp4
+6920174757101_20240411-143211_front_returnGood_70f754088050_1305_17327712807.mp4
+6920459905012_20240411-143922_back_addGood_70f75407b7ae_550_17788571404.mp4
+6920459905012_20240411-143922_front_addGood_70f75407b7ae_550_17788571404.mp4
+6920459905012_20240411-143930_back_returnGood_70f75407b7ae_555_17788571404.mp4
+6920459905012_20240411-143930_front_returnGood_70f75407b7ae_555_17788571404.mp4
+6920459905012_20240411-143947_back_addGood_70f754088050_550_17327712807.mp4
+6920459905012_20240411-143947_front_addGood_70f754088050_550_17327712807.mp4
+6920459905012_20240411-143956_back_returnGood_70f754088050_550_17327712807.mp4
+6920459905012_20240411-143956_front_returnGood_70f754088050_550_17327712807.mp4
+6920907810707_20240411-143338_back_addGood_70f754088050_75_17327712807.mp4
+6920907810707_20240411-143338_front_addGood_70f754088050_75_17327712807.mp4
+6920907810707_20240411-143339_back_addGood_70f75407b7ae_80_17788571404.mp4
+6920907810707_20240411-143339_front_addGood_70f75407b7ae_80_17788571404.mp4
+6920907810707_20240411-143347_back_returnGood_70f754088050_80_17327712807.mp4
+6920907810707_20240411-143347_front_returnGood_70f754088050_80_17327712807.mp4
+6920907810707_20240411-143356_back_returnGood_70f75407b7ae_80_17788571404.mp4
+6920907810707_20240411-143356_front_returnGood_70f75407b7ae_80_17788571404.mp4
+6922130119213_20240411-142631_back_addGood_70f754088050_1020_17327712807.mp4
+6922130119213_20240411-142631_front_addGood_70f754088050_1020_17327712807.mp4
+6922130119213_20240411-142636_back_addGood_70f75407b7ae_1020_17788571404.mp4
+6922130119213_20240411-142636_front_addGood_70f75407b7ae_1020_17788571404.mp4
+6922130119213_20240411-142641_back_returnGood_70f754088050_1020_17327712807.mp4
+6922130119213_20240411-142641_front_returnGood_70f754088050_1020_17327712807.mp4
+6922130119213_20240411-142647_back_returnGood_70f75407b7ae_1020_17788571404.mp4
+6922130119213_20240411-142647_front_returnGood_70f75407b7ae_1020_17788571404.mp4
+6922577700968_20240411-141822_back_addGood_70f75407b7ae_1040_17788571404.mp4
+6922577700968_20240411-141822_front_addGood_70f75407b7ae_1040_17788571404.mp4
+6922577700968_20240411-141834_back_addGood_70f754088050_1045_17327712807.mp4
+6922577700968_20240411-141834_front_addGood_70f754088050_1045_17327712807.mp4
+6922577700968_20240411-141839_back_returnGood_70f75407b7ae_1045_17788571404.mp4
+6922577700968_20240411-141839_front_returnGood_70f75407b7ae_1045_17788571404.mp4
+6922577700968_20240411-141844_back_returnGood_70f754088050_1045_17327712807.mp4
+6922577700968_20240411-141844_front_returnGood_70f754088050_1045_17327712807.mp4
+6922868291168_20240411-142913_back_addGood_70f754088050_1160_17327712807.mp4
+6922868291168_20240411-142913_front_addGood_70f754088050_1160_17327712807.mp4
+6922868291168_20240411-142921_back_addGood_70f75407b7ae_1150_17788571404.mp4
+6922868291168_20240411-142921_front_addGood_70f75407b7ae_1150_17788571404.mp4
+6922868291168_20240411-142929_back_returnGood_70f754088050_1160_17327712807.mp4
+6922868291168_20240411-142929_front_returnGood_70f754088050_1160_17327712807.mp4
+6922868291168_20240411-142933_back_returnGood_70f75407b7ae_1155_17788571404.mp4
+6922868291168_20240411-142933_front_returnGood_70f75407b7ae_1155_17788571404.mp4
+6923450601549_20240411-162014_back_addGood_70f75407b7ae_600_17788571404.mp4
+6923450601549_20240411-162014_front_addGood_70f75407b7ae_600_17788571404.mp4
+6923450601549_20240411-162024_back_returnGood_70f75407b7ae_600_17788571404.mp4
+6923450601549_20240411-162024_front_returnGood_70f75407b7ae_600_17788571404.mp4
+6923450601549_20240411-162216_back_addGood_70f754088050_595_17327712807.mp4
+6923450601549_20240411-162216_front_addGood_70f754088050_595_17327712807.mp4
+6923450601549_20240411-162227_back_returnGood_70f754088050_595_17327712807.mp4
+6923450601549_20240411-162227_front_returnGood_70f754088050_595_17327712807.mp4
+6923450603574_20240411-163042_back_addGood_70f75407b7ae_870_17788571404.mp4
+6923450603574_20240411-163042_front_addGood_70f75407b7ae_870_17788571404.mp4
+6923450603574_20240411-163049_back_returnGood_70f75407b7ae_870_17788571404.mp4
+6923450603574_20240411-163049_front_returnGood_70f75407b7ae_870_17788571404.mp4
+6923450603574_20240411-163104_back_addGood_70f754088050_865_17327712807.mp4
+6923450603574_20240411-163104_front_addGood_70f754088050_865_17327712807.mp4
+6923450603574_20240411-163114_back_returnGood_70f754088050_865_17327712807.mp4
+6923450603574_20240411-163114_front_returnGood_70f754088050_865_17327712807.mp4
+6923450605288_20240411-161704_back_addGood_70f75407b7ae_250_17788571404.mp4
+6923450605288_20240411-161704_front_addGood_70f75407b7ae_250_17788571404.mp4
+6923450605288_20240411-161715_back_returnGood_70f75407b7ae_250_17788571404.mp4
+6923450605288_20240411-161715_front_returnGood_70f75407b7ae_250_17788571404.mp4
+6923450605288_20240411-161748_back_addGood_70f754088050_245_17327712807.mp4
+6923450605288_20240411-161748_front_addGood_70f754088050_245_17327712807.mp4
+6923450605288_20240411-161800_back_returnGood_70f754088050_245_17327712807.mp4
+6923450605288_20240411-161800_front_returnGood_70f754088050_245_17327712807.mp4
+6923450610428_20240411-161209_back_addGood_70f75407b7ae_275_17788571404.mp4
+6923450610428_20240411-161209_front_addGood_70f75407b7ae_275_17788571404.mp4
+6923450610428_20240411-161217_back_returnGood_70f75407b7ae_275_17788571404.mp4
+6923450610428_20240411-161217_front_returnGood_70f75407b7ae_275_17788571404.mp4
+6923450610428_20240411-161235_back_addGood_70f754088050_270_17327712807.mp4
+6923450610428_20240411-161235_front_addGood_70f754088050_270_17327712807.mp4
+6923450610428_20240411-161249_back_returnGood_70f754088050_275_17327712807.mp4
+6923450610428_20240411-161249_front_returnGood_70f754088050_275_17327712807.mp4
+6923450610459_20240411-162814_back_addGood_70f75407b7ae_445_17788571404.mp4
+6923450610459_20240411-162814_front_addGood_70f75407b7ae_445_17788571404.mp4
+6923450610459_20240411-162822_back_returnGood_70f75407b7ae_450_17788571404.mp4
+6923450610459_20240411-162822_front_returnGood_70f75407b7ae_450_17788571404.mp4
+6923450610459_20240411-162854_back_addGood_70f754088050_445_17327712807.mp4
+6923450610459_20240411-162854_front_addGood_70f754088050_445_17327712807.mp4
+6923450610459_20240411-162906_back_returnGood_70f754088050_445_17327712807.mp4
+6923450610459_20240411-162906_front_returnGood_70f754088050_445_17327712807.mp4
+6923450611067_20240411-162639_back_addGood_70f75407b7ae_625_17788571404.mp4
+6923450611067_20240411-162639_front_addGood_70f75407b7ae_625_17788571404.mp4
+6923450611067_20240411-162648_back_returnGood_70f75407b7ae_625_17788571404.mp4
+6923450611067_20240411-162648_front_returnGood_70f75407b7ae_625_17788571404.mp4
+6923450611067_20240411-162752_back_addGood_70f754088050_620_17327712807.mp4
+6923450611067_20240411-162752_front_addGood_70f754088050_620_17327712807.mp4
+6923450611067_20240411-162808_back_returnGood_70f754088050_625_17327712807.mp4
+6923450611067_20240411-162808_front_returnGood_70f754088050_625_17327712807.mp4
+6923450612415_20240411-160636_back_addGood_70f75407b7ae_870_17788571404.mp4
+6923450612415_20240411-160636_front_addGood_70f75407b7ae_870_17788571404.mp4
+6923450612415_20240411-160724_back_addGood_70f754088050_865_17327712807.mp4
+6923450612415_20240411-160724_front_addGood_70f754088050_865_17327712807.mp4
+6923450612415_20240411-160735_back_returnGood_70f754088050_865_17327712807.mp4
+6923450612415_20240411-160735_front_returnGood_70f754088050_865_17327712807.mp4
+6923450612415_20240411-161013_back_returnGood_70f75407b7ae_865_17788571404.mp4
+6923450612415_20240411-161013_front_returnGood_70f75407b7ae_865_17788571404.mp4
+6923450612484_20240411-161509_back_addGood_70f75407b7ae_445_17788571404.mp4
+6923450612484_20240411-161509_front_addGood_70f75407b7ae_445_17788571404.mp4
+6923450612484_20240411-161517_back_returnGood_70f75407b7ae_445_17788571404.mp4
+6923450612484_20240411-161517_front_returnGood_70f75407b7ae_445_17788571404.mp4
+6923450612484_20240411-161535_back_addGood_70f754088050_450_17327712807.mp4
+6923450612484_20240411-161535_front_addGood_70f754088050_450_17327712807.mp4
+6923450612484_20240411-161546_back_returnGood_70f754088050_450_17327712807.mp4
+6923450612484_20240411-161546_front_returnGood_70f754088050_450_17327712807.mp4
+6923450657829_20240411-163522_back_addGood_70f75407b7ae_985_17788571404.mp4
+6923450657829_20240411-163522_front_addGood_70f75407b7ae_985_17788571404.mp4
+6923450657829_20240411-163532_back_returnGood_70f75407b7ae_985_17788571404.mp4
+6923450657829_20240411-163532_front_returnGood_70f75407b7ae_985_17788571404.mp4
+6923450657829_20240411-163554_back_addGood_70f754088050_990_17327712807.mp4
+6923450657829_20240411-163554_front_addGood_70f754088050_990_17327712807.mp4
+6923450657829_20240411-163606_back_returnGood_70f754088050_990_17327712807.mp4
+6923450657829_20240411-163606_front_returnGood_70f754088050_990_17327712807.mp4
+6923450659441_20240411-163152_back_addGood_70f75407b7ae_1695_17788571404.mp4
+6923450659441_20240411-163152_front_addGood_70f75407b7ae_1695_17788571404.mp4
+6923450659441_20240411-163204_back_returnGood_70f75407b7ae_1695_17788571404.mp4
+6923450659441_20240411-163204_front_returnGood_70f75407b7ae_1695_17788571404.mp4
+6923450659441_20240411-163217_back_addGood_70f754088050_1690_17327712807.mp4
+6923450659441_20240411-163217_front_addGood_70f754088050_1690_17327712807.mp4
+6923450659441_20240411-163231_back_returnGood_70f754088050_1690_17327712807.mp4
+6923450659441_20240411-163231_front_returnGood_70f754088050_1690_17327712807.mp4
+6923450666838_20240411-162541_back_addGood_70f75407b7ae_285_17788571404.mp4
+6923450666838_20240411-162541_front_addGood_70f75407b7ae_285_17788571404.mp4
+6923450666838_20240411-162549_back_returnGood_70f75407b7ae_285_17788571404.mp4
+6923450666838_20240411-162549_front_returnGood_70f75407b7ae_285_17788571404.mp4
+6923450666838_20240411-162637_back_addGood_70f754088050_285_17327712807.mp4
+6923450666838_20240411-162637_front_addGood_70f754088050_285_17327712807.mp4
+6923450666838_20240411-162704_back_returnGood_70f754088050_285_17327712807.mp4
+6923450666838_20240411-162704_front_returnGood_70f754088050_285_17327712807.mp4
+6923450668207_20240411-161832_back_addGood_70f75407b7ae_350_17788571404.mp4
+6923450668207_20240411-161832_front_addGood_70f75407b7ae_350_17788571404.mp4
+6923450668207_20240411-161839_back_returnGood_70f75407b7ae_350_17788571404.mp4
+6923450668207_20240411-161839_front_returnGood_70f75407b7ae_350_17788571404.mp4
+6923450668207_20240411-161904_back_addGood_70f754088050_350_17327712807.mp4
+6923450668207_20240411-161904_front_addGood_70f754088050_350_17327712807.mp4
+6923450668207_20240411-161913_back_returnGood_70f754088050_355_17327712807.mp4
+6923450668207_20240411-161913_front_returnGood_70f754088050_355_17327712807.mp4
+6923450677858_20240411-163609_back_addGood_70f75407b7ae_5_17788571404.mp4
+6923450677858_20240411-163609_front_addGood_70f75407b7ae_5_17788571404.mp4
+6923450677858_20240411-163618_back_returnGood_70f75407b7ae_1020_17788571404.mp4
+6923450677858_20240411-163618_front_returnGood_70f75407b7ae_1020_17788571404.mp4
+6923450677858_20240411-163726_back_addGood_70f754088050_1025_17327712807.mp4
+6923450677858_20240411-163726_front_addGood_70f754088050_1025_17327712807.mp4
+6923450677858_20240411-163737_back_returnGood_70f754088050_1025_17327712807.mp4
+6923450677858_20240411-163737_front_returnGood_70f754088050_1025_17327712807.mp4
+6923644286293_20240411-141557_back_addGood_70f754088050_795_17327712807.mp4
+6923644286293_20240411-141557_front_addGood_70f754088050_795_17327712807.mp4
+6923644286293_20240411-141601_back_addGood_70f75407b7ae_800_17788571404.mp4
+6923644286293_20240411-141601_front_addGood_70f75407b7ae_800_17788571404.mp4
+6923644286293_20240411-141605_back_returnGood_70f754088050_795_17327712807.mp4
+6923644286293_20240411-141605_front_returnGood_70f754088050_795_17327712807.mp4
+6923644286293_20240411-141609_back_returnGood_70f75407b7ae_800_17788571404.mp4
+6923644286293_20240411-141609_front_returnGood_70f75407b7ae_800_17788571404.mp4
+6923644298760_20240411-141459_back_addGood_70f75407b7ae_1020_17788571404.mp4
+6923644298760_20240411-141459_front_addGood_70f75407b7ae_1020_17788571404.mp4
+6923644298760_20240411-141500_back_addGood_70f754088050_1020_17327712807.mp4
+6923644298760_20240411-141500_front_addGood_70f754088050_1020_17327712807.mp4
+6923644298760_20240411-141511_back_returnGood_70f754088050_1020_17327712807.mp4
+6923644298760_20240411-141511_front_returnGood_70f754088050_1020_17327712807.mp4
+6923644298760_20240411-141516_back_returnGood_70f75407b7ae_1020_17788571404.mp4
+6923644298760_20240411-141516_front_returnGood_70f75407b7ae_1020_17788571404.mp4
+6924743915824_20240411-143302_back_addGood_70f75407b7ae_150_17788571404.mp4
+6924743915824_20240411-143302_back_addGood_70f754088050_150_17327712807.mp4
+6924743915824_20240411-143302_front_addGood_70f75407b7ae_150_17788571404.mp4
+6924743915824_20240411-143302_front_addGood_70f754088050_150_17327712807.mp4
+6924743915824_20240411-143310_back_returnGood_70f75407b7ae_155_17788571404.mp4
+6924743915824_20240411-143310_back_returnGood_70f754088050_150_17327712807.mp4
+6924743915824_20240411-143310_front_returnGood_70f75407b7ae_155_17788571404.mp4
+6924743915824_20240411-143310_front_returnGood_70f754088050_150_17327712807.mp4
+6924882497106_20240411-143858_back_addGood_70f75407b7ae_360_17788571404.mp4
+6924882497106_20240411-143858_front_addGood_70f75407b7ae_360_17788571404.mp4
+6924882497106_20240411-143904_back_returnGood_70f75407b7ae_360_17788571404.mp4
+6924882497106_20240411-143904_front_returnGood_70f75407b7ae_360_17788571404.mp4
+6924882497106_20240411-143915_back_addGood_70f754088050_355_17327712807.mp4
+6924882497106_20240411-143915_front_addGood_70f754088050_355_17327712807.mp4
+6924882497106_20240411-143924_back_returnGood_70f754088050_355_17327712807.mp4
+6924882497106_20240411-143924_front_returnGood_70f754088050_355_17327712807.mp4
+6925307305525_20240411-141034_back_addGood_70f75407b7ae_1670_17788571404.mp4
+6925307305525_20240411-141034_front_addGood_70f75407b7ae_1670_17788571404.mp4
+6925307305525_20240411-141044_back_returnGood_70f75407b7ae_1670_17788571404.mp4
+6925307305525_20240411-141044_front_returnGood_70f75407b7ae_1670_17788571404.mp4
+6925307305525_20240411-141055_back_addGood_70f754088050_1670_17327712807.mp4
+6925307305525_20240411-141055_front_addGood_70f754088050_1670_17327712807.mp4
+6925307305525_20240411-141106_back_returnGood_70f754088050_1670_17327712807.mp4
+6925307305525_20240411-141106_front_returnGood_70f754088050_1670_17327712807.mp4
+6928804011173_20240411-143817_back_addGood_70f75407b7ae_555_17788571404.mp4
+6928804011173_20240411-143817_front_addGood_70f75407b7ae_555_17788571404.mp4
+6928804011173_20240411-143825_back_returnGood_70f75407b7ae_550_17788571404.mp4
+6928804011173_20240411-143825_front_returnGood_70f75407b7ae_550_17788571404.mp4
+6928804011173_20240411-143833_back_addGood_70f754088050_545_17327712807.mp4
+6928804011173_20240411-143833_front_addGood_70f754088050_545_17327712807.mp4
+6928804011173_20240411-143841_back_returnGood_70f754088050_550_17327712807.mp4
+6928804011173_20240411-143841_front_returnGood_70f754088050_550_17327712807.mp4
+6931925828032_20240411-162501_back_addGood_70f75407b7ae_405_17788571404.mp4
+6931925828032_20240411-162501_front_addGood_70f75407b7ae_405_17788571404.mp4
+6931925828032_20240411-162511_back_returnGood_70f75407b7ae_405_17788571404.mp4
+6931925828032_20240411-162511_front_returnGood_70f75407b7ae_405_17788571404.mp4
+6931925828032_20240411-162532_back_addGood_70f754088050_405_17327712807.mp4
+6931925828032_20240411-162532_front_addGood_70f754088050_405_17327712807.mp4
+6931925828032_20240411-162540_back_returnGood_70f754088050_405_17327712807.mp4
+6931925828032_20240411-162540_front_returnGood_70f754088050_405_17327712807.mp4
+6933620900051_20240411-150018_back_addGood_70f75407b7ae_5_17788571404.mp4
+6933620900051_20240411-150018_front_addGood_70f75407b7ae_5_17788571404.mp4
+6933620900051_20240411-150035_back_returnGood_70f75407b7ae_380_17788571404.mp4
+6933620900051_20240411-150035_front_returnGood_70f75407b7ae_380_17788571404.mp4
+6933620900051_20240411-150103_back_addGood_70f754088050_455_17327712807.mp4
+6933620900051_20240411-150103_front_addGood_70f754088050_455_17327712807.mp4
+6933620900051_20240411-150116_back_returnGood_70f754088050_455_17327712807.mp4
+6933620900051_20240411-150116_front_returnGood_70f754088050_455_17327712807.mp4
+6934665095108_20240411-141931_back_addGood_70f754088050_360_17327712807.mp4
+6934665095108_20240411-141931_front_addGood_70f754088050_360_17327712807.mp4
+6934665095108_20240411-141936_back_addGood_70f75407b7ae_360_17788571404.mp4
+6934665095108_20240411-141936_front_addGood_70f75407b7ae_360_17788571404.mp4
+6934665095108_20240411-141940_back_returnGood_70f754088050_365_17327712807.mp4
+6934665095108_20240411-141940_front_returnGood_70f754088050_365_17327712807.mp4
+6934665095108_20240411-141945_back_returnGood_70f75407b7ae_360_17788571404.mp4
+6934665095108_20240411-141945_front_returnGood_70f75407b7ae_360_17788571404.mp4
+6935270642121_20240411-144253_back_addGood_70f75407b7ae_155_17788571404.mp4
+6935270642121_20240411-144253_front_addGood_70f75407b7ae_155_17788571404.mp4
+6935270642121_20240411-144255_back_addGood_70f754088050_155_17327712807.mp4
+6935270642121_20240411-144255_front_addGood_70f754088050_155_17327712807.mp4
+6935270642121_20240411-144300_back_returnGood_70f75407b7ae_155_17788571404.mp4
+6935270642121_20240411-144300_front_returnGood_70f75407b7ae_155_17788571404.mp4
+6935270642121_20240411-144304_back_returnGood_70f754088050_155_17327712807.mp4
+6935270642121_20240411-144304_front_returnGood_70f754088050_155_17327712807.mp4
+6935284417326_20240411-143504_back_addGood_70f754088050_420_17327712807.mp4
+6935284417326_20240411-143504_front_addGood_70f754088050_420_17327712807.mp4
+6935284417326_20240411-143508_back_addGood_70f75407b7ae_415_17788571404.mp4
+6935284417326_20240411-143508_front_addGood_70f75407b7ae_415_17788571404.mp4
+6935284417326_20240411-143517_back_returnGood_70f754088050_420_17327712807.mp4
+6935284417326_20240411-143517_front_returnGood_70f754088050_420_17327712807.mp4
+6935284417326_20240411-143521_back_returnGood_70f75407b7ae_415_17788571404.mp4
+6935284417326_20240411-143521_front_returnGood_70f75407b7ae_415_17788571404.mp4
+6941025140798_20240411-135647_back_addGood_70f75407b7ae_1760_17788571404.mp4
+6941025140798_20240411-135647_front_addGood_70f75407b7ae_1760_17788571404.mp4
+6941025140798_20240411-135655_back_returnGood_70f75407b7ae_1760_17788571404.mp4
+6941025140798_20240411-135655_front_returnGood_70f75407b7ae_1760_17788571404.mp4
+6941025140798_20240411-140026_back_addGood_70f754088050_1765_17327712807.mp4
+6941025140798_20240411-140026_front_addGood_70f754088050_1765_17327712807.mp4
+6941025140798_20240411-140105_back_returnGood_70f754088050_1760_17327712807.mp4
+6941025140798_20240411-140105_front_returnGood_70f754088050_1760_17327712807.mp4
+6952074634794_20240411-143701_back_addGood_70f75407b7ae_275_17788571404.mp4
+6952074634794_20240411-143701_front_addGood_70f75407b7ae_275_17788571404.mp4
+6952074634794_20240411-143707_back_returnGood_70f75407b7ae_275_17788571404.mp4
+6952074634794_20240411-143709_back_returnGood_70f754088050_5_17327712807.mp4
+6952074634794_20240411-143709_front_returnGood_70f754088050_5_17327712807.mp4
+6952074634794_20240411-143720_back_returnGood_70f754088050_265_17327712807.mp4
+6952074634794_20240411-143720_front_returnGood_70f754088050_265_17327712807.mp4
+6954432711307_20240411-161612_back_addGood_70f75407b7ae_460_17788571404.mp4
+6954432711307_20240411-161612_front_addGood_70f75407b7ae_460_17788571404.mp4
+6954432711307_20240411-161622_back_returnGood_70f75407b7ae_460_17788571404.mp4
+6954432711307_20240411-161622_front_returnGood_70f75407b7ae_460_17788571404.mp4
+6954432711307_20240411-161647_back_addGood_70f754088050_460_17327712807.mp4
+6954432711307_20240411-161647_front_addGood_70f754088050_460_17327712807.mp4
+6954432711307_20240411-161700_back_returnGood_70f754088050_460_17327712807.mp4
+6954432711307_20240411-161700_front_returnGood_70f754088050_460_17327712807.mp4
+6959546100993_20240411-135257_back_addGood_70f75407b7ae_295_17788571404.mp4
+6959546100993_20240411-135257_front_addGood_70f75407b7ae_295_17788571404.mp4
+6959546100993_20240411-135339_back_returnGood_70f75407b7ae_295_17788571404.mp4
+6959546100993_20240411-135339_front_returnGood_70f75407b7ae_295_17788571404.mp4
+6959546100993_20240411-141255_back_addGood_70f754088050_295_17327712807.mp4
+6959546100993_20240411-141255_front_addGood_70f754088050_295_17327712807.mp4
+6959546100993_20240411-141309_back_returnGood_70f754088050_295_17327712807.mp4
+6959546100993_20240411-141309_front_returnGood_70f754088050_295_17327712807.mp4
+6971075127463_20240411-135002_back_addGood_70f75407b7ae_210_17788571404.mp4
+6971075127463_20240411-135002_front_addGood_70f75407b7ae_210_17788571404.mp4
+6971075127463_20240411-135058_back_returnGood_70f75407b7ae_210_17788571404.mp4
+6971075127463_20240411-135058_front_returnGood_70f75407b7ae_210_17788571404.mp4
+6971075127463_20240411-141154_back_addGood_70f754088050_215_17327712807.mp4
+6971075127463_20240411-141154_front_addGood_70f754088050_215_17327712807.mp4
+6971075127463_20240411-141214_back_returnGood_70f754088050_210_17327712807.mp4
+6971075127463_20240411-141214_front_returnGood_70f754088050_210_17327712807.mp4
+6971328580533_20240411-135748_back_addGood_70f75407b7ae_405_17788571404.mp4
+6971328580533_20240411-135748_front_addGood_70f75407b7ae_405_17788571404.mp4
+6971328580533_20240411-135757_back_returnGood_70f75407b7ae_405_17788571404.mp4
+6971328580533_20240411-135757_front_returnGood_70f75407b7ae_405_17788571404.mp4
+6971328580533_20240411-140231_back_addGood_70f754088050_405_17327712807.mp4
+6971328580533_20240411-140231_front_addGood_70f754088050_405_17327712807.mp4
+6971328580533_20240411-140529_back_addGood_70f754088050_410_17327712807.mp4
+6971328580533_20240411-140529_front_addGood_70f754088050_410_17327712807.mp4
+6971328580533_20240411-140745_back_returnGood_70f754088050_405_17327712807.mp4
+6971328580533_20240411-140745_front_returnGood_70f754088050_405_17327712807.mp4
+6971738655333_20240411-144616_back_addGood_70f75407b7ae_270_17788571404.mp4
+6971738655333_20240411-144616_back_addGood_70f754088050_260_17327712807.mp4
+6971738655333_20240411-144616_front_addGood_70f75407b7ae_270_17788571404.mp4
+6971738655333_20240411-144616_front_addGood_70f754088050_260_17327712807.mp4
+6971738655333_20240411-144633_back_returnGood_70f75407b7ae_270_17788571404.mp4
+6971738655333_20240411-144633_front_returnGood_70f75407b7ae_270_17788571404.mp4
+6971738655333_20240411-144635_back_returnGood_70f754088050_260_17327712807.mp4
+6971738655333_20240411-144635_front_returnGood_70f754088050_260_17327712807.mp4
+6972378998200_20240411-142603_back_addGood_70f754088050_410_17327712807.mp4
+6972378998200_20240411-142603_front_addGood_70f754088050_410_17327712807.mp4
+6972378998200_20240411-142604_back_addGood_70f75407b7ae_410_17788571404.mp4
+6972378998200_20240411-142604_front_addGood_70f75407b7ae_410_17788571404.mp4
+6972378998200_20240411-142613_back_returnGood_70f75407b7ae_410_17788571404.mp4
+6972378998200_20240411-142613_back_returnGood_70f754088050_410_17327712807.mp4
+6972378998200_20240411-142613_front_returnGood_70f75407b7ae_410_17788571404.mp4
+6972378998200_20240411-142613_front_returnGood_70f754088050_410_17327712807.mp4
+6972790052733_20240411-162926_back_addGood_70f75407b7ae_690_17788571404.mp4
+6972790052733_20240411-162926_front_addGood_70f75407b7ae_690_17788571404.mp4
+6972790052733_20240411-162933_back_returnGood_70f75407b7ae_690_17788571404.mp4
+6972790052733_20240411-162933_front_returnGood_70f75407b7ae_690_17788571404.mp4
+6972790052733_20240411-162948_back_addGood_70f754088050_690_17327712807.mp4
+6972790052733_20240411-162948_front_addGood_70f754088050_690_17327712807.mp4
+6972790052733_20240411-163001_back_returnGood_70f754088050_690_17327712807.mp4
+6972790052733_20240411-163001_front_returnGood_70f754088050_690_17327712807.mp4
+6974627182033_20240411-150747_back_addGood_70f75407b7ae_485_17788571404.mp4
+6974627182033_20240411-150747_front_addGood_70f75407b7ae_485_17788571404.mp4
+6974627182033_20240411-150756_back_returnGood_70f75407b7ae_480_17788571404.mp4
+6974627182033_20240411-150756_front_returnGood_70f75407b7ae_480_17788571404.mp4
+6974627182033_20240411-150825_back_addGood_70f754088050_495_17327712807.mp4
+6974627182033_20240411-150825_front_addGood_70f754088050_495_17327712807.mp4
+6974627182033_20240411-150835_back_returnGood_70f754088050_495_17327712807.mp4
+6974627182033_20240411-150835_front_returnGood_70f754088050_495_17327712807.mp4
+6974913231612_20240411-135543_back_addGood_70f75407b7ae_870_17788571404.mp4
+6974913231612_20240411-135543_front_addGood_70f75407b7ae_870_17788571404.mp4
+6974913231612_20240411-135552_back_returnGood_70f75407b7ae_865_17788571404.mp4
+6974913231612_20240411-135552_front_returnGood_70f75407b7ae_865_17788571404.mp4
+6974913231612_20240411-140906_back_addGood_70f754088050_755_17327712807.mp4
+6974913231612_20240411-140906_front_addGood_70f754088050_755_17327712807.mp4
+6974913231612_20240411-140917_back_returnGood_70f754088050_755_17327712807.mp4
+6974913231612_20240411-140917_front_returnGood_70f754088050_755_17327712807.mp4
+6974995172711_20240411-135456_back_addGood_70f75407b7ae_1455_17788571404.mp4
+6974995172711_20240411-135456_front_addGood_70f75407b7ae_1455_17788571404.mp4
+6974995172711_20240411-135506_back_returnGood_70f75407b7ae_1460_17788571404.mp4
+6974995172711_20240411-135506_front_returnGood_70f75407b7ae_1460_17788571404.mp4
+6974995172711_20240411-140831_back_addGood_70f754088050_1460_17327712807.mp4
+6974995172711_20240411-140831_front_addGood_70f754088050_1460_17327712807.mp4
+6974995172711_20240411-140844_back_returnGood_70f754088050_1460_17327712807.mp4
+6974995172711_20240411-140844_front_returnGood_70f754088050_1460_17327712807.mp4
+6976090230303_20240411-144457_back_addGood_70f75407b7ae_390_17788571404.mp4
+6976090230303_20240411-144457_front_addGood_70f75407b7ae_390_17788571404.mp4
+6976090230303_20240411-144458_back_addGood_70f754088050_390_17327712807.mp4
+6976090230303_20240411-144458_front_addGood_70f754088050_390_17327712807.mp4
+6976090230303_20240411-144508_back_returnGood_70f754088050_390_17327712807.mp4
+6976090230303_20240411-144508_front_returnGood_70f754088050_390_17327712807.mp4
+6976090230303_20240411-144509_back_returnGood_70f75407b7ae_390_17788571404.mp4
+6976090230303_20240411-144509_front_returnGood_70f75407b7ae_390_17788571404.mp4
+6976371220276_20240411-150456_back_addGood_70f75407b7ae_390_17788571404.mp4
+6976371220276_20240411-150456_front_addGood_70f75407b7ae_390_17788571404.mp4
+6976371220276_20240411-150505_back_returnGood_70f75407b7ae_390_17788571404.mp4
+6976371220276_20240411-150505_front_returnGood_70f75407b7ae_390_17788571404.mp4
+6976371220276_20240411-150559_back_addGood_70f754088050_405_17327712807.mp4
+6976371220276_20240411-150559_front_addGood_70f754088050_405_17327712807.mp4
+6976371220276_20240411-150610_back_returnGood_70f754088050_405_17327712807.mp4
+6976371220276_20240411-150610_front_returnGood_70f754088050_405_17327712807.mp4
+230537101280010007_20240412-140824_back_addGood_70f754088050_565_13725988807.mp4
+230537101280010007_20240412-140824_front_addGood_70f754088050_565_13725988807.mp4
+230537101280010007_20240412-140835_back_returnGood_70f754088050_565_13725988807.mp4
+230537101280010007_20240412-140835_front_returnGood_70f754088050_565_13725988807.mp4
+2500456001326_20240412-140949_back_addGood_70f754088050_150_13725988807.mp4
+2500456001326_20240412-140949_front_addGood_70f754088050_150_13725988807.mp4
+2500456001326_20240412-140958_back_returnGood_70f754088050_155_13725988807.mp4
+2500456001326_20240412-140958_front_returnGood_70f754088050_155_13725988807.mp4
+2500458675341_20240412-140915_back_addGood_70f754088050_130_13725988807.mp4
+2500458675341_20240412-140915_front_addGood_70f754088050_130_13725988807.mp4
+2500458675341_20240412-140924_back_returnGood_70f754088050_130_13725988807.mp4
+2500458675341_20240412-140924_front_returnGood_70f754088050_130_13725988807.mp4
+2500463464671_20240412-140718_back_addGood_70f754088050_810_13725988807.mp4
+2500463464671_20240412-140718_front_addGood_70f754088050_810_13725988807.mp4
+2500463464671_20240412-140731_back_returnGood_70f754088050_810_13725988807.mp4
+2500463464671_20240412-140731_front_returnGood_70f754088050_810_13725988807.mp4
+6901070613142_20240412-144631_back_addGood_70f754088050_240_13725988807.mp4
+6901070613142_20240412-144631_front_addGood_70f754088050_240_13725988807.mp4
+6901070613142_20240412-144643_back_returnGood_70f754088050_240_13725988807.mp4
+6901070613142_20240412-144643_front_returnGood_70f754088050_240_13725988807.mp4
+6901586000993_20240412-152404_back_addGood_70f754088050_890_13725988807.mp4
+6901586000993_20240412-152404_front_addGood_70f754088050_890_13725988807.mp4
+6901586000993_20240412-152440_back_returnGood_70f754088050_885_13725988807.mp4
+6901586000993_20240412-152440_front_returnGood_70f754088050_885_13725988807.mp4
+6901668053893_20240412-150115_back_addGood_70f754088050_70_13725988807.mp4
+6901668053893_20240412-150115_front_addGood_70f754088050_70_13725988807.mp4
+6901668053893_20240412-150125_back_returnGood_70f754088050_70_13725988807.mp4
+6901668053893_20240412-150125_front_returnGood_70f754088050_70_13725988807.mp4
+6902007010249_20240412-144518_back_addGood_70f754088050_755_13725988807.mp4
+6902007010249_20240412-144518_front_addGood_70f754088050_755_13725988807.mp4
+6902007010249_20240412-144529_back_returnGood_70f754088050_755_13725988807.mp4
+6902007010249_20240412-144529_front_returnGood_70f754088050_755_13725988807.mp4
+6902022135514_20240412-144740_back_addGood_70f754088050_3180_13725988807.mp4
+6902022135514_20240412-144740_front_addGood_70f754088050_3180_13725988807.mp4
+6902022135514_20240412-144750_back_returnGood_70f754088050_3180_13725988807.mp4
+6902022135514_20240412-144750_front_returnGood_70f754088050_3180_13725988807.mp4
+6902265114369_20240412-144022_back_addGood_70f754088050_720_13725988807.mp4
+6902265114369_20240412-144022_front_addGood_70f754088050_720_13725988807.mp4
+6902265114369_20240412-144034_back_returnGood_70f754088050_720_13725988807.mp4
+6902265114369_20240412-144034_front_returnGood_70f754088050_720_13725988807.mp4
+6902265908012_20240412-144141_back_addGood_70f754088050_1145_13725988807.mp4
+6902265908012_20240412-144141_front_addGood_70f754088050_1145_13725988807.mp4
+6902265908012_20240412-144149_back_returnGood_70f754088050_1145_13725988807.mp4
+6902265908012_20240412-144149_front_returnGood_70f754088050_1145_13725988807.mp4
+69025143_20240412-135423_back_addGood_70f754088050_3015_13725988807.mp4
+69025143_20240412-135423_front_addGood_70f754088050_3015_13725988807.mp4
+69025143_20240412-135439_back_returnGood_70f754088050_3015_13725988807.mp4
+69025143_20240412-135439_front_returnGood_70f754088050_3015_13725988807.mp4
+6907992103952_20240412-141542_back_addGood_70f754088050_190_13725988807.mp4
+6907992103952_20240412-141542_front_addGood_70f754088050_190_13725988807.mp4
+6907992103952_20240412-141554_back_returnGood_70f754088050_190_13725988807.mp4
+6907992103952_20240412-141554_front_returnGood_70f754088050_190_13725988807.mp4
+6907992104157_20240412-141255_back_addGood_70f754088050_1120_13725988807.mp4
+6907992104157_20240412-141255_front_addGood_70f754088050_1120_13725988807.mp4
+6907992104157_20240412-141307_back_returnGood_70f754088050_1120_13725988807.mp4
+6907992104157_20240412-141307_front_returnGood_70f754088050_1120_13725988807.mp4
+6907992105260_20240412-142144_back_addGood_70f754088050_2775_13725988807.mp4
+6907992105260_20240412-142144_front_addGood_70f754088050_2775_13725988807.mp4
+6907992105260_20240412-142156_back_returnGood_70f754088050_2775_13725988807.mp4
+6907992105260_20240412-142156_front_returnGood_70f754088050_2775_13725988807.mp4
+6907992105260_20240412-143214_back_addGood_70f754088050_2770_13725988807.mp4
+6907992105260_20240412-143214_front_addGood_70f754088050_2770_13725988807.mp4
+6907992105260_20240412-143225_back_returnGood_70f754088050_2775_13725988807.mp4
+6907992105260_20240412-143225_front_returnGood_70f754088050_2775_13725988807.mp4
+6907992105765_20240412-141505_back_addGood_70f754088050_2085_13725988807.mp4
+6907992105765_20240412-141505_front_addGood_70f754088050_2085_13725988807.mp4
+6907992105765_20240412-141523_back_returnGood_70f754088050_2085_13725988807.mp4
+6907992105765_20240412-141523_front_returnGood_70f754088050_2085_13725988807.mp4
+6907992106205_20240412-141729_back_addGood_70f754088050_790_13725988807.mp4
+6907992106205_20240412-141729_front_addGood_70f754088050_790_13725988807.mp4
+6907992106205_20240412-141741_back_returnGood_70f754088050_790_13725988807.mp4
+6907992106205_20240412-141741_front_returnGood_70f754088050_790_13725988807.mp4
+6907992106311_20240412-141326_back_addGood_70f754088050_890_13725988807.mp4
+6907992106311_20240412-141326_front_addGood_70f754088050_890_13725988807.mp4
+6907992106311_20240412-141341_back_returnGood_70f754088050_890_13725988807.mp4
+6907992106311_20240412-141341_front_returnGood_70f754088050_890_13725988807.mp4
+6914973602908_20240412-134547_back_addGood_70f754088050_505_13725988807.mp4
+6914973602908_20240412-134547_front_addGood_70f754088050_505_13725988807.mp4
+6914973602908_20240412-134600_back_returnGood_70f754088050_505_13725988807.mp4
+6914973602908_20240412-134600_front_returnGood_70f754088050_505_13725988807.mp4
+6914973604223_20240412-143609_back_addGood_70f754088050_230_13725988807.mp4
+6914973604223_20240412-143609_front_addGood_70f754088050_230_13725988807.mp4
+6914973604223_20240412-143619_back_returnGood_70f754088050_230_13725988807.mp4
+6914973604223_20240412-143619_front_returnGood_70f754088050_230_13725988807.mp4
+6914973606340_20240412-134352_back_addGood_70f754088050_325_13725988807.mp4
+6914973606340_20240412-134352_front_addGood_70f754088050_325_13725988807.mp4
+6914973606340_20240412-134406_back_returnGood_70f754088050_330_13725988807.mp4
+6914973606340_20240412-134406_front_returnGood_70f754088050_330_13725988807.mp4
+6919188092377_20240412-141841_back_addGood_70f754088050_515_13725988807.mp4
+6919188092377_20240412-141841_front_addGood_70f754088050_515_13725988807.mp4
+6919188092377_20240412-141850_back_returnGood_70f754088050_515_13725988807.mp4
+6919188092377_20240412-141850_front_returnGood_70f754088050_515_13725988807.mp4
+6920152400630_20240412-151036_back_returnGood_70f754088050_580_13725988807.mp4
+6920174757101_20240412-144934_back_addGood_70f754088050_1300_13725988807.mp4
+6920174757101_20240412-144934_front_addGood_70f754088050_1300_13725988807.mp4
+6920174757101_20240412-144946_back_returnGood_70f754088050_1300_13725988807.mp4
+6920174757101_20240412-144946_front_returnGood_70f754088050_1300_13725988807.mp4
+6920459905012_20240412-150826_back_returnGood_70f754088050_550_13725988807.mp4
+6920907810707_20240412-145330_back_addGood_70f754088050_75_13725988807.mp4
+6920907810707_20240412-145330_front_addGood_70f754088050_75_13725988807.mp4
+6920907810707_20240412-145340_back_returnGood_70f754088050_75_13725988807.mp4
+6920907810707_20240412-145340_front_returnGood_70f754088050_75_13725988807.mp4
+6922130119213_20240412-144416_back_addGood_70f754088050_1020_13725988807.mp4
+6922130119213_20240412-144416_front_addGood_70f754088050_1020_13725988807.mp4
+6922130119213_20240412-144426_back_returnGood_70f754088050_1020_13725988807.mp4
+6922130119213_20240412-144426_front_returnGood_70f754088050_1020_13725988807.mp4
+6922577700968_20240412-141700_back_addGood_70f754088050_1040_13725988807.mp4
+6922577700968_20240412-141700_front_addGood_70f754088050_1040_13725988807.mp4
+6922577700968_20240412-141710_back_returnGood_70f754088050_1040_13725988807.mp4
+6922577700968_20240412-141710_front_returnGood_70f754088050_1040_13725988807.mp4
+6922868291168_20240412-145057_back_addGood_70f754088050_1160_13725988807.mp4
+6922868291168_20240412-145057_front_addGood_70f754088050_1160_13725988807.mp4
+6922868291168_20240412-145113_back_returnGood_70f754088050_1160_13725988807.mp4
+6922868291168_20240412-145113_front_returnGood_70f754088050_1160_13725988807.mp4
+6923450601549_20240412-134454_back_addGood_70f754088050_640_13725988807.mp4
+6923450601549_20240412-134454_front_addGood_70f754088050_640_13725988807.mp4
+6923450601549_20240412-134504_back_returnGood_70f754088050_635_13725988807.mp4
+6923450601549_20240412-134504_front_returnGood_70f754088050_635_13725988807.mp4
+6923450603574_20240412-135226_back_addGood_70f754088050_970_13725988807.mp4
+6923450603574_20240412-135226_front_addGood_70f754088050_970_13725988807.mp4
+6923450603574_20240412-135240_back_returnGood_70f754088050_965_13725988807.mp4
+6923450603574_20240412-135240_front_returnGood_70f754088050_965_13725988807.mp4
+6923450605288_20240412-134133_back_addGood_70f754088050_470_13725988807.mp4
+6923450605288_20240412-134133_front_addGood_70f754088050_470_13725988807.mp4
+6923450605288_20240412-134143_back_returnGood_70f754088050_470_13725988807.mp4
+6923450605288_20240412-134143_front_returnGood_70f754088050_470_13725988807.mp4
+6923450605332_20240412-135742_back_addGood_70f754088050_1785_13725988807.mp4
+6923450605332_20240412-135742_front_addGood_70f754088050_1785_13725988807.mp4
+6923450605332_20240412-135756_back_returnGood_70f754088050_1785_13725988807.mp4
+6923450605332_20240412-135756_front_returnGood_70f754088050_1785_13725988807.mp4
+6923450610428_20240412-133618_back_addGood_70f754088050_320_13725988807.mp4
+6923450610428_20240412-133618_front_addGood_70f754088050_320_13725988807.mp4
+6923450610428_20240412-133632_back_returnGood_70f754088050_320_13725988807.mp4
+6923450610428_20240412-133632_front_returnGood_70f754088050_320_13725988807.mp4
+6923450610459_20240412-135040_back_addGood_70f754088050_555_13725988807.mp4
+6923450610459_20240412-135040_front_addGood_70f754088050_555_13725988807.mp4
+6923450610459_20240412-135057_back_returnGood_70f754088050_555_13725988807.mp4
+6923450610459_20240412-135057_front_returnGood_70f754088050_555_13725988807.mp4
+6923450611067_20240412-134949_back_addGood_70f754088050_800_13725988807.mp4
+6923450611067_20240412-134949_front_addGood_70f754088050_800_13725988807.mp4
+6923450611067_20240412-135002_back_returnGood_70f754088050_800_13725988807.mp4
+6923450611067_20240412-135002_front_returnGood_70f754088050_800_13725988807.mp4
+6923450612415_20240412-133515_back_addGood_70f754088050_820_13725988807.mp4
+6923450612415_20240412-133515_front_addGood_70f754088050_820_13725988807.mp4
+6923450612415_20240412-133532_back_returnGood_70f754088050_820_13725988807.mp4
+6923450612415_20240412-133532_front_returnGood_70f754088050_820_13725988807.mp4
+6923450612484_20240412-133746_back_addGood_70f754088050_255_13725988807.mp4
+6923450612484_20240412-133746_front_addGood_70f754088050_255_13725988807.mp4
+6923450612484_20240412-133758_back_returnGood_70f754088050_255_13725988807.mp4
+6923450612484_20240412-133758_front_returnGood_70f754088050_255_13725988807.mp4
+6923450657829_20240412-135628_back_addGood_70f754088050_965_13725988807.mp4
+6923450657829_20240412-135628_front_addGood_70f754088050_965_13725988807.mp4
+6923450657829_20240412-135640_back_returnGood_70f754088050_965_13725988807.mp4
+6923450657829_20240412-135640_front_returnGood_70f754088050_965_13725988807.mp4
+6923450659441_20240412-135319_back_addGood_70f754088050_1825_13725988807.mp4
+6923450659441_20240412-135319_front_addGood_70f754088050_1825_13725988807.mp4
+6923450659441_20240412-135334_back_returnGood_70f754088050_1825_13725988807.mp4
+6923450659441_20240412-135334_front_returnGood_70f754088050_1825_13725988807.mp4
+6923450666838_20240412-134807_back_addGood_70f754088050_760_13725988807.mp4
+6923450666838_20240412-134807_front_addGood_70f754088050_760_13725988807.mp4
+6923450666838_20240412-134818_back_returnGood_70f754088050_760_13725988807.mp4
+6923450666838_20240412-134818_front_returnGood_70f754088050_760_13725988807.mp4
+6923450668207_20240412-134250_back_addGood_70f754088050_700_13725988807.mp4
+6923450668207_20240412-134250_front_addGood_70f754088050_700_13725988807.mp4
+6923450668207_20240412-134302_back_returnGood_70f754088050_700_13725988807.mp4
+6923450668207_20240412-134302_front_returnGood_70f754088050_700_13725988807.mp4
+6923450677858_20240412-135523_back_addGood_70f754088050_910_13725988807.mp4
+6923450677858_20240412-135523_front_addGood_70f754088050_910_13725988807.mp4
+6923450677858_20240412-135537_back_returnGood_70f754088050_910_13725988807.mp4
+6923450677858_20240412-135537_front_returnGood_70f754088050_910_13725988807.mp4
+6923644286293_20240412-141148_back_addGood_70f754088050_810_13725988807.mp4
+6923644286293_20240412-141148_front_addGood_70f754088050_810_13725988807.mp4
+6923644286293_20240412-141157_back_returnGood_70f754088050_805_13725988807.mp4
+6923644286293_20240412-141157_front_returnGood_70f754088050_805_13725988807.mp4
+6923644298760_20240412-141219_back_addGood_70f754088050_1020_13725988807.mp4
+6923644298760_20240412-141219_front_addGood_70f754088050_1020_13725988807.mp4
+6923644298760_20240412-141227_back_returnGood_70f754088050_1020_13725988807.mp4
+6923644298760_20240412-141227_front_returnGood_70f754088050_1020_13725988807.mp4
+6924743915824_20240412-145245_back_addGood_70f754088050_155_13725988807.mp4
+6924743915824_20240412-145245_front_addGood_70f754088050_155_13725988807.mp4
+6924743915824_20240412-145254_back_returnGood_70f754088050_155_13725988807.mp4
+6924743915824_20240412-145254_front_returnGood_70f754088050_155_13725988807.mp4
+6924882497106_20240412-150553_back_addGood_70f754088050_355_13725988807.mp4
+6924882497106_20240412-150553_front_addGood_70f754088050_355_13725988807.mp4
+6924882497106_20240412-150604_back_returnGood_70f754088050_355_13725988807.mp4
+6924882497106_20240412-150604_front_returnGood_70f754088050_355_13725988807.mp4
+6925307305525_20240412-152608_back_addGood_70f754088050_590_13725988807.mp4
+6925307305525_20240412-152608_front_addGood_70f754088050_590_13725988807.mp4
+6925307305525_20240412-152627_back_returnGood_70f754088050_590_13725988807.mp4
+6925307305525_20240412-152627_front_returnGood_70f754088050_590_13725988807.mp4
+6928033404968_20240412-143452_back_addGood_70f754088050_400_13725988807.mp4
+6928033404968_20240412-143452_front_addGood_70f754088050_400_13725988807.mp4
+6928033404968_20240412-143502_back_returnGood_70f754088050_400_13725988807.mp4
+6928033404968_20240412-143502_front_returnGood_70f754088050_400_13725988807.mp4
+6928804011173_20240412-152735_back_addGood_70f754088050_545_13725988807.mp4
+6928804011173_20240412-152735_front_addGood_70f754088050_545_13725988807.mp4
+6928804011173_20240412-152746_back_returnGood_70f754088050_545_13725988807.mp4
+6928804011173_20240412-152746_front_returnGood_70f754088050_545_13725988807.mp4
+6931925828032_20240412-134659_back_addGood_70f754088050_415_13725988807.mp4
+6931925828032_20240412-134659_front_addGood_70f754088050_415_13725988807.mp4
+6931925828032_20240412-134711_back_returnGood_70f754088050_415_13725988807.mp4
+6931925828032_20240412-134711_front_returnGood_70f754088050_415_13725988807.mp4
+6933620900051_20240412-140306_back_addGood_70f754088050_385_13725988807.mp4
+6933620900051_20240412-140306_front_addGood_70f754088050_385_13725988807.mp4
+6933620900051_20240412-140326_back_returnGood_70f754088050_390_13725988807.mp4
+6933620900051_20240412-140326_front_returnGood_70f754088050_390_13725988807.mp4
+6934665095108_20240412-141758_back_addGood_70f754088050_355_13725988807.mp4
+6934665095108_20240412-141758_front_addGood_70f754088050_355_13725988807.mp4
+6934665095108_20240412-141807_back_returnGood_70f754088050_355_13725988807.mp4
+6934665095108_20240412-141807_front_returnGood_70f754088050_355_13725988807.mp4
+6935270642121_20240412-151112_back_addGood_70f754088050_165_13725988807.mp4
+6935270642121_20240412-151112_front_addGood_70f754088050_165_13725988807.mp4
+6935270642121_20240412-151124_back_returnGood_70f754088050_165_13725988807.mp4
+6935270642121_20240412-151124_front_returnGood_70f754088050_165_13725988807.mp4
+6935284417326_20240412-145558_back_addGood_70f754088050_410_13725988807.mp4
+6935284417326_20240412-145558_front_addGood_70f754088050_410_13725988807.mp4
+6935284417326_20240412-145610_back_returnGood_70f754088050_410_13725988807.mp4
+6935284417326_20240412-145610_front_returnGood_70f754088050_410_13725988807.mp4
+6941025140798_20240412-152222_back_addGood_70f754088050_1160_13725988807.mp4
+6941025140798_20240412-152222_front_addGood_70f754088050_1160_13725988807.mp4
+6941025140798_20240412-152235_back_returnGood_70f754088050_1155_13725988807.mp4
+6941025140798_20240412-152235_front_returnGood_70f754088050_1155_13725988807.mp4
+6952074634794_20240412-153052_back_addGood_70f754088050_265_13725988807.mp4
+6952074634794_20240412-153052_front_addGood_70f754088050_265_13725988807.mp4
+6952074634794_20240412-153105_back_returnGood_70f754088050_265_13725988807.mp4
+6952074634794_20240412-153105_front_returnGood_70f754088050_265_13725988807.mp4
+6952074634794_20240412-153233_back_addGood_70f754088050_265_13725988807.mp4
+6952074634794_20240412-153233_front_addGood_70f754088050_265_13725988807.mp4
+6952074634794_20240412-153245_back_returnGood_70f754088050_265_13725988807.mp4
+6952074634794_20240412-153245_front_returnGood_70f754088050_265_13725988807.mp4
+6954432711307_20240412-134028_back_addGood_70f754088050_355_13725988807.mp4
+6954432711307_20240412-134028_front_addGood_70f754088050_355_13725988807.mp4
+6954432711307_20240412-134040_back_returnGood_70f754088050_350_13725988807.mp4
+6954432711307_20240412-134040_front_returnGood_70f754088050_350_13725988807.mp4
+6959546100993_20240412-142438_back_addGood_70f754088050_295_13725988807.mp4
+6959546100993_20240412-142438_front_addGood_70f754088050_295_13725988807.mp4
+6959546100993_20240412-142455_back_returnGood_70f754088050_295_13725988807.mp4
+6959546100993_20240412-142455_front_returnGood_70f754088050_295_13725988807.mp4
+6971075127463_20240412-142330_back_addGood_70f754088050_210_13725988807.mp4
+6971075127463_20240412-142330_front_addGood_70f754088050_210_13725988807.mp4
+6971075127463_20240412-142347_back_returnGood_70f754088050_215_13725988807.mp4
+6971075127463_20240412-142347_front_returnGood_70f754088050_215_13725988807.mp4
+6971075127470_20240412-142650_back_addGood_70f754088050_215_13725988807.mp4
+6971075127470_20240412-142650_front_addGood_70f754088050_215_13725988807.mp4
+6971075127470_20240412-142700_back_returnGood_70f754088050_215_13725988807.mp4
+6971075127470_20240412-142700_front_returnGood_70f754088050_215_13725988807.mp4
+6971328580533_20240412-152303_back_addGood_70f754088050_655_13725988807.mp4
+6971328580533_20240412-152303_front_addGood_70f754088050_655_13725988807.mp4
+6971328580533_20240412-152322_back_returnGood_70f754088050_650_13725988807.mp4
+6971328580533_20240412-152322_front_returnGood_70f754088050_650_13725988807.mp4
+6971738655333_20240412-141033_back_addGood_70f754088050_270_13725988807.mp4
+6971738655333_20240412-141033_front_addGood_70f754088050_270_13725988807.mp4
+6971738655333_20240412-141042_back_returnGood_70f754088050_270_13725988807.mp4
+6971738655333_20240412-141042_front_returnGood_70f754088050_270_13725988807.mp4
+6972378998200_20240412-144314_back_addGood_70f754088050_410_13725988807.mp4
+6972378998200_20240412-144314_front_addGood_70f754088050_410_13725988807.mp4
+6972378998200_20240412-144326_back_returnGood_70f754088050_410_13725988807.mp4
+6972378998200_20240412-144326_front_returnGood_70f754088050_410_13725988807.mp4
+6972790052733_20240412-135134_back_addGood_70f754088050_525_13725988807.mp4
+6972790052733_20240412-135134_front_addGood_70f754088050_525_13725988807.mp4
+6972790052733_20240412-135145_back_returnGood_70f754088050_525_13725988807.mp4
+6972790052733_20240412-135145_front_returnGood_70f754088050_525_13725988807.mp4
+6974913231612_20240412-142848_back_addGood_70f754088050_500_13725988807.mp4
+6974913231612_20240412-142848_front_addGood_70f754088050_500_13725988807.mp4
+6974913231612_20240412-142900_back_returnGood_70f754088050_495_13725988807.mp4
+6974913231612_20240412-142900_front_returnGood_70f754088050_495_13725988807.mp4
+6974995172711_20240412-152143_back_addGood_70f754088050_455_13725988807.mp4
+6974995172711_20240412-152143_front_addGood_70f754088050_455_13725988807.mp4
+6974995172711_20240412-152158_back_returnGood_70f754088050_455_13725988807.mp4
+6974995172711_20240412-152158_front_returnGood_70f754088050_455_13725988807.mp4
+6976371220276_20240412-140448_back_addGood_70f754088050_295_13725988807.mp4
+6976371220276_20240412-140448_front_addGood_70f754088050_295_13725988807.mp4
+6976371220276_20240412-140459_back_returnGood_70f754088050_295_13725988807.mp4
+6976371220276_20240412-140459_front_returnGood_70f754088050_295_13725988807.mp4
+850009021632_20240412-152522_back_addGood_70f754088050_470_13725988807.mp4
+850009021632_20240412-152522_front_addGood_70f754088050_470_13725988807.mp4
+850009021632_20240412-152543_back_returnGood_70f754088050_470_13725988807.mp4
+850009021632_20240412-152543_front_returnGood_70f754088050_470_13725988807.mp4

tracking/matching/视频分类/双.txt

@@ -0,0 +1,208 @@
+6901070613142_20240411-170415_back_addGood_70f75407b7ae_430_17788571404.mp4
+6901070613142_20240411-170415_front_addGood_70f75407b7ae_430_17788571404.mp4
+6901070613142_20240411-170424_back_returnGood_70f75407b7ae_430_17788571404.mp4
+6901070613142_20240411-170424_front_returnGood_70f75407b7ae_430_17788571404.mp4
+6901070613142_20240411-170441_back_addGood_70f754088050_430_17327712807.mp4
+6901070613142_20240411-170441_front_addGood_70f754088050_430_17327712807.mp4
+6901070613142_20240411-170450_back_returnGood_70f754088050_430_17327712807.mp4
+6901070613142_20240411-170450_front_returnGood_70f754088050_430_17327712807.mp4
+6902538007367_20240411-165931_back_addGood_70f75407b7ae_995_17788571404.mp4
+6902538007367_20240411-165931_front_addGood_70f75407b7ae_995_17788571404.mp4
+6902538007367_20240411-165942_back_returnGood_70f75407b7ae_995_17788571404.mp4
+6902538007367_20240411-165942_front_returnGood_70f75407b7ae_995_17788571404.mp4
+6902538007367_20240411-165954_back_addGood_70f754088050_1000_17327712807.mp4
+6902538007367_20240411-165954_front_addGood_70f754088050_1000_17327712807.mp4
+6902538007367_20240411-170005_back_returnGood_70f754088050_1000_17327712807.mp4
+6902538007367_20240411-170005_front_returnGood_70f754088050_1000_17327712807.mp4
+6920152400630_20240411-165136_back_addGood_70f75407b7ae_720_17788571404.mp4
+6920152400630_20240411-165136_front_addGood_70f75407b7ae_720_17788571404.mp4
+6920152400630_20240411-165151_back_returnGood_70f75407b7ae_715_17788571404.mp4
+6920152400630_20240411-165151_front_returnGood_70f75407b7ae_715_17788571404.mp4
+6920152400630_20240411-165213_back_addGood_70f754088050_720_17327712807.mp4
+6920152400630_20240411-165213_front_addGood_70f754088050_720_17327712807.mp4
+6920152400630_20240411-165224_back_returnGood_70f754088050_720_17327712807.mp4
+6920152400630_20240411-165224_front_returnGood_70f754088050_720_17327712807.mp4
+6920907810707_20240411-165615_back_addGood_70f75407b7ae_225_17788571404.mp4
+6920907810707_20240411-165615_front_addGood_70f75407b7ae_225_17788571404.mp4
+6920907810707_20240411-165625_back_returnGood_70f75407b7ae_225_17788571404.mp4
+6920907810707_20240411-165625_front_returnGood_70f75407b7ae_225_17788571404.mp4
+6920907810707_20240411-165635_back_addGood_70f754088050_225_17327712807.mp4
+6920907810707_20240411-165635_front_addGood_70f754088050_225_17327712807.mp4
+6920907810707_20240411-165646_back_returnGood_70f754088050_225_17327712807.mp4
+6920907810707_20240411-165646_front_returnGood_70f754088050_225_17327712807.mp4
+6923450605288_20240411-172045_back_addGood_70f75407b7ae_750_17788571404.mp4
+6923450605288_20240411-172045_front_addGood_70f75407b7ae_750_17788571404.mp4
+6923450605288_20240411-172058_back_returnGood_70f75407b7ae_750_17788571404.mp4
+6923450605288_20240411-172058_front_returnGood_70f75407b7ae_750_17788571404.mp4
+6923450605288_20240411-172134_back_addGood_70f754088050_750_17327712807.mp4
+6923450605288_20240411-172134_front_addGood_70f754088050_750_17327712807.mp4
+6923450605288_20240411-172147_back_returnGood_70f754088050_750_17327712807.mp4
+6923450605288_20240411-172147_front_returnGood_70f754088050_750_17327712807.mp4
+6923450610428_20240411-171842_back_addGood_70f75407b7ae_270_17788571404.mp4
+6923450610428_20240411-171842_front_addGood_70f75407b7ae_270_17788571404.mp4
+6923450610428_20240411-171900_back_returnGood_70f75407b7ae_755_17788571404.mp4
+6923450610428_20240411-171900_front_returnGood_70f75407b7ae_755_17788571404.mp4
+6923450610428_20240411-171918_back_addGood_70f754088050_755_17327712807.mp4
+6923450610428_20240411-171918_front_addGood_70f754088050_755_17327712807.mp4
+6923450610428_20240411-172000_back_returnGood_70f754088050_755_17327712807.mp4
+6923450610428_20240411-172000_front_returnGood_70f754088050_755_17327712807.mp4
+6923450659441_20240411-171417_back_addGood_70f75407b7ae_2340_17788571404.mp4
+6923450659441_20240411-171417_front_addGood_70f75407b7ae_2340_17788571404.mp4
+6923450659441_20240411-171430_back_returnGood_70f75407b7ae_2335_17788571404.mp4
+6923450659441_20240411-171430_front_returnGood_70f75407b7ae_2335_17788571404.mp4
+6923450659441_20240411-171445_back_addGood_70f754088050_2340_17327712807.mp4
+6923450659441_20240411-171445_front_addGood_70f754088050_2340_17327712807.mp4
+6923450659441_20240411-171456_back_returnGood_70f754088050_2340_17327712807.mp4
+6923450659441_20240411-171456_front_returnGood_70f754088050_2340_17327712807.mp4
+6923450677858_20240411-171658_back_addGood_70f75407b7ae_1310_17788571404.mp4
+6923450677858_20240411-171658_front_addGood_70f75407b7ae_1310_17788571404.mp4
+6923450677858_20240411-171709_back_returnGood_70f75407b7ae_1310_17788571404.mp4
+6923450677858_20240411-171709_front_returnGood_70f75407b7ae_1310_17788571404.mp4
+6923450677858_20240411-171720_back_addGood_70f754088050_1310_17327712807.mp4
+6923450677858_20240411-171720_front_addGood_70f754088050_1310_17327712807.mp4
+6923450677858_20240411-171730_back_returnGood_70f754088050_1315_17327712807.mp4
+6923450677858_20240411-171730_front_returnGood_70f754088050_1315_17327712807.mp4
+6928804011173_20240411-165756_back_addGood_70f75407b7ae_615_17788571404.mp4
+6928804011173_20240411-165756_front_addGood_70f75407b7ae_615_17788571404.mp4
+6928804011173_20240411-165808_back_returnGood_70f75407b7ae_620_17788571404.mp4
+6928804011173_20240411-165808_front_returnGood_70f75407b7ae_620_17788571404.mp4
+6928804011173_20240411-165822_back_addGood_70f754088050_620_17327712807.mp4
+6928804011173_20240411-165822_front_addGood_70f754088050_620_17327712807.mp4
+6928804011173_20240411-165830_back_returnGood_70f754088050_620_17327712807.mp4
+6928804011173_20240411-165830_front_returnGood_70f754088050_620_17327712807.mp4
+6976371220276_20240411-170159_back_addGood_70f75407b7ae_745_17788571404.mp4
+6976371220276_20240411-170159_front_addGood_70f75407b7ae_745_17788571404.mp4
+6976371220276_20240411-170211_back_returnGood_70f75407b7ae_745_17788571404.mp4
+6976371220276_20240411-170211_front_returnGood_70f75407b7ae_745_17788571404.mp4
+6976371220276_20240411-170230_back_addGood_70f754088050_745_17327712807.mp4
+6976371220276_20240411-170230_front_addGood_70f754088050_745_17327712807.mp4
+6976371220276_20240411-170240_back_returnGood_70f754088050_745_17327712807.mp4
+6976371220276_20240411-170240_front_returnGood_70f754088050_745_17327712807.mp4
+230537101280010007_20240412-114205_back_addGood_70f75407b7ae_720_17327712807.mp4
+230537101280010007_20240412-114205_front_addGood_70f75407b7ae_720_17327712807.mp4
+230537101280010007_20240412-114214_back_returnGood_70f75407b7ae_720_17327712807.mp4
+230537101280010007_20240412-114214_front_returnGood_70f75407b7ae_720_17327712807.mp4
+2500456001326_20240412-110503_back_addGood_70f75407b7ae_1085_17327712807.mp4
+2500456001326_20240412-110503_front_addGood_70f75407b7ae_1085_17327712807.mp4
+2500456001326_20240412-110513_back_returnGood_70f75407b7ae_1085_17327712807.mp4
+2500456001326_20240412-110513_front_returnGood_70f75407b7ae_1085_17327712807.mp4
+6901070613142_20240412-110200_back_addGood_70f754088050_1180_17788571404.mp4
+6901070613142_20240412-110200_front_addGood_70f754088050_1180_17788571404.mp4
+6901070613142_20240412-110207_back_returnGood_70f754088050_1180_17788571404.mp4
+6901070613142_20240412-110207_front_returnGood_70f754088050_1180_17788571404.mp4
+6901070613142_20240412-112959_back_addGood_70f75407b7ae_655_17327712807.mp4
+6901070613142_20240412-112959_front_addGood_70f75407b7ae_655_17327712807.mp4
+6901070613142_20240412-113011_back_returnGood_70f75407b7ae_655_17327712807.mp4
+6901070613142_20240412-113011_front_returnGood_70f75407b7ae_655_17327712807.mp4
+6901668053893_20240412-113635_back_addGood_70f75407b7ae_565_17327712807.mp4
+6901668053893_20240412-113635_front_addGood_70f75407b7ae_565_17327712807.mp4
+6901668053893_20240412-113645_back_returnGood_70f75407b7ae_640_17327712807.mp4
+6901668053893_20240412-113645_front_returnGood_70f75407b7ae_640_17327712807.mp4
+6902007010249_20240412-113050_back_addGood_70f75407b7ae_1460_17327712807.mp4
+6902007010249_20240412-113050_front_addGood_70f75407b7ae_1460_17327712807.mp4
+6902007010249_20240412-113103_back_returnGood_70f75407b7ae_1460_17327712807.mp4
+6902007010249_20240412-113103_front_returnGood_70f75407b7ae_1460_17327712807.mp4
+6902022135514_20240412-112914_back_addGood_70f75407b7ae_3640_17327712807.mp4
+6902022135514_20240412-112914_front_addGood_70f75407b7ae_3640_17327712807.mp4
+6902022135514_20240412-112926_back_returnGood_70f75407b7ae_3640_17327712807.mp4
+6902022135514_20240412-112926_front_returnGood_70f75407b7ae_3640_17327712807.mp4
+6902265114369_20240412-110609_back_addGood_70f75407b7ae_990_17327712807.mp4
+6902265114369_20240412-110609_front_addGood_70f75407b7ae_990_17327712807.mp4
+6902265114369_20240412-110618_back_returnGood_70f75407b7ae_990_17327712807.mp4
+6902265114369_20240412-110618_front_returnGood_70f75407b7ae_990_17327712807.mp4
+6902265908012_20240412-111958_back_addGood_70f75407b7ae_1520_17327712807.mp4
+6902265908012_20240412-111958_front_addGood_70f75407b7ae_1520_17327712807.mp4
+6902265908012_20240412-112012_back_returnGood_70f75407b7ae_1520_17327712807.mp4
+6902265908012_20240412-112012_front_returnGood_70f75407b7ae_1520_17327712807.mp4
+6902538007367_20240412-105046_back_addGood_70f754088050_930_17788571404.mp4
+6902538007367_20240412-105046_front_addGood_70f754088050_930_17788571404.mp4
+6902538007367_20240412-105057_back_returnGood_70f754088050_930_17788571404.mp4
+6902538007367_20240412-105057_front_returnGood_70f754088050_930_17788571404.mp4
+6902538007367_20240412-105130_back_addGood_70f754088050_930_17788571404.mp4
+6902538007367_20240412-105130_front_addGood_70f754088050_930_17788571404.mp4
+6902538007367_20240412-105143_back_returnGood_70f754088050_935_17788571404.mp4
+6902538007367_20240412-105143_front_returnGood_70f754088050_935_17788571404.mp4
+6907992103952_20240412-114032_back_addGood_70f75407b7ae_545_17327712807.mp4
+6907992103952_20240412-114032_front_addGood_70f75407b7ae_545_17327712807.mp4
+6907992103952_20240412-114043_back_returnGood_70f75407b7ae_540_17327712807.mp4
+6907992103952_20240412-114043_front_returnGood_70f75407b7ae_540_17327712807.mp4
+6907992106311_20240412-110328_back_addGood_70f75407b7ae_2565_17327712807.mp4
+6907992106311_20240412-110328_front_addGood_70f75407b7ae_2565_17327712807.mp4
+6907992106311_20240412-110342_back_returnGood_70f75407b7ae_2570_17327712807.mp4
+6907992106311_20240412-110342_front_returnGood_70f75407b7ae_2570_17327712807.mp4
+6920152400630_20240412-112256_back_addGood_70f75407b7ae_1230_17327712807.mp4
+6920152400630_20240412-112256_front_addGood_70f75407b7ae_1230_17327712807.mp4
+6920152400630_20240412-112308_back_returnGood_70f75407b7ae_1230_17327712807.mp4
+6920152400630_20240412-112308_front_returnGood_70f75407b7ae_1230_17327712807.mp4
+6920174757101_20240412-112806_back_addGood_70f75407b7ae_2120_17327712807.mp4
+6920174757101_20240412-112806_front_addGood_70f75407b7ae_2120_17327712807.mp4
+6920174757101_20240412-112823_back_returnGood_70f75407b7ae_2125_17327712807.mp4
+6920174757101_20240412-112823_front_returnGood_70f75407b7ae_2125_17327712807.mp4
+6920459905012_20240412-104811_back_addGood_70f754088050_840_17788571404.mp4
+6920459905012_20240412-104811_front_addGood_70f754088050_840_17788571404.mp4
+6920459905012_20240412-104906_back_returnGood_70f754088050_840_17788571404.mp4
+6920459905012_20240412-104906_front_returnGood_70f754088050_840_17788571404.mp4
+6920459905012_20240412-105345_back_addGood_70f754088050_830_17788571404.mp4
+6920459905012_20240412-105345_front_addGood_70f754088050_830_17788571404.mp4
+6920459905012_20240412-105356_back_returnGood_70f754088050_830_17788571404.mp4
+6920459905012_20240412-105356_front_returnGood_70f754088050_830_17788571404.mp4
+6920459905012_20240412-113755_back_addGood_70f75407b7ae_970_17327712807.mp4
+6920459905012_20240412-113755_front_addGood_70f75407b7ae_970_17327712807.mp4
+6920459905012_20240412-113808_back_returnGood_70f75407b7ae_970_17327712807.mp4
+6920459905012_20240412-113808_front_returnGood_70f75407b7ae_970_17327712807.mp4
+6920907810707_20240412-105728_back_addGood_70f754088050_150_17788571404.mp4
+6920907810707_20240412-105728_front_addGood_70f754088050_150_17788571404.mp4
+6920907810707_20240412-105739_back_returnGood_70f754088050_145_17788571404.mp4
+6920907810707_20240412-105739_front_returnGood_70f754088050_145_17788571404.mp4
+6920907810707_20240412-113710_back_addGood_70f75407b7ae_900_17327712807.mp4
+6920907810707_20240412-113710_front_addGood_70f75407b7ae_900_17327712807.mp4
+6920907810707_20240412-113720_back_returnGood_70f75407b7ae_900_17327712807.mp4
+6920907810707_20240412-113720_front_returnGood_70f75407b7ae_900_17327712807.mp4
+6922130119213_20240412-111854_back_addGood_70f75407b7ae_1310_17327712807.mp4
+6922130119213_20240412-111854_front_addGood_70f75407b7ae_1310_17327712807.mp4
+6922130119213_20240412-111904_back_returnGood_70f75407b7ae_1310_17327712807.mp4
+6922130119213_20240412-111904_front_returnGood_70f75407b7ae_1310_17327712807.mp4
+6922577700968_20240412-114323_back_addGood_70f75407b7ae_1045_17327712807.mp4
+6922577700968_20240412-114323_front_addGood_70f75407b7ae_1045_17327712807.mp4
+6922577700968_20240412-114333_back_returnGood_70f75407b7ae_1310_17327712807.mp4
+6922577700968_20240412-114333_front_returnGood_70f75407b7ae_1310_17327712807.mp4
+6922868291168_20240412-112724_back_addGood_70f75407b7ae_4540_17327712807.mp4
+6922868291168_20240412-112724_front_addGood_70f75407b7ae_4540_17327712807.mp4
+6922868291168_20240412-112736_back_returnGood_70f75407b7ae_4540_17327712807.mp4
+6922868291168_20240412-112736_front_returnGood_70f75407b7ae_4540_17327712807.mp4
+6923644286293_20240412-114002_back_addGood_70f75407b7ae_1535_17327712807.mp4
+6923644286293_20240412-114002_front_addGood_70f75407b7ae_1535_17327712807.mp4
+6923644286293_20240412-114012_back_returnGood_70f75407b7ae_1535_17327712807.mp4
+6923644286293_20240412-114012_front_returnGood_70f75407b7ae_1535_17327712807.mp4
+6924743915824_20240412-104437_back_addGood_70f754088050_455_17788571404.mp4
+6924743915824_20240412-104437_front_addGood_70f754088050_455_17788571404.mp4
+6924743915824_20240412-104448_back_returnGood_70f754088050_455_17788571404.mp4
+6924743915824_20240412-104448_front_returnGood_70f754088050_455_17788571404.mp4
+6924743915824_20240412-113553_back_addGood_70f75407b7ae_920_17327712807.mp4
+6924743915824_20240412-113553_front_addGood_70f75407b7ae_920_17327712807.mp4
+6924743915824_20240412-113603_back_returnGood_70f75407b7ae_920_17327712807.mp4
+6924743915824_20240412-113603_front_returnGood_70f75407b7ae_920_17327712807.mp4
+6928804011173_20240412-105808_back_addGood_70f754088050_915_17788571404.mp4
+6928804011173_20240412-105808_front_addGood_70f754088050_915_17788571404.mp4
+6928804011173_20240412-105818_back_returnGood_70f754088050_910_17788571404.mp4
+6928804011173_20240412-105818_front_returnGood_70f754088050_910_17788571404.mp4
+6934665095108_20240412-114106_back_addGood_70f75407b7ae_885_17327712807.mp4
+6934665095108_20240412-114106_front_addGood_70f75407b7ae_885_17327712807.mp4
+6934665095108_20240412-114116_back_returnGood_70f75407b7ae_885_17327712807.mp4
+6934665095108_20240412-114116_front_returnGood_70f75407b7ae_885_17327712807.mp4
+6935270642121_20240412-111602_back_addGood_70f75407b7ae_540_17327712807.mp4
+6935270642121_20240412-111602_front_addGood_70f75407b7ae_540_17327712807.mp4
+6935270642121_20240412-111614_back_returnGood_70f75407b7ae_540_17327712807.mp4
+6935270642121_20240412-111614_front_returnGood_70f75407b7ae_540_17327712807.mp4
+6952074634794_20240412-104633_back_addGood_70f754088050_855_17788571404.mp4
+6952074634794_20240412-104633_front_addGood_70f754088050_855_17788571404.mp4
+6952074634794_20240412-104700_back_returnGood_70f754088050_855_17788571404.mp4
+6952074634794_20240412-104700_front_returnGood_70f754088050_855_17788571404.mp4
+6952074634794_20240412-113515_back_addGood_70f75407b7ae_595_17327712807.mp4
+6952074634794_20240412-113515_front_addGood_70f75407b7ae_595_17327712807.mp4
+6952074634794_20240412-113524_back_returnGood_70f75407b7ae_595_17327712807.mp4
+6952074634794_20240412-113524_front_returnGood_70f75407b7ae_595_17327712807.mp4
+6972378998200_20240412-111721_back_addGood_70f75407b7ae_870_17327712807.mp4
+6972378998200_20240412-111721_front_addGood_70f75407b7ae_870_17327712807.mp4
+6972378998200_20240412-111741_back_returnGood_70f75407b7ae_865_17327712807.mp4
+6972378998200_20240412-111741_front_returnGood_70f75407b7ae_865_17327712807.mp4

tracking/matching/视频分类/视频文件命名规则.txt

@@ -0,0 +1,12 @@
+采集文件名字段规则：
+230537101280010007_20240411-144945_back_returnGood_70f75407b7ae_565_17788571404.mp4
+
+String targetName = 
+	barCode + "_" （条形码字段）
+	+ recordFileName  + "_" （文件名字段：时间格式精确到秒）
+	+ "back/front"+ "_" （后/前摄字段）
+	+ "addGood/returnGood"+ "_"（加/退购字段）
+	+ macId + "_" （mac地址字段：去除中间冒号）
+	+ Math.abs(goodsWeight) + "_" （商品重量字段：变化的绝对值）
+	+ user.phone （采集人手机号字段）
+	+ ".mp4";

tracking/matching/视频分类/较暗.txt

@@ -0,0 +1,6 @@
+6920152400630_20240412-151024_back_addGood_70f754088050_580_13725988807.mp4
+6920152400630_20240412-151024_front_addGood_70f754088050_580_13725988807.mp4
+6920152400630_20240412-151036_front_returnGood_70f754088050_580_13725988807.mp4
+6920459905012_20240412-150815_back_addGood_70f754088050_550_13725988807.mp4
+6920459905012_20240412-150815_front_addGood_70f754088050_550_13725988807.mp4
+6920459905012_20240412-150826_front_returnGood_70f754088050_550_13725988807.mp4

tracking/shopcart/cart_program/carttempt.py

@@ -0,0 +1,151 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Tue Sep 19 18:17:55 2023
+
+@author: ym
+"""
+
+import cv2
+import os
+import numpy as np
+
+
+def tempt_add_adjc():
+    
+    temp = cv2.imread("img.png")
+    
+    path = r"D:\DeepLearning\yolov5\runs\trajectory"
+    patr = r"D:\DeepLearning\yolov5\tracking\result"
+    for filename in os.listdir(path):
+        imgpath = os.path.join(path, filename)
+        
+        img = cv2.imread(imgpath)
+        
+        img1 = cv2.add(img, temp)
+        
+        img1path = os.path.join(patr, filename)
+        cv2.imwrite(img1path, img1)
+        
+def temp_add_boarder():
+    temp = cv2.imread("cartedge.png")
+    temp[640:, 0:20, :] = 255
+    temp[640:, -20:, :] = 255
+    temp[-20:, :, :] = 255
+    
+    cv2.imwrite("cartboarder.png", temp)
+
+    
+def create_front_temp():
+    image = cv2.imread("image_front.png")
+    Height, Width = image.shape[:2]
+    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+    thresh, binary = cv2.threshold(gray, 1, 255, cv2.THRESH_BINARY_INV)
+    board = cv2.bitwise_not(binary)
+    contours, _ = cv2.findContours(board, cv2.RETR_LIST, cv2.CHAIN_APPROX_NONE)
+    
+    k = 0
+    for cnt in contours: 
+        img = np.zeros((Height, Width), dtype=np.uint8)
+        cv2.drawContours(img, [cnt], -1, 255, 3)
+        k += 1
+        cv2.imwrite(f"fronttemp_{k}.png", img)
+    
+    imgshow = cv2.drawContours(image, contours, -1, (0,255,0), 3)
+    cv2.imwrite("board_ftmp_line.png", imgshow)
+    
+    # cv2.imwrite("4.png", board)
+    # cv2.imwrite("1.png", gray)
+    # cv2.imwrite("2.png", binary)
+
+
+    
+
+def create_back_temp():
+    '''
+    image1.png：从中获取轮廓的初始图像
+    image2.png：主要用于显示效果
+    Return：img.png
+    '''
+
+    image = cv2.imread("image1.png")
+    
+    Height, Width = image.shape[:2]
+    
+    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+    
+    gray[:405, :] = 0
+    thresh, binary = cv2.threshold(gray, 254, 255, cv2.THRESH_BINARY)
+    cv2.imwrite("shopcart.png", binary)
+    
+    imgshow = cv2.cvtColor(binary, cv2.COLOR_GRAY2BGR)
+    
+    
+    
+    contours, _ = cv2.findContours(binary, cv2.RETR_LIST, cv2.CHAIN_APPROX_NONE)
+    
+    imgshow = cv2.drawContours(imgshow, contours, -1, (0,255,0), 1)
+    cv2.imwrite("imgshow.png", imgshow)
+    
+    
+    image2 = cv2.imread("image2.png")
+    image2 = cv2.drawContours(image2, contours, -1, (0,255,0), 3)
+    
+    
+    for cnt in contours:
+        _, start, _, num = cv2.boundingRect(cnt) 
+        
+        x1 = (cnt[:, 0, 0] != 0)
+        x2 = (cnt[:, 0, 0] != Width-1)
+        x3 = (cnt[:, 0, 1] != Height-1)
+        x = (x1 & x2) & x3
+        idx = np.where(x)
+        cntx = cnt[idx, :, :][0]
+        
+        cnt1 = cntx[:,0,:].copy()
+        
+        cntx[:, 0, 1] -= 60
+        cnt2 = cntx[:,0,:].copy()
+        
+        
+        cv2.drawContours(image2,[cntx], 0, (0,0,255), 2)
+        
+        
+        
+    img = np.zeros(gray.shape, np.uint8)
+    for i in range(len(cnt1)):
+        x1, y1 = cnt1[i]
+        x2, y2 = cnt2[i]
+        cv2.rectangle(img, (x1-1, y1-1), (x1+1, y1+1), 255, 1)
+        cv2.rectangle(img, (x2-1, y2-1), (x2+1, y2+1), 255, 1)
+        
+        
+        
+    cv2.imwrite("img.png", img)    
+    
+    
+if __name__ == "__main__":
+    # create_back_temp()  
+    # temp_add_boarder()
+    # tempt_add_adjc()
+    
+    create_front_temp()
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    
+    

tracking/shopcart/cart_program/新建文本文档.txt

@@ -0,0 +1 @@
+求取购物车轮廓，判断任一点是否在购物车内、是否在购物车边框附近

tracking/test_merge.py

@@ -0,0 +1,173 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Fri Feb 23 11:04:48 2024
+
+@author: ym
+"""
+import numpy as np
+import cv2
+from scipy.spatial.distance import cdist
+# from trackers.utils import matching
+
+def readDict(boxes, feat_dicts):
+    feat = []
+    for i in range(boxes.shape[0]):   
+        tid, fid, bid = int(boxes[i, 4]), int(boxes[i, 7]), int(boxes[i, 8])
+        feat.append(feat_dicts[fid][bid])
+        
+        # img = feat_dicts[fid][f'{bid}_img']
+        # cv2.imwrite(f'./result/imgs/{tid}_{fid}_{bid}.png', img)
+    
+    return np.asarray(feat, dtype=np.float32)
+
+
+
+def track_equal_track(atrack, btrack, feat_dicts):
+    # boxes: [x, y, w, h, track_id, score, cls, frame_index, box_index]
+    aboxes = atrack.boxes
+    bboxes = btrack.boxes
+    
+    ''' 1. 判断轨迹在时序上是否有交集 '''
+    afids = aboxes[:, 7].astype(np.int_)
+    bfids = bboxes[:, 7].astype(np.int_)
+    # 帧索引交集
+    interfid = set(afids).intersection(set(bfids))
+    
+    # 或者直接判断帧索引是否有交集，返回 Ture or False
+    # interfid = set(afids).isdisjoint(set(bfids))
+    
+    
+    ''' 2. 轨迹空间iou'''
+    alabel = np.array([0] * afids.size, dtype=np.int_)
+    blabel = np.array([1] * bfids.size, dtype=np.int_)
+    
+    label = np.concatenate((alabel, blabel), axis=0)
+    fids = np.concatenate((afids, bfids), axis=0)
+    indices = np.argsort(fids)
+    idx_pair = []
+    for i in range(len(indices)-1):
+        idx1, idx2 = indices[i], indices[i+1]
+        if label[idx1] != label[idx2] and fids[idx2] - fids[idx1] == 1:
+            if label[idx1] == 0:
+                a_idx = idx1
+                b_idx = idx2-alabel.size
+            else:
+                a_idx = idx2
+                b_idx = idx1-alabel.size 
+            
+            idx_pair.append((a_idx, b_idx))
+    
+    ious = []
+    for a, b in idx_pair:
+        abox, bbox = aboxes[a, :], bboxes[b, :]
+        
+        xa1, ya1 = abox[0] - abox[2]/2, abox[1] - abox[3]/2 
+        xa2, ya2 = abox[0] + abox[2]/2, abox[1] + abox[3]/2
+        
+        xb1, yb1 = bbox[0] - bbox[2]/2, bbox[1] - bbox[3]/2
+        xb2, yb2 = bbox[0] + bbox[2]/2, bbox[1] + bbox[3]/2 
+        
+        
+        inter = (np.minimum(xb2, xa2) - np.maximum(xb1, xa1)).clip(0) * \
+                     (np.minimum(yb2, ya2) - np.maximum(yb1, ya1)).clip(0)
+                     
+        # Union Area
+        box1_area = abox[2] * abox[3]
+        box2_area = bbox[2] * bbox[3]
+        union = box1_area + box2_area - inter + 1e-6
+
+        ious.append(inter/union)
+    
+    ''' 3. 轨迹特征相似度判断'''
+    afeat = readDict(aboxes, feat_dicts)
+    bfeat = readDict(bboxes, feat_dicts)
+    feat = np.concatenate((afeat, bfeat), axis=0)
+    
+    emb_simil = 1-np.maximum(0.0, cdist(feat, feat, 'cosine'))
+    emb_ = 1-cdist(np.mean(afeat, axis=0)[None, :], np.mean(bfeat, axis=0)[None, :], 'cosine')
+     
+    cont1 = False if len(interfid) else True
+    cont2 = all(iou>0.5 for iou in ious)
+    cont3 = emb_[0, 0]>0.75
+    
+    cont = cont1 and cont2 and cont3
+    
+    
+    
+    
+    
+    
+    
+    return cont
+
+
+
+def track_equal_str(atrack, btrack):
+    if atrack == btrack:
+        return True
+    else:
+        return False
+
+
+def merge_track(Residual):
+    out_list = []
+    alist = [t for t in Residual]
+    while alist:
+        atrack = alist[0]
+        cur_list = []
+        cur_list.append(atrack)
+        alist.pop(0)
+        
+        blist = [b for b in alist]
+        alist = []
+        for btrack in blist:
+            if track_equal_str(atrack, btrack):
+                cur_list.append(btrack)
+            else:
+                alist.append(btrack)
+                
+        out_list.append(cur_list)
+    return out_list
+    
+def main():
+    Residual = ['a', 'b', 'c', 'd', 'a', 'b', 'c', 'b', 'c', 'd']
+    out_list = merge_track(Residual)
+    
+    print(Residual)
+    print(out_list)
+
+if __name__ == "__main__": 
+    
+    main()
+
+
+
+
+# =============================================================================
+# for i, atrack in enumerate(input_list):
+#     cur_list = []
+#     cur_list.append(atrack)
+#     del input_list[i]
+#     
+#     for j, btrack in enumerate(input_list):
+#         if track_equal(atrack, btrack):
+#             cur_list.append(btrack)
+#             del input_list[j]
+#     
+#     out_list.append(cur_list)
+# =============================================================================
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+   

tracking/test_tracking.py

@@ -0,0 +1,149 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Wed Sep 20 17:33:00 2023
+
+@author: ym
+"""
+
+import cv2
+import os
+import numpy as np
+import time
+import pickle
+import matplotlib.pyplot as plt
+import pandas as pd 
+
+from scipy.spatial.distance import cdist
+
+from pathlib import Path
+
+
+
+# ================= using for import ultralytics
+import sys
+sys.path.append(r"D:\yolov5track")
+from utils.gen import Profile
+
+from dotrack.dotracks_back import doBackTracks
+from dotrack.dotracks_front import doFrontTracks 
+from utils.drawtracks import draw5points, drawTrack, drawtracefeat, plot_frameID_y2, drawFeatures, draw_all_trajectories
+
+# from datetime import datetime
+# from utils.proBoxes import boxes_add_fid
+# from utils.plotting import boxing_img  #, Annotator, colors,
+# from utils import Boxes, IterableSimpleNamespace, yaml_load
+# from trackers import BOTSORT, BYTETracker
+# from utils.mergetrack import track_equal_track
+# from utils.basetrack import MoveState, ShoppingCart, doTracks
+
+
+def detect_start_end(bboxes, features_dict, filename):
+    
+    boxes = np.empty(shape=(0, 9), dtype = np.float)
+    if filename.find("back") >= 0:
+        vts = doBackTracks(bboxes, features_dict)
+        vtx = [t for t in vts if t.cls != 0]
+        
+        for track in vtx:
+            if track.moving_index.size:
+                boxes = np.concatenate((boxes, track.moving_index), axis=0)
+                
+    elif filename.find("front") >= 0:
+        vts = doFrontTracks(bboxes, features_dict)
+        vtx = [t for t in vts if t.cls != 0]
+        
+        for track in vtx:
+            for start, end in track.dynamic_y2:
+                boxes = np.concatenate((boxes, track.boxes[start:end+1, :]), axis=0)    
+            for start, end in track.dynamic_y1:
+                boxes = np.concatenate((boxes, track.boxes[start:end+1, :]), axis=0)
+    
+    start = np.min(boxes[:, 0])
+    end = np.max(boxes[:, 1])
+    
+    if start > 5:
+        start = start - 5
+    else:
+        start = 0
+    
+    return start, end
+
+def save_subimgs(vts, file):
+    imgdir = Path(f'./result/imgs/{file}')
+    if not imgdir.exists():
+        imgdir.mkdir(parents=True, exist_ok=True)
+    
+    for i, track in enumerate(vts.Residual):  
+        boxes = track.boxes
+        for ii in range(len(boxes)):
+            tid, fid, bid = int(boxes[ii, 4]), int(boxes[ii, 7]), int(boxes[ii, 8])
+            
+            img = vts.TracksDict[f"frame_{fid}"]["imgs"][bid]
+            # feat = TracksDict[f"frame_{fid}"]["feats"][bid]
+            # box = TracksDict[f"frame_{fid}"]["boxes"][bid]
+            
+            cv2.imwrite(str(imgdir) + f"/{tid}_{fid}_{bid}.png", img)
+
+def have_tracked():
+    trackdict = r'./data/trackdicts'
+    alltracks = []
+    k = 0
+    gt = Profile()
+    for filename in os.listdir(trackdict):
+        filename = 'test_20240402-173935_6920152400975_front_174037379.pkl'
+        file, ext = os.path.splitext(filename)
+        filepath = os.path.join(trackdict, filename)
+        TracksDict = np.load(filepath, allow_pickle=True)
+
+        bboxes = TracksDict['TrackBoxes']
+        with gt:
+            if filename.find("front") >= 0:
+                vts = doFrontTracks(bboxes, TracksDict)
+                vts.classify()
+                
+                save_subimgs(vts, file)
+
+                plt = plot_frameID_y2(vts)
+                
+                savedir = save_dir.joinpath(f'{file}_y2.png') 
+                
+                plt.savefig(savedir)  
+                plt.close()
+            else:
+                vts = doBackTracks(bboxes, TracksDict)
+                vts.classify()
+                alltracks.append(vts)
+                
+                save_subimgs(vts, file)
+                edgeline = cv2.imread("./shopcart/cart_tempt/edgeline.png")
+                draw_all_trajectories(vts, edgeline, save_dir, filename)
+        print(file+f" need time: {gt.dt:.2f}s")
+        
+        
+        
+        # k += 1
+        # if k==1:
+        #     break
+    
+    if len(alltracks):
+        drawFeatures(alltracks, save_dir)
+         
+    
+    
+if __name__ == "__main__": 
+    # now = datetime.now()
+    # time_string = now.strftime("%Y%m%d%H%M%S")[:8]
+    
+    save_dir = Path('./result/tracks')
+    if not save_dir.exists():
+        save_dir.mkdir(parents=True, exist_ok=True)
+
+    have_tracked()    
+   
+
+    
+    
+    
+    
+    
+    

tracking/trackers/README.md

@@ -0,0 +1,94 @@
+# Tracker
+
+## Supported Trackers
+
+- [x] ByteTracker
+- [x] BoT-SORT
+
+## Usage
+
+### python interface:
+
+You can use the Python interface to track objects using the YOLO model.
+
+```python
+from ultralytics import YOLO
+
+model = YOLO("yolov8n.pt")  # or a segmentation model .i.e yolov8n-seg.pt
+model.track(
+    source="video/streams",
+    stream=True,
+    tracker="botsort.yaml",  # or 'bytetrack.yaml'
+    show=True,
+)
+```
+
+You can get the IDs of the tracked objects using the following code:
+
+```python
+from ultralytics import YOLO
+
+model = YOLO("yolov8n.pt")
+
+for result in model.track(source="video.mp4"):
+    print(
+        result.boxes.id.cpu().numpy().astype(int)
+    )  # this will print the IDs of the tracked objects in the frame
+```
+
+If you want to use the tracker with a folder of images or when you loop on the video frames, you should use the `persist` parameter to tell the model that these frames are related to each other so the IDs will be fixed for the same objects. Otherwise, the IDs will be different in each frame because in each loop, the model creates a new object for tracking, but the `persist` parameter makes it use the same object for tracking.
+
+```python
+import cv2
+from ultralytics import YOLO
+
+cap = cv2.VideoCapture("video.mp4")
+model = YOLO("yolov8n.pt")
+while True:
+    ret, frame = cap.read()
+    if not ret:
+        break
+    results = model.track(frame, persist=True)
+    boxes = results[0].boxes.xyxy.cpu().numpy().astype(int)
+    ids = results[0].boxes.id.cpu().numpy().astype(int)
+    for box, id in zip(boxes, ids):
+        cv2.rectangle(frame, (box[0], box[1]), (box[2], box[3]), (0, 255, 0), 2)
+        cv2.putText(
+            frame,
+            f"Id {id}",
+            (box[0], box[1]),
+            cv2.FONT_HERSHEY_SIMPLEX,
+            1,
+            (0, 0, 255),
+            2,
+        )
+    cv2.imshow("frame", frame)
+    if cv2.waitKey(1) & 0xFF == ord("q"):
+        break
+```
+
+## Change tracker parameters
+
+You can change the tracker parameters by editing the `tracker.yaml` file which is located in the ultralytics/cfg/trackers folder.
+
+## Command Line Interface (CLI)
+
+You can also use the command line interface to track objects using the YOLO model.
+
+```bash
+yolo detect track source=... tracker=...
+yolo segment track source=... tracker=...
+yolo pose track source=... tracker=...
+```
+
+By default, trackers will use the configuration in `ultralytics/cfg/trackers`. We also support using a modified tracker config file. Please refer to the tracker config files in `ultralytics/cfg/trackers`.
+
+## Contribute to Our Trackers Section
+
+Are you proficient in multi-object tracking and have successfully implemented or adapted a tracking algorithm with Ultralytics YOLO? We invite you to contribute to our Trackers section! Your real-world applications and solutions could be invaluable for users working on tracking tasks.
+
+By contributing to this section, you help expand the scope of tracking solutions available within the Ultralytics YOLO framework, adding another layer of functionality and utility for the community.
+
+To initiate your contribution, please refer to our [Contributing Guide](https://docs.ultralytics.com/help/contributing) for comprehensive instructions on submitting a Pull Request (PR) 🛠️. We are excited to see what you bring to the table!
+
+Together, let's enhance the tracking capabilities of the Ultralytics YOLO ecosystem 🙏!

tracking/trackers/__init__.py

@@ -0,0 +1,10 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+
+from .bot_sort import BOTSORT
+from .byte_tracker import BYTETracker
+from .track import register_tracker
+
+
+
+__all__ = 'register_tracker', 'BOTSORT', 'BYTETracker'  # allow simpler import
+

tracking/trackers/basetrack.py

@@ -0,0 +1,71 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+
+from collections import OrderedDict
+
+import numpy as np
+
+
+class TrackState:
+    """Enumeration of possible object tracking states."""
+
+    New = 0
+    Tracked = 1
+    Lost = 2
+    Removed = 3
+
+
+class BaseTrack:
+    """Base class for object tracking, handling basic track attributes and operations."""
+
+    _count = 0
+
+    track_id = 0
+    is_activated = False
+    state = TrackState.New
+
+    history = OrderedDict()
+    features = []
+    curr_feature = None
+    score = 0
+    start_frame = 0
+    frame_id = 0
+    time_since_update = 0
+
+    # Multi-camera
+    location = (np.inf, np.inf)
+
+    @property
+    def end_frame(self):
+        """Return the last frame ID of the track."""
+        return self.frame_id
+
+    @staticmethod
+    def next_id():
+        """Increment and return the global track ID counter."""
+        BaseTrack._count += 1
+        return BaseTrack._count
+
+    def activate(self, *args):
+        """Activate the track with the provided arguments."""
+        raise NotImplementedError
+
+    def predict(self):
+        """Predict the next state of the track."""
+        raise NotImplementedError
+
+    def update(self, *args, **kwargs):
+        """Update the track with new observations."""
+        raise NotImplementedError
+
+    def mark_lost(self):
+        """Mark the track as lost."""
+        self.state = TrackState.Lost
+
+    def mark_removed(self):
+        """Mark the track as removed."""
+        self.state = TrackState.Removed
+
+    @staticmethod
+    def reset_id():
+        """Reset the global track ID counter."""
+        BaseTrack._count = 0

tracking/trackers/bot_sort.py

@@ -0,0 +1,198 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+
+from collections import deque
+
+import numpy as np
+
+from .basetrack import TrackState
+from .byte_tracker import BYTETracker, STrack
+from .utils import matching
+# from .utils.gmc import GMC
+from .utils.kalman_filter import KalmanFilterXYWH
+
+from .reid.reid_interface import ReIDInterface
+from .reid.config import config
+
+class BOTrack(STrack):
+    shared_kalman = KalmanFilterXYWH()
+
+    def __init__(self, tlwh, score, cls, feat=None, feat_history=50):
+        """Initialize YOLOv8 object with temporal parameters, such as feature history, alpha and current features."""
+        super().__init__(tlwh, score, cls)
+
+        self.smooth_feat = None
+        self.curr_feat = None
+        if feat is not None:
+            self.update_features(feat)
+        self.features = deque([], maxlen=feat_history)
+        self.alpha = 0.9
+
+    def update_features(self, feat):
+        """Update features vector and smooth it using exponential moving average."""
+        feat /= np.linalg.norm(feat)
+        self.curr_feat = feat
+        if self.smooth_feat is None:
+            self.smooth_feat = feat
+        else:
+            self.smooth_feat = self.alpha * self.smooth_feat + (1 - self.alpha) * feat
+        self.features.append(feat)
+        self.smooth_feat /= np.linalg.norm(self.smooth_feat)
+
+    def predict(self):
+        """Predicts the mean and covariance using Kalman filter."""
+        mean_state = self.mean.copy()
+        if self.state != TrackState.Tracked:
+            mean_state[6] = 0
+            mean_state[7] = 0
+
+        self.mean, self.covariance = self.kalman_filter.predict(mean_state, self.covariance)
+
+    def re_activate(self, new_track, frame_id, new_id=False):
+        """Reactivates a track with updated features and optionally assigns a new ID."""
+        if new_track.curr_feat is not None:
+            self.update_features(new_track.curr_feat)
+        super().re_activate(new_track, frame_id, new_id)
+
+    def update(self, new_track, frame_id):
+        """Update the YOLOv8 instance with new track and frame ID."""
+        if new_track.curr_feat is not None:
+            self.update_features(new_track.curr_feat)
+        super().update(new_track, frame_id)
+
+    @property
+    def tlwh(self):
+        """Get current position in bounding box format `(top left x, top left y,
+        width, height)`.
+        """
+        if self.mean is None:
+            return self._tlwh.copy()
+        ret = self.mean[:4].copy()
+        ret[:2] -= ret[2:] / 2
+        return ret
+
+    @staticmethod
+    def multi_predict(stracks):
+        """Predicts the mean and covariance of multiple object tracks using shared Kalman filter."""
+        if len(stracks) <= 0:
+            return
+        multi_mean = np.asarray([st.mean.copy() for st in stracks])
+        multi_covariance = np.asarray([st.covariance for st in stracks])
+        for i, st in enumerate(stracks):
+            if st.state != TrackState.Tracked:
+                multi_mean[i][6] = 0
+                multi_mean[i][7] = 0
+        multi_mean, multi_covariance = BOTrack.shared_kalman.multi_predict(multi_mean, multi_covariance)
+        for i, (mean, cov) in enumerate(zip(multi_mean, multi_covariance)):
+            stracks[i].mean = mean
+            stracks[i].covariance = cov
+
+    def convert_coords(self, tlwh):
+        """Converts Top-Left-Width-Height bounding box coordinates to X-Y-Width-Height format."""
+        return self.tlwh_to_xywh(tlwh)
+
+    @staticmethod
+    def tlwh_to_xywh(tlwh):
+        """Convert bounding box to format `(center x, center y, width,
+        height)`.
+        """
+        ret = np.asarray(tlwh).copy()
+        ret[:2] += ret[2:] / 2
+        return ret
+
+
+class BOTSORT(BYTETracker):
+
+    def __init__(self, args, frame_rate=30):
+        """Initialize YOLOv8 object with ReID module and GMC algorithm."""
+        super().__init__(args, frame_rate)
+        # ReID module
+        self.proximity_thresh = args.proximity_thresh
+        self.appearance_thresh = args.appearance_thresh
+
+        if args.with_reid:
+            # Haven't supported BoT-SORT(reid) yet
+            self.encoder = ReIDInterface(config)
+        
+        # self.gmc = GMC(method=args.gmc_method)     # commented by WQG
+
+    def get_kalmanfilter(self):
+        """Returns an instance of KalmanFilterXYWH for object tracking."""
+        return KalmanFilterXYWH()
+
+    def init_track(self, dets, scores, cls, imgs):
+        """Initialize track with detections, scores, and classes."""
+        if len(dets) == 0:
+            return []
+        if self.args.with_reid and self.encoder is not None:
+            features_keep = self.encoder.inference(imgs, dets)
+            return [BOTrack(xyxy, s, c, f) for (xyxy, s, c, f) in zip(dets, scores, cls, features_keep)]  # detections
+        else:
+            return [BOTrack(xyxy, s, c) for (xyxy, s, c) in zip(dets, scores, cls)]  # detections
+
+    def get_dists(self, tracks, detections):
+        """Get distances between tracks and detections using IoU and (optionally) ReID embeddings."""
+        dists = matching.iou_distance(tracks, detections)
+        # proximity_thresh 应该设较大的值，表示只有两个boxes离得较远时，不考虑reid特征
+        dists_mask = (dists > self.proximity_thresh)
+
+        # TODO: mot20
+        # if not self.args.mot20:
+        dists = matching.fuse_score(dists, detections)
+
+        if self.args.with_reid and self.encoder is not None:
+            emb_dists = matching.embedding_distance(tracks, detections) / 2.0
+            emb_dists[emb_dists > self.appearance_thresh] = 1.0
+            emb_dists[dists_mask] = 1.0
+            dists = np.minimum(dists, emb_dists)
+  
+        return dists
+    
+    def get_dists_1(self, tracks, detections):
+        """Get distances between tracks and detections using IoU and (optionally) ReID embeddings."""
+        iou_dists = matching.iou_distance(tracks, detections)
+        iou_dists_mask = (iou_dists>0.9)
+        
+        iou_dists = matching.fuse_score(iou_dists, detections)
+        weight = 0.4
+        if self.args.with_reid and self.encoder is not None:
+            emb_dists = matching.embedding_distance(tracks, detections)
+            
+            '''============ iou_dists 和 emb_dists 融合有两种策略 ==========='''
+            '''1. reid 相似度阈值，低于该值的两 boxes 图像不可能是同一对象，需要确定一个合理的可信阈值
+               2. iou 的约束为若约束，故 iou_dists 应设置为较大的值
+            '''
+            emb_dists_mask = (emb_dists > 0.85)
+            iou_dists[emb_dists_mask] = 1
+            emb_dists[iou_dists_mask] = 1
+  
+            dists = np.minimum(iou_dists, emb_dists)
+            '''2. embed 阈值'''
+            # dists = (1-weight)*iou_dists + weight*emb_dists
+        else:
+            
+            dists = iou_dists.copy()
+  
+        return dists
+
+
+
+
+
+
+
+    def multi_predict(self, tracks):
+        """Predict and track multiple objects with YOLOv8 model."""
+        BOTrack.multi_predict(tracks)
+        
+        
+    def get_result(self):
+        '''written by WQG'''
+        activate_tracks = np.asarray([x.tlbr.tolist() + [x.track_id, x.score, x.cls, x.idx] 
+                                      for x in self.tracked_stracks if x.is_activated], dtype=np.float32)
+        
+        track_features = []
+        if self.args.with_reid and self.encoder is not None:
+            track_features = np.asarray([x.curr_feat for x in self.tracked_stracks if x.is_activated], dtype=np.float32)
+            
+                
+        return (activate_tracks, track_features)

tracking/trackers/byte_tracker.py

@@ -0,0 +1,464 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+
+import numpy as np
+
+from .basetrack import BaseTrack, TrackState
+from .utils import matching
+from .utils.kalman_filter import KalmanFilterXYAH
+
+
+def dists_update(dists, strack_pool, detections):
+    '''written by WQG'''
+    
+    if len(strack_pool) and len(detections):
+        # alabel = np.array([int(stack.cls) if int(stack.cls)==0 or int(stack.cls)==9 else -1 for stack in strack_pool])
+        # blabel = np.array([int(stack.cls) if int(stack.cls)==0 or int(stack.cls)==9 else -1 for stack in detections])
+
+        alabel = np.array([int(stack.cls) for stack in strack_pool])
+        blabel = np.array([int(stack.cls) for stack in detections])
+        amlabel = np.expand_dims(alabel, axis=1).repeat(len(detections),axis=1)
+        bmlabel = np.expand_dims(blabel, axis=0).repeat(len(strack_pool),axis=0)
+        dist_label = 1 - (bmlabel == amlabel)
+        dists = np.where(dists > dist_label, dists, dist_label)
+    return dists
+
+
+class STrack(BaseTrack):
+    shared_kalman = KalmanFilterXYAH()
+
+    def __init__(self, tlwh, score, cls):
+        """wait activate."""
+        self._tlwh = np.asarray(self.tlbr_to_tlwh(tlwh[:-1]), dtype=np.float32)
+        self.kalman_filter = None
+        self.mean, self.covariance = None, None
+        self.is_activated = False
+        
+        self.first_find = False    ###
+
+        self.score = score
+        self.tracklet_len = 0
+        self.cls = cls
+        self.idx = tlwh[-1]
+
+    def predict(self):
+        """Predicts mean and covariance using Kalman filter."""
+        mean_state = self.mean.copy()
+        if self.state != TrackState.Tracked:
+            mean_state[7] = 0
+        self.mean, self.covariance = self.kalman_filter.predict(mean_state, self.covariance)
+
+    @staticmethod
+    def multi_predict(stracks):
+        """Perform multi-object predictive tracking using Kalman filter for given stracks."""
+        if len(stracks) <= 0:
+            return
+        multi_mean = np.asarray([st.mean.copy() for st in stracks])
+        multi_covariance = np.asarray([st.covariance for st in stracks])
+        for i, st in enumerate(stracks):
+            if st.state != TrackState.Tracked:
+                multi_mean[i][7] = 0
+        multi_mean, multi_covariance = STrack.shared_kalman.multi_predict(multi_mean, multi_covariance)
+        for i, (mean, cov) in enumerate(zip(multi_mean, multi_covariance)):
+            stracks[i].mean = mean
+            stracks[i].covariance = cov
+
+    @staticmethod
+    def multi_gmc(stracks, H=np.eye(2, 3)):
+        """Update state tracks positions and covariances using a homography matrix."""
+        if len(stracks) > 0:
+            multi_mean = np.asarray([st.mean.copy() for st in stracks])
+            multi_covariance = np.asarray([st.covariance for st in stracks])
+
+            R = H[:2, :2]
+            R8x8 = np.kron(np.eye(4, dtype=float), R)
+            t = H[:2, 2]
+
+            for i, (mean, cov) in enumerate(zip(multi_mean, multi_covariance)):
+                mean = R8x8.dot(mean)
+                mean[:2] += t
+                cov = R8x8.dot(cov).dot(R8x8.transpose())
+
+                stracks[i].mean = mean
+                stracks[i].covariance = cov
+
+    def activate(self, kalman_filter, frame_id):
+        """Start a new tracklet."""
+        self.kalman_filter = kalman_filter
+        self.track_id = self.next_id()
+        self.mean, self.covariance = self.kalman_filter.initiate(self.convert_coords(self._tlwh))
+
+        self.tracklet_len = 0
+        self.state = TrackState.Tracked
+        if frame_id == 1:
+            self.is_activated = True
+        else:
+            self.first_find = True      ### Add by WQG  
+        self.frame_id = frame_id
+        self.start_frame = frame_id
+
+    def re_activate(self, new_track, frame_id, new_id=False):
+        """Reactivates a previously lost track with a new detection."""
+        self.mean, self.covariance = self.kalman_filter.update(self.mean, self.covariance,
+                                                               self.convert_coords(new_track.tlwh))
+        self.tracklet_len = 0
+        self.state = TrackState.Tracked
+        self.is_activated = True
+        self.frame_id = frame_id
+        if new_id:
+            self.track_id = self.next_id()
+        self.score = new_track.score
+        self.cls = new_track.cls
+        self.idx = new_track.idx
+        
+        self._tlwh = new_track._tlwh
+
+    def update(self, new_track, frame_id):
+        """
+        Update a matched track
+        :type new_track: STrack
+        :type frame_id: int
+        :return:
+        """
+        self.frame_id = frame_id
+        self.tracklet_len += 1
+
+        new_tlwh = new_track.tlwh
+        self.mean, self.covariance = self.kalman_filter.update(self.mean, self.covariance,
+                                                               self.convert_coords(new_tlwh))
+        self.state = TrackState.Tracked
+        self.is_activated = True
+
+        self.score = new_track.score
+        self.cls = new_track.cls
+        self.idx = new_track.idx
+        
+        self._tlwh = new_track._tlwh
+        
+
+    def convert_coords(self, tlwh):
+        """Convert a bounding box's top-left-width-height format to its x-y-angle-height equivalent."""
+        return self.tlwh_to_xyah(tlwh)
+
+    @property
+    def tlwh(self):
+        """Get current position in bounding box format `(top left x, top left y,
+        width, height)`.
+        """
+        if self.mean is None:
+            return self._tlwh.copy()
+        ret = self.mean[:4].copy()
+        ret[2] *= ret[3]
+        ret[:2] -= ret[2:] / 2
+        return ret
+
+    @property
+    def tlbr(self):
+        """Convert bounding box to format `(min x, min y, max x, max y)`, i.e.,
+        `(top left, bottom right)`.
+        """
+        ret = self.tlwh.copy()
+        ret[2:] += ret[:2]
+        return ret
+
+    @staticmethod
+    def tlwh_to_xyah(tlwh):
+        """Convert bounding box to format `(center x, center y, aspect ratio,
+        height)`, where the aspect ratio is `width / height`.
+        """
+        ret = np.asarray(tlwh).copy()
+        ret[:2] += ret[2:] / 2
+        ret[2] /= ret[3]
+        return ret
+
+    @staticmethod
+    def tlbr_to_tlwh(tlbr):
+        """Converts top-left bottom-right format to top-left width height format."""
+        ret = np.asarray(tlbr).copy()
+        ret[2:] -= ret[:2]
+        return ret
+
+    @staticmethod
+    def tlwh_to_tlbr(tlwh):
+        """Converts tlwh bounding box format to tlbr format."""
+        ret = np.asarray(tlwh).copy()
+        ret[2:] += ret[:2]
+        return ret
+
+    def __repr__(self):
+        """Return a string representation of the BYTETracker object with start and end frames and track ID."""
+        return f'OT_{self.track_id}_({self.start_frame}-{self.end_frame})'
+
+
+class BYTETracker:
+
+    def __init__(self, args, frame_rate=30):
+        """Initialize a YOLOv8 object to track objects with given arguments and frame rate."""
+        self.tracked_stracks = []  # type: list[STrack]
+        self.lost_stracks = []  # type: list[STrack]
+        self.removed_stracks = []  # type: list[STrack]
+
+        self.frame_id = 0
+        self.args = args
+        self.max_time_lost = int(frame_rate / 30.0 * args.track_buffer)
+        self.kalman_filter = self.get_kalmanfilter()
+        self.reset_id()
+        
+        # Add by WQG
+        self.args.new_track_thresh = 0.5
+        
+
+    def update(self, results, img=None):
+        """Updates object tracker with new detections and returns tracked object bounding boxes."""
+        self.frame_id += 1
+        activated_stracks = []
+        refind_stracks = []
+        lost_stracks = []
+        removed_stracks = []
+
+        scores = results.conf
+        cls = results.cls
+        
+# =============================================================================
+#         # get xyxy and add index
+#         bboxes = results.xyxy
+#         bboxes = np.concatenate([bboxes, np.arange(len(bboxes)).reshape(-1, 1)], axis=-1)
+# =============================================================================
+        bboxes = results.xyxyb
+        
+        
+        remain_inds = scores > self.args.track_high_thresh
+        inds_low = scores > self.args.track_low_thresh
+        inds_high = scores < self.args.track_high_thresh
+
+        inds_second = np.logical_and(inds_low, inds_high)
+        dets_second = bboxes[inds_second]
+        dets = bboxes[remain_inds]
+        scores_keep = scores[remain_inds]
+        scores_second = scores[inds_second]
+        cls_keep = cls[remain_inds]
+        cls_second = cls[inds_second]
+
+        detections = self.init_track(dets, scores_keep, cls_keep, img)
+        
+        # Add newly detected tracklets to tracked_stracks
+        unconfirmed = []
+        tracked_stracks = []  # type: list[STrack]
+        for track in self.tracked_stracks:
+            if not track.is_activated:
+                unconfirmed.append(track)
+            else:
+                tracked_stracks.append(track)
+        
+        
+        # Step 2: First association, with high score detection boxes
+        strack_pool = self.joint_stracks(tracked_stracks, self.lost_stracks)
+        # Predict the current location with KF
+        self.multi_predict(strack_pool)
+        
+# ============================================================= 没必要gmc，WQG
+#         if hasattr(self, 'gmc') and img is not None:
+#             warp = self.gmc.apply(img, dets)
+#             STrack.multi_gmc(strack_pool, warp)
+#             STrack.multi_gmc(unconfirmed, warp)
+# =============================================================================
+
+        dists = self.get_dists_1(strack_pool, detections)
+        
+        '''written by WQG for different class'''
+        dists = dists_update(dists, strack_pool, detections)
+
+        matches, u_track, u_detection = matching.linear_assignment(dists, thresh=self.args.match_thresh)
+        for itracked, idet in matches:
+            track = strack_pool[itracked]
+            det = detections[idet]
+            if track.state == TrackState.Tracked:
+                track.update(det, self.frame_id)
+                activated_stracks.append(track)
+            else:
+                track.re_activate(det, self.frame_id, new_id=False)
+                refind_stracks.append(track)
+        
+        
+        # Step 3: Second association, with low score detection boxes
+        # association the untrack to the low score detections
+        detections_second = self.init_track(dets_second, scores_second, cls_second, img)
+        r_tracked_stracks = [strack_pool[i] for i in u_track if strack_pool[i].state == TrackState.Tracked]
+        
+        # TODO
+        dists = matching.iou_distance(r_tracked_stracks, detections_second)
+        '''written by WQG for different class'''
+        dists = dists_update(dists, r_tracked_stracks, detections_second)
+        
+        matches, u_track, u_detection_second = matching.linear_assignment(dists, thresh=0.5)
+        for itracked, idet in matches:
+            track = r_tracked_stracks[itracked]
+            det = detections_second[idet]
+            if track.state == TrackState.Tracked:
+                track.update(det, self.frame_id)
+                activated_stracks.append(track)
+            else:
+                track.re_activate(det, self.frame_id, new_id=False)
+                refind_stracks.append(track)
+
+        for it in u_track:
+            track = r_tracked_stracks[it]
+            if track.state != TrackState.Lost:
+                track.mark_lost()
+                lost_stracks.append(track)
+        
+        # Deal with unconfirmed tracks, usually tracks with only one beginning frame
+        detections = [detections[i] for i in u_detection]
+        dists = self.get_dists_1(unconfirmed, detections)
+        '''written by WQG for different class'''
+        dists = dists_update(dists, unconfirmed, detections)
+        
+        matches, u_unconfirmed, u_detection = matching.linear_assignment(dists, thresh=0.7)
+        for itracked, idet in matches:
+            unconfirmed[itracked].update(detections[idet], self.frame_id)
+            activated_stracks.append(unconfirmed[itracked])
+        for it in u_unconfirmed:
+            track = unconfirmed[it]
+            if self.frame_id - track.end_frame > 2:   # Add by WQG
+                track.mark_removed()
+                removed_stracks.append(track)
+        # Step 4: Init new stracks
+        for inew in u_detection:
+            track = detections[inew]
+            if track.score < self.args.new_track_thresh:
+                continue
+            track.activate(self.kalman_filter, self.frame_id)
+            activated_stracks.append(track)
+        # Step 5: Update state
+        for track in self.lost_stracks:
+            if self.frame_id - track.end_frame > self.max_time_lost:
+                track.mark_removed()
+                removed_stracks.append(track)
+
+        self.tracked_stracks = [t for t in self.tracked_stracks if t.state == TrackState.Tracked]
+        self.tracked_stracks = self.joint_stracks(self.tracked_stracks, activated_stracks)
+        self.tracked_stracks = self.joint_stracks(self.tracked_stracks, refind_stracks)
+        self.lost_stracks = self.sub_stracks(self.lost_stracks, self.tracked_stracks)
+        self.lost_stracks.extend(lost_stracks)
+        self.lost_stracks = self.sub_stracks(self.lost_stracks, self.removed_stracks)
+        self.tracked_stracks, self.lost_stracks = self.remove_duplicate_stracks(self.tracked_stracks, self.lost_stracks)
+        self.removed_stracks.extend(removed_stracks)
+        if len(self.removed_stracks) > 1000:
+            self.removed_stracks = self.removed_stracks[-999:]  # clip remove stracks to 1000 maximum
+        
+        '''x.tlbr have update by function:
+                @property
+                def tlwh(self):
+        '''
+        
+        ##================ 原算法输出
+        # output = np.asarray([x.tlbr.tolist() + [x.track_id, x.score, x.cls, x.frame_id, x.idx] 
+        #                     for x in self.tracked_stracks if x.is_activated], dtype=np.float32)
+        
+        ## ===== write by WQG
+        output1 = [x.tlwh_to_tlbr(x._tlwh).tolist() + [x.track_id, x.score, x.cls, x.frame_id, x.idx] 
+                              for x in self.tracked_stracks if x.is_activated]
+        
+        output2 = [x.tlwh_to_tlbr(x._tlwh).tolist() + [x.track_id, x.score, x.cls, x.frame_id, x.idx] 
+                              for x in activated_stracks if x.first_find]
+        
+        output = np.asarray(output1+output2, dtype=np.float32)
+
+        return output
+    
+    
+    def get_result(self):
+        '''written by WQG'''
+# =============================================================================
+#         activate_tracks = np.asarray([x.tlbr.tolist() + [x.track_id, x.score, x.cls, x.idx] 
+#                                       for x in self.tracked_stracks if x.is_activated], dtype=np.float32)
+#         
+#         track_features = []
+# =============================================================================
+        tracks = []
+        feats = []                  
+        for t in self.tracked_stracks:
+            if t.is_activated:
+                track = t.tlbr.tolist() + [t.track_id, t.score, t.cls, t.idx] 
+                feat = t.curr_feature
+                
+                tracks.append(track)
+                feats.append(feat)
+        
+        tracks = np.asarray(tracks, dtype=np.float32)
+   
+        return (tracks, feats)
+
+
+    def get_kalmanfilter(self):
+        """Returns a Kalman filter object for tracking bounding boxes."""
+        return KalmanFilterXYAH()
+
+    def init_track(self, dets, scores, cls, img=None):
+        """Initialize object tracking with detections and scores using STrack algorithm."""
+        return [STrack(xyxy, s, c) for (xyxy, s, c) in zip(dets, scores, cls)] if len(dets) else []  # detections
+
+    def get_dists(self, tracks, detections):
+        """Calculates the distance between tracks and detections using IOU and fuses scores."""
+        dists = matching.iou_distance(tracks, detections)
+        # TODO: mot20
+        # if not self.args.mot20:
+        dists = matching.fuse_score(dists, detections)
+        return dists
+    def get_dists_1(self, tracks, detections):
+        """Calculates the distance between tracks and detections using IOU and fuses scores."""
+        
+        pass
+    
+
+    def multi_predict(self, tracks):
+        """Returns the predicted tracks using the YOLOv8 network."""
+        STrack.multi_predict(tracks)
+
+    def reset_id(self):
+        """Resets the ID counter of STrack."""
+        STrack.reset_id()
+
+    @staticmethod
+    def joint_stracks(tlista, tlistb):
+        """Combine two lists of stracks into a single one."""
+        exists = {}
+        res = []
+        for t in tlista:
+            exists[t.track_id] = 1
+            res.append(t)
+        for t in tlistb:
+            tid = t.track_id
+            if not exists.get(tid, 0):
+                exists[tid] = 1
+                res.append(t)
+        return res
+
+    @staticmethod
+    def sub_stracks(tlista, tlistb):
+        """DEPRECATED CODE in https://github.com/ultralytics/ultralytics/pull/1890/
+        stracks = {t.track_id: t for t in tlista}
+        for t in tlistb:
+            tid = t.track_id
+            if stracks.get(tid, 0):
+                del stracks[tid]
+        return list(stracks.values())
+        """
+        track_ids_b = {t.track_id for t in tlistb}
+        return [t for t in tlista if t.track_id not in track_ids_b]
+
+    @staticmethod
+    def remove_duplicate_stracks(stracksa, stracksb):
+        """Remove duplicate stracks with non-maximum IOU distance."""
+        pdist = matching.iou_distance(stracksa, stracksb)
+        pairs = np.where(pdist < 0.15)
+        dupa, dupb = [], []
+        for p, q in zip(*pairs):
+            timep = stracksa[p].frame_id - stracksa[p].start_frame
+            timeq = stracksb[q].frame_id - stracksb[q].start_frame
+            if timep > timeq:
+                dupb.append(q)
+            else:
+                dupa.append(p)
+        resa = [t for i, t in enumerate(stracksa) if i not in dupa]
+        resb = [t for i, t in enumerate(stracksb) if i not in dupb]
+        return resa, resb

tracking/trackers/cfg/botsort.yaml

@@ -0,0 +1,18 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+# Default YOLO tracker settings for BoT-SORT tracker https://github.com/NirAharon/BoT-SORT
+
+tracker_type: botsort  # tracker type, ['botsort', 'bytetrack']
+track_high_thresh: 0.5  # threshold for the first association
+track_low_thresh: 0.1  # threshold for the second association
+new_track_thresh: 0.6  # threshold for init new track if the detection does not match any tracks
+track_buffer: 30  # buffer to calculate the time when to remove tracks
+match_thresh: 0.8  # threshold for matching tracks
+# min_box_area: 10  # threshold for min box areas(for tracker evaluation, not used for now)
+# mot20: False  # for tracker evaluation(not used for now)
+
+# BoT-SORT settings
+gmc_method: sparseOptFlow  # method of global motion compensation
+# ReID model related thresh (not supported yet)
+proximity_thresh: 0.5
+appearance_thresh: 0.25
+with_reid: True

tracking/trackers/cfg/bytetrack.yaml

@@ -0,0 +1,11 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+# Default YOLO tracker settings for ByteTrack tracker https://github.com/ifzhang/ByteTrack
+
+tracker_type: bytetrack  # tracker type, ['botsort', 'bytetrack']
+track_high_thresh: 0.5  # threshold for the first association
+track_low_thresh: 0.1  # threshold for the second association
+new_track_thresh: 0.6  # threshold for init new track if the detection does not match any tracks
+track_buffer: 30  # buffer to calculate the time when to remove tracks
+match_thresh: 0.8  # threshold for matching tracks
+# min_box_area: 10  # threshold for min box areas(for tracker evaluation, not used for now)
+# mot20: False  # for tracker evaluation(not used for now)

tracking/trackers/reid/__init__.py

@@ -0,0 +1,7 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Fri Jan 19 16:15:35 2024
+
+@author: ym
+"""
+

tracking/trackers/reid/config.py

@@ -0,0 +1,42 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Fri Jan 19 14:01:46 2024
+
+@author: ym
+"""
+
+import torch
+import os
+# import torchvision.transforms as T
+class Config:
+    # network settings
+    backbone = 'resnet18' # [resnet18, mobilevit_s, mobilenet_v2, mobilenetv3]
+    batch_size = 8
+    embedding_size = 256
+    img_size = 224
+    
+    current_path = os.path.dirname(os.path.abspath(__file__))
+    model_path = os.path.join(current_path, r"ckpts\resnet18_1220\best.pth")
+    
+    # model_path = "./trackers/reid/ckpts/resnet18_1220/best.pth"
+    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+    
+# =============================================================================
+#     metric = 'arcface'  # [cosface, arcface]
+#     drop_ratio = 0.5
+#    
+#     # training settings
+#     checkpoints = "checkpoints/Mobilev3Large_1225"  # [resnet18, mobilevit_s, mobilenet_v2, mobilenetv3]
+#     restore = False
+#     
+#     test_model = "./checkpoints/resnet18_1220/best.pth"
+#     
+# 
+# 
+# 
+#     device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+#     pin_memory = True  # if memory is large, set it True to speed up a bit
+#     num_workers = 4  # dataloader
+# =============================================================================
+
+config = Config()

tracking/trackers/reid/model/BAM.py

@@ -0,0 +1,83 @@
+import torch.nn as nn
+import torchvision
+from torch.nn import init
+
+class Flatten(nn.Module):
+    def forward(self, x):
+        return x.view(x.shape[0], -1)
+
+class ChannelAttention(nn.Module):
+    def __int__(self,channel,reduction, num_layers):
+        super(ChannelAttention,self).__init__()
+        self.avgpool = nn.AdaptiveAvgPool2d(1)
+        gate_channels = [channel]
+        gate_channels += [len(channel)//reduction]*num_layers
+        gate_channels += [channel]
+
+        self.ca = nn.Sequential()
+        self.ca.add_module('flatten', Flatten())
+        for i in range(len(gate_channels)-2):
+            self.ca.add_module('',nn.Linear(gate_channels[i], gate_channels[i+1]))
+            self.ca.add_module('',nn.BatchNorm1d(gate_channels[i+1]))
+            self.ca.add_module('',nn.ReLU())
+        self.ca.add_module('',nn.Linear(gate_channels[-2], gate_channels[-1]))
+
+    def forward(self, x):
+        res = self.avgpool(x)
+        res = self.ca(res)
+        res = res.unsqueeze(-1).unsqueeze(-1).expand_as(x)
+        return res
+
+class SpatialAttention(nn.Module):
+    def __int__(self, channel,reduction=16,num_lay=3,dilation=2):
+        super(SpatialAttention).__init__()
+        self.sa = nn.Sequential()
+        self.sa.add_module('', nn.Conv2d(kernel_size=1, in_channels=channel, out_channels=(channel//reduction)*3))
+        self.sa.add_module('',nn.BatchNorm2d(num_features=(channel//reduction)))
+        self.sa.add_module('',nn.ReLU())
+        for i in range(num_lay):
+            self.sa.add_module('', nn.Conv2d(kernel_size=3,
+                                             in_channels=(channel//reduction),
+                                             out_channels=(channel//reduction),
+                                             padding=1,
+                                             dilation= 2))
+            self.sa.add_module('',nn.BatchNorm2d(channel//reduction))
+            self.sa.add_module('',nn.ReLU())
+        self.sa.add_module('',nn.Conv2d(channel//reduction, 1, kernel_size=1))
+    def forward(self,x):
+        res = self.sa(x)
+        res = res.expand_as(x)
+        return res
+
+class BAMblock(nn.Module):
+    def __init__(self,channel=512, reduction=16, dia_val=2):
+        super(BAMblock, self).__init__()
+        self.ca = ChannelAttention(channel, reduction)
+        self.sa = SpatialAttention(channel,reduction,dia_val)
+        self.sigmoid = nn.Sigmoid()
+
+    def init_weights(self):
+        for m in self.modules():
+            if isinstance(m, nn.Conv2d):
+                init.kaiming_normal(m.weight, mode='fan_out')
+                if m.bais is not None:
+                    init.constant_(m.bias, 0)
+                elif isinstance(m, nn.BatchNorm2d):
+                    init.constant_(m.weight, 1)
+                    init.constant_(m.bias, 0)
+                elif isinstance(m, nn.Linear):
+                    init.normal_(m.weight, std=0.001)
+                    if m.bias is not None:
+                        init.constant_(m.bias, 0)
+
+    def forward(self,x):
+        b, c, _, _ = x.size()
+        sa_out=self.sa(x)
+        ca_out=self.ca(x)
+        weight=self.sigmoid(sa_out+ca_out)
+        out=(1+weight)*x
+        return out
+
+if __name__ =="__main__":
+
+    print(512//14)

tracking/trackers/reid/model/CBAM.py

@@ -0,0 +1,68 @@
+import torch
+import torch.nn as nn
+import torch.nn.init as init
+
+class channelAttention(nn.Module):
+    def __init__(self, channel, reduction=16):
+        super(channelAttention, self).__init__()
+        self.Maxpooling = nn.AdaptiveMaxPool2d(1)
+        self.Avepooling = nn.AdaptiveAvgPool2d(1)
+        self.ca = nn.Sequential()
+        self.ca.add_module('conv1',nn.Conv2d(channel, channel//reduction, 1, bias=False))
+        self.ca.add_module('Relu', nn.ReLU())
+        self.ca.add_module('conv2',nn.Conv2d(channel//reduction, channel, 1, bias=False))
+        self.sigmod = nn.Sigmoid()
+
+    def forward(self, x):
+        M_out = self.Maxpooling(x)
+        A_out = self.Avepooling(x)
+        M_out = self.ca(M_out)
+        A_out = self.ca(A_out)
+        out = self.sigmod(M_out+A_out)
+        return out
+
+class SpatialAttention(nn.Module):
+    def __init__(self, kernel_size=7):
+        super().__init__()
+        self.conv = nn.Conv2d(in_channels=2, out_channels=1, kernel_size=kernel_size, padding=kernel_size // 2)
+        self.sigmoid = nn.Sigmoid()
+
+    def forward(self, x):
+        max_result, _ = torch.max(x, dim=1, keepdim=True)
+        avg_result = torch.mean(x, dim=1, keepdim=True)
+        result = torch.cat([max_result, avg_result], dim=1)
+        output = self.conv(result)
+        output = self.sigmoid(output)
+        return output
+class CBAM(nn.Module):
+    def __init__(self, channel=512, reduction=16, kernel_size=7):
+        super().__init__()
+        self.ca = channelAttention(channel, reduction)
+        self.sa = SpatialAttention(kernel_size)
+
+    def init_weights(self):
+        for m in self.modules():#权重初始化
+            if isinstance(m, nn.Conv2d):
+                init.kaiming_normal_(m.weight, mode='fan_out')
+                if m.bias is not None:
+                    init.constant_(m.bias, 0)
+            elif isinstance(m, nn.BatchNorm2d):
+                init.constant_(m.weight, 1)
+                init.constant_(m.bias, 0)
+            elif isinstance(m, nn.Linear):
+                init.normal_(m.weight, std=0.001)
+                if m.bias is not None:
+                    init.constant_(m.bias, 0)
+
+    def forward(self, x):
+        # b,c_,_ = x.size()
+        # residual = x
+        out = x*self.ca(x)
+        out = out*self.sa(out)
+        return out
+if __name__ == '__main__':
+    input=torch.randn(50,512,7,7)
+    kernel_size=input.shape[2]
+    cbam = CBAM(channel=512,reduction=16,kernel_size=kernel_size)
+    output=cbam(input)
+    print(output.shape)

tracking/trackers/reid/model/Tool.py

@@ -0,0 +1,33 @@
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+class GeM(nn.Module):
+    def __init__(self, p=3, eps=1e-6):
+        super(GeM, self).__init__()
+        self.p = nn.Parameter(torch.ones(1) * p)
+        self.eps = eps
+
+    def forward(self, x):
+        return self.gem(x, p=self.p, eps=self.eps, stride = 2)
+
+    def gem(self, x, p=3, eps=1e-6, stride = 2):
+        return F.avg_pool2d(x.clamp(min=eps).pow(p), (x.size(-2), x.size(-1)), stride=2).pow(1. / p)
+
+    def __repr__(self):
+        return self.__class__.__name__ + \
+               '(' + 'p=' + '{:.4f}'.format(self.p.data.tolist()[0]) + \
+               ', ' + 'eps=' + str(self.eps) + ')'
+
+class TripletLoss(nn.Module):
+    def __init__(self, margin):
+        super(TripletLoss, self).__init__()
+        self.margin = margin
+
+    def forward(self, anchor, positive, negative, size_average = True):
+        distance_positive = (anchor-positive).pow(2).sum(1)
+        distance_negative = (anchor-negative).pow(2).sum(1)
+        losses = F.relu(distance_negative-distance_positive+self.margin)
+        return losses.mean() if size_average else losses.sum()
+
+if __name__ == '__main__':
+    print('')