403 lines
18 KiB
Python
403 lines
18 KiB
Python
# 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)
|