diff --git a/contrast/.idea/.gitignore b/contrast/.idea/.gitignore
new file mode 100644
index 0000000..35410ca
--- /dev/null
+++ b/contrast/.idea/.gitignore
@@ -0,0 +1,8 @@
+# 默认忽略的文件
+/shelf/
+/workspace.xml
+# 基于编辑器的 HTTP 客户端请求
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml
diff --git a/contrast/.idea/contrastInference.iml b/contrast/.idea/contrastInference.iml
new file mode 100644
index 0000000..6d6038d
--- /dev/null
+++ b/contrast/.idea/contrastInference.iml
@@ -0,0 +1,12 @@
+
+
+
+
+
+
+
+
+
+
+
+
\ No newline at end of file
diff --git a/contrast/.idea/deployment.xml b/contrast/.idea/deployment.xml
new file mode 100644
index 0000000..b7f9a78
--- /dev/null
+++ b/contrast/.idea/deployment.xml
@@ -0,0 +1,14 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
\ No newline at end of file
diff --git a/contrast/.idea/inspectionProfiles/Project_Default.xml b/contrast/.idea/inspectionProfiles/Project_Default.xml
new file mode 100644
index 0000000..920d523
--- /dev/null
+++ b/contrast/.idea/inspectionProfiles/Project_Default.xml
@@ -0,0 +1,12 @@
+
+
+
+
+
+
+
+
\ No newline at end of file
diff --git a/contrast/.idea/inspectionProfiles/profiles_settings.xml b/contrast/.idea/inspectionProfiles/profiles_settings.xml
new file mode 100644
index 0000000..105ce2d
--- /dev/null
+++ b/contrast/.idea/inspectionProfiles/profiles_settings.xml
@@ -0,0 +1,6 @@
+
+
+
+
+
+
\ No newline at end of file
diff --git a/contrast/.idea/misc.xml b/contrast/.idea/misc.xml
new file mode 100644
index 0000000..3afa107
--- /dev/null
+++ b/contrast/.idea/misc.xml
@@ -0,0 +1,7 @@
+
+
+
+
+
+
+
\ No newline at end of file
diff --git a/contrast/.idea/modules.xml b/contrast/.idea/modules.xml
new file mode 100644
index 0000000..316bf04
--- /dev/null
+++ b/contrast/.idea/modules.xml
@@ -0,0 +1,8 @@
+
+
+
+
+
+
+
+
\ No newline at end of file
diff --git a/contrast/__init__.py b/contrast/__init__.py
new file mode 100644
index 0000000..e3e0f3f
--- /dev/null
+++ b/contrast/__init__.py
@@ -0,0 +1 @@
+# from .config import config
\ No newline at end of file
diff --git a/contrast/__pycache__/__init__.cpython-39.pyc b/contrast/__pycache__/__init__.cpython-39.pyc
new file mode 100644
index 0000000..f894aad
Binary files /dev/null and b/contrast/__pycache__/__init__.cpython-39.pyc differ
diff --git a/contrast/__pycache__/config.cpython-38.pyc b/contrast/__pycache__/config.cpython-38.pyc
new file mode 100644
index 0000000..c6934bc
Binary files /dev/null and b/contrast/__pycache__/config.cpython-38.pyc differ
diff --git a/contrast/__pycache__/config.cpython-39.pyc b/contrast/__pycache__/config.cpython-39.pyc
new file mode 100644
index 0000000..ba23f1d
Binary files /dev/null and b/contrast/__pycache__/config.cpython-39.pyc differ
diff --git a/contrast/__pycache__/inference.cpython-39.pyc b/contrast/__pycache__/inference.cpython-39.pyc
new file mode 100644
index 0000000..54fce2e
Binary files /dev/null and b/contrast/__pycache__/inference.cpython-39.pyc differ
diff --git a/contrast/config.py b/contrast/config.py
new file mode 100644
index 0000000..aea7680
--- /dev/null
+++ b/contrast/config.py
@@ -0,0 +1,84 @@
+import torch
+import torchvision.transforms as T
+
+
+class Config:
+ # network settings
+ backbone = 'vit' # [resnet18, mobilevit_s, mobilenet_v2, mobilenetv3_small, mobilenetv3_large, mobilenet_v1, PPLCNET_x1_0, PPLCNET_x0_5, PPLCNET_x2_5]
+ metric = 'softmax' # [cosface, arcface, softmax]
+ cbam = True
+ embedding_size = 256 # 256
+ drop_ratio = 0.5
+ img_size = 224
+
+ teacher = 'vit' # [resnet18, mobilevit_s, mobilenet_v2, mobilenetv3_small, mobilenetv3_large, mobilenet_v1, PPLCNET_x1_0, PPLCNET_x0_5, PPLCNET_x2_5]
+ student = 'resnet'
+ # data preprocess
+ # input_shape = [1, 128, 128]
+ """transforms.RandomCrop(size),
+ transforms.RandomVerticalFlip(p=0.5),
+ transforms.RandomHorizontalFlip(),
+ RandomRotate(15, 0.3),
+ # RandomGaussianBlur()"""
+
+ train_transform = T.Compose([
+ T.ToTensor(),
+ T.Resize((img_size, img_size)),
+ # T.RandomCrop(img_size*4//5),
+ # T.RandomHorizontalFlip(p=0.5),
+ T.RandomRotation(180),
+ T.ColorJitter(brightness=0.5),
+ T.ConvertImageDtype(torch.float32),
+ T.Normalize(mean=[0.5], std=[0.5]),
+ ])
+ test_transform = T.Compose([
+ T.ToTensor(),
+ T.Resize((img_size, img_size)),
+ T.ConvertImageDtype(torch.float32),
+ T.Normalize(mean=[0.5], std=[0.5]),
+ ])
+
+ # dataset
+ train_root = './data/2250_train/train' # 初始筛选过一次的数据集
+ # train_root = './data/0625_train/train'
+ test_root = "./data/2250_train/val/"
+ # test_root = "./data/0625_train/val"
+
+ test_list = "./data/2250_train/val_pair.txt"
+ test_group_json = "./data/2250_train/cross_same.json"
+ # test_group_json = "./data/0625_train/cross_same.json"
+ # test_list = "./data/test_data_100/val_pair.txt"
+
+ # training settings
+ checkpoints = "checkpoints/vit_b_16_0815/" # [resnet18, mobilevit_s, mobilenet_v2, mobilenetv3]
+ restore = True
+ # restore_model = "checkpoints/renet18_2250_0315/best_resnet18_2250_0315.pth" # best_resnet18_1491_0306.pth
+ restore_model = "checkpoints/vit_b_16_0730/best.pth" # best_resnet18_1491_0306.pth
+
+ # test_model = "./checkpoints/renet18_1887_0311/best_resnet18_1887_0311.pth"
+ testbackbone = 'resnet18' # [resnet18, mobilevit_s, mobilenet_v2, mobilenetv3_small, mobilenetv3_large, mobilenet_v1, PPLCNET_x1_0, PPLCNET_x0_5]
+ # test_val = "./data/2250_train"
+ test_val = "./data/0625_train"
+ test_model = "checkpoints/resnet18_0721/best.pth"
+
+ train_batch_size = 128 # 256
+ test_batch_size = 256 # 256
+
+
+ epoch = 300
+ optimizer = 'adamw' # ['sgd', 'adam'， 'adamw']
+ lr = 1e-3 # 1e-2
+ lr_step = 10 # 10
+ lr_decay = 0.95 # 0.98
+ weight_decay = 5e-4
+ loss = 'focal_loss' # ['focal_loss', 'cross_entropy']
+ device = torch.device('cuda:1' if torch.cuda.is_available() else 'cpu')
+ # device = torch.device('cuda:0' 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
+
+ group_test = True
+ # group_test = False
+
+config = Config()
\ No newline at end of file
diff --git a/contrast/contrast_one2one.py b/contrast/contrast_one2one.py
new file mode 100644
index 0000000..42b9a2a
--- /dev/null
+++ b/contrast/contrast_one2one.py
@@ -0,0 +1,380 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Fri Aug 30 17:53:03 2024
+
+1. 确认在相同CamerType下，track.data 中 CamerID 项数量 = 图像数 = 帧ID数 = 最大帧ID
+
+2. 读取0/1_tracking_output.data 中数据，boxes、feats，len(boxes)=len(feats)
+ 帧ID约束
+
+3. 优先选择前摄
+
+4. 保存图像数据
+
+5. 一次购物事件类型
+ shopEvent: {barcode:
+ type: getout, input
+ front_traj:[{imgpath: str,
+ box: arrar(1, 9),
+ feat: array(1, 256)
+ }]
+ back_traj: [{imgpath: str,
+ box: arrar(1, 9),
+ feat: array(1, 256)
+ }]
+ }
+
+
+
+@author: ym
+
+"""
+import numpy as np
+import cv2
+import os
+import sys
+
+import pickle
+import torch
+import time
+import json
+from config import config as conf
+from model import resnet18
+from inference import load_contrast_model
+from inference import featurize
+
+
+sys.path.append(r"D:\DetectTracking")
+from tracking.utils.read_data import extract_data, read_tracking_output, read_deletedBarcode_file
+
+IMG_FORMAT = ['.bmp', '.jpg', '.jpeg', '.png']
+
+model = load_contrast_model()
+
+def creat_shopping_event(basepath):
+ eventList = []
+
+ '''一、构造放入商品事件列表'''
+ k = 0
+ for filename in os.listdir(basepath):
+ # filename = "20240723-155413_6904406215720"
+
+ '''filename下为一次购物事件'''
+ filepath = os.path.join(basepath, filename)
+
+ '''================ 0. 检查 filename 及 filepath 正确性和有效性 ================'''
+ nmlist = filename.split('_')
+ if filename.find('2024')<0 or len(nmlist)!=2 or len(nmlist[0])!=15 or len(nmlist[1])<11:
+ continue
+ if not os.path.isdir(filepath): continue
+ print(f"Event name: {filename}")
+
+ '''================ 1. 构造事件描述字典，暂定 9 items ==============='''
+ event = {}
+ event['barcode'] = nmlist[1]
+ event['type'] = 'input'
+ event['filepath'] = filepath
+ event['back_imgpaths'] = []
+ event['front_imgpaths'] = []
+ event['back_boxes'] = np.empty((0, 9), dtype=np.float64)
+ event['front_boxes'] = np.empty((0, 9), dtype=np.float64)
+ event['back_feats'] = np.empty((0, 256), dtype=np.float64)
+ event['front_feats'] = np.empty((0, 256), dtype=np.float64)
+ # event['feats_compose'] = np.empty((0, 256), dtype=np.float64)
+ # event['feats_select'] = np.empty((0, 256), dtype=np.float64)
+
+
+ '''================= 1. 读取 data 文件 ============================='''
+ for dataname in os.listdir(filepath):
+ # filename = '1_track.data'
+ datapath = os.path.join(filepath, dataname)
+ if not os.path.isfile(datapath): continue
+
+ CamerType = dataname.split('_')[0]
+ ''' 3.1 读取 0/1_track.data 中数据，暂不考虑'''
+ # if dataname.find("_track.data")>0:
+ # bboxes, ffeats, trackerboxes, tracker_feat_dict, trackingboxes, tracking_feat_dict = extract_data(datapath)
+
+ ''' 3.2 读取 0/1_tracking_output.data 中数据'''
+ if dataname.find("_tracking_output.data")>0:
+ tracking_output_boxes, tracking_output_feats = read_tracking_output(datapath)
+ if len(tracking_output_boxes) != len(tracking_output_feats): continue
+ if CamerType == '0':
+ event['back_boxes'] = tracking_output_boxes
+ event['back_feats'] = tracking_output_feats
+ elif CamerType == '1':
+ event['front_boxes'] = tracking_output_boxes
+ event['front_feats'] = tracking_output_feats
+
+ # '''1.1 事件的特征表征方式选择'''
+ # bk_feats = event['back_feats']
+ # ft_feats = event['front_feats']
+
+ # feats_compose = np.empty((0, 256), dtype=np.float64)
+ # if len(ft_feats):
+ # feats_compose = np.concatenate((feats_compose, ft_feats), axis=0)
+ # if len(bk_feats):
+ # feats_compose = np.concatenate((feats_compose, bk_feats), axis=0)
+ # event['feats_compose'] = feats_compose
+
+ # '''3. 构造前摄特征'''
+ # if len(ft_feats):
+ # event['feats_select'] = ft_feats
+
+
+
+ '''================ 2. 读取图像文件地址，并按照帧ID排序 ============='''
+ frontImgs, frontFid = [], []
+ backImgs, backFid = [], []
+ for imgname in os.listdir(filepath):
+ name, ext = os.path.splitext(imgname)
+ if ext not in IMG_FORMAT or name.find('frameId')<0: continue
+
+ CamerType = name.split('_')[0]
+ frameId = int(name.split('_')[3])
+ imgpath = os.path.join(filepath, imgname)
+ if CamerType == '0':
+ backImgs.append(imgpath)
+ backFid.append(frameId)
+ if CamerType == '1':
+ frontImgs.append(imgpath)
+ frontFid.append(frameId)
+
+ frontIdx = np.argsort(np.array(frontFid))
+ backIdx = np.argsort(np.array(backFid))
+
+ '''2.1 生成依据帧 ID 排序的前后摄图像地址列表'''
+ frontImgs = [frontImgs[i] for i in frontIdx]
+ backImgs = [backImgs[i] for i in backIdx]
+
+ '''2.2 将前、后摄图像路径添加至事件字典'''
+ bfid = event['back_boxes'][:, 7].astype(np.int64)
+ ffid = event['front_boxes'][:, 7].astype(np.int64)
+ if len(bfid) and max(bfid) <= len(backImgs):
+ event['back_imgpaths'] = [backImgs[i-1] for i in bfid]
+ if len(ffid) and max(ffid) <= len(frontImgs):
+ event['front_imgpaths'] = [frontImgs[i-1] for i in ffid]
+
+
+ '''================ 3. 判断当前事件有效性，并添加至事件列表 =========='''
+ condt1 = len(event['back_imgpaths'])==0 or len(event['front_imgpaths'])==0
+ condt2 = len(event['front_feats'])==0 and len(event['back_feats'])==0
+
+ if condt1 or condt2:
+ print(f" Error, condt1: {condt1}, condt2: {condt2}")
+ continue
+
+ eventList.append(event)
+
+ # k += 1
+ # if k==1:
+ # continue
+
+ '''一、构造放入商品事件列表，暂不处理'''
+ # delepath = os.path.join(basepath, 'deletedBarcode.txt')
+ # bcdList = read_deletedBarcode_file(delepath)
+ # for slist in bcdList:
+ # getoutFold = slist['SeqDir'].strip()
+ # getoutPath = os.path.join(basepath, getoutFold)
+
+ # '''取出事件文件夹不存在，跳出循环'''
+ # if not os.path.exists(getoutPath) and not os.path.isdir(getoutPath):
+ # continue
+
+ # ''' 生成取出事件字典 '''
+ # event = {}
+ # event['barcode'] = slist['Deleted'].strip()
+ # event['type'] = 'getout'
+ # event['basepath'] = getoutPath
+
+
+ return eventList
+
+def get_std_barcodeDict(bcdpath):
+ stdBlist = []
+ for filename in os.listdir(bcdpath):
+ filepath = os.path.join(bcdpath, filename)
+ if not os.path.isdir(filepath) or not filename.isdigit(): continue
+
+ stdBlist.append(filename)
+
+
+ bcdpaths = [(barcode, os.path.join(bcdpath, barcode)) for barcode in stdBlist]
+
+ k = 0
+ for barcode, bpath in bcdpaths:
+ stdBarcodeDict = {}
+ stdBarcodeDict[barcode] = []
+ for root, dirs, files in os.walk(bpath):
+
+ imgpaths = []
+ if "base" in dirs:
+ broot = os.path.join(root, "base")
+ for imgname in os.listdir(broot):
+ imgpath = os.path.join(broot, imgname)
+ _, ext = os.path.splitext(imgpath)
+ if ext not in IMG_FORMAT: continue
+ imgpaths.append(imgpath)
+
+ stdBarcodeDict[barcode].extend(imgpaths)
+ break
+
+ else:
+ for imgname in files:
+ imgpath = os.path.join(root, imgname)
+ _, ext = os.path.splitext(imgpath)
+ if ext not in IMG_FORMAT: continue
+ imgpaths.append(imgpath)
+ stdBarcodeDict[barcode].extend(imgpaths)
+
+ jsonpath = os.path.join(r'\\192.168.1.28\share\测试_202406\contrast\barcodes', f"{barcode}.pickle")
+ with open(jsonpath, 'wb') as f:
+ pickle.dump(stdBarcodeDict, f)
+
+ print(f"Barcode: {barcode}")
+
+ k += 1
+ if k == 10:
+ break
+
+
+
+
+ return stdBarcodeDict
+
+
+def one2one_test(filepath):
+
+ savepath = r'\\192.168.1.28\share\测试_202406\contrast'
+
+ '''获得 Barcode 列表'''
+ bcdpath = r'\\192.168.1.28\share\已标注数据备份\对比数据\barcode\barcode_1771'
+ stdBarcodeDict = get_std_barcodeDict(bcdpath)
+
+
+ eventList = creat_shopping_event(filepath)
+ print("=========== eventList have generated! ===========")
+ barcodeDict = {}
+ for event in eventList:
+ '''9 items: barcode, type, filepath, back_imgpaths, front_imgpaths,
+ back_boxes, front_boxes, back_feats, front_feats
+ '''
+
+ barcode = event['barcode']
+ if barcode not in stdBarcodeDict.keys():
+ continue
+
+
+ if len(event['feats_select']):
+ event_feats = event['feats_select']
+ elif len(event['back_feats']):
+ event_feats = event['back_feats']
+ else:
+ continue
+
+ std_bcdpath = os.path.join(bcdpath, barcode)
+
+
+
+ for root, dirs, files in os.walk(std_bcdpath):
+ if "base" in files:
+ std_bcdpath = os.path.join(root, "base")
+ break
+
+
+
+
+
+
+
+
+
+
+
+
+
+ '''保存一次购物事件的轨迹子图'''
+ basename = os.path.basename(event['filepath'])
+ spath = os.path.join(savepath, basename)
+ if not os.path.exists(spath):
+ os.makedirs(spath)
+ cameras = ('front', 'back')
+ for camera in cameras:
+ if camera == 'front':
+ boxes = event['front_boxes']
+ imgpaths = event['front_imgpaths']
+ else:
+ boxes = event['back_boxes']
+ imgpaths = event['back_imgpaths']
+
+ for i, box in enumerate(boxes):
+ x1, y1, x2, y2, tid, score, cls, fid, bid = box
+
+ imgpath = imgpaths[i]
+ image = cv2.imread(imgpath)
+ subimg = image[int(y1/2):int(y2/2), int(x1/2):int(x2/2), :]
+
+ camerType, timeTamp, _, frameID = os.path.basename(imgpath).split('.')[0].split('_')
+ subimgName = f"{camerType}_{tid}_fid({fid}, {frameID}).png"
+ subimgPath = os.path.join(spath, subimgName)
+
+ cv2.imwrite(subimgPath, subimg)
+ print(f"Image saved: {basename}")
+
+
+
+def batch_inference(imgpaths, batch):
+ size = len(imgpaths)
+ groups = []
+ for i in range(0, size, batch):
+ end = min(batch + i, size)
+ groups.append(imgpaths[i: end])
+
+ features = []
+ for group in groups:
+ feature = featurize(group, conf.test_transform, model, conf.device)
+ features.append(feature)
+
+ return features
+
+def main_infer():
+
+
+
+ bpath = r"\\192.168.1.28\share\测试_202406\contrast\barcodes"
+ for filename in os.listdir(bpath):
+ filepath = os.path.join(bpath, filename)
+
+ with open(filepath, 'rb') as f:
+ bpDict = pickle.load(f)
+
+ for barcode, imgpaths in bpDict.items():
+ feature = batch_inference(imgpaths, 8)
+
+ print("Done!!!")
+
+
+
+def main():
+ fplist = [#r'\\192.168.1.28\share\测试_202406\0723\0723_1',
+ #r'\\192.168.1.28\share\测试_202406\0723\0723_2',
+ r'\\192.168.1.28\share\测试_202406\0723\0723_3',
+ #r'\\192.168.1.28\share\测试_202406\0722\0722_01',
+ #r'\\192.168.1.28\share\测试_202406\0722\0722_02'
+ ]
+
+
+
+ for filepath in fplist:
+ one2one_test(filepath)
+
+ # for filepath in fplist:
+ # try:
+ # one2one_test(filepath)
+
+ # except Exception as e:
+ # print(f'{filepath}, Error: {e}')
+
+if __name__ == '__main__':
+ # main()
+ main_infer()
\ No newline at end of file
diff --git a/contrast/inference.py b/contrast/inference.py
new file mode 100644
index 0000000..e7a6dbc
--- /dev/null
+++ b/contrast/inference.py
@@ -0,0 +1,103 @@
+import os
+import os.path as osp
+
+import torch
+
+import numpy as np
+from model import resnet18
+from PIL import Image
+
+from torch.nn.functional import softmax
+from config import config as conf
+import time
+
+embedding_size = conf.embedding_size
+img_size = conf.img_size
+device = conf.device
+
+def load_contrast_model():
+ model = resnet18().to(conf.device)
+ model.load_state_dict(torch.load(conf.test_model, map_location=conf.device))
+ model.eval()
+ print('load model {} '.format(conf.testbackbone))
+
+ return model
+
+
+def group_image(imageDirs, batch) -> list:
+ images = []
+ """Group image paths by batch size"""
+ with os.scandir(imageDirs) as entries:
+ for imgpth in entries:
+ print(imgpth)
+ images.append(os.sep.join([imageDirs, imgpth.name]))
+ print(f"{len(images)} images in {imageDirs}")
+ size = len(images)
+ res = []
+ for i in range(0, size, batch):
+ end = min(batch + i, size)
+ res.append(images[i: end])
+ return res
+
+def test_preprocess(images: list, transform) -> torch.Tensor:
+ res = []
+ for img in images:
+ # print(img)
+ im = Image.open(img)
+ im = transform(im)
+ res.append(im)
+ # data = torch.cat(res, dim=0) # shape: (batch, 128, 128)
+ # data = data[:, None, :, :] # shape: (batch, 1, 128, 128)
+ data = torch.stack(res)
+ return data
+
+def featurize(images: list, transform, net, device) -> dict:
+ """featurize each image and save into a dictionary
+ Args:
+ images: image paths
+ transform: test transform
+ net: pretrained model
+ device: cpu or cuda
+ Returns:
+ Dict (key: imagePath, value: feature)
+ """
+ data = test_preprocess(images, transform)
+ data = data.to(device)
+ net = net.to(device)
+ with torch.no_grad():
+ features = net(data)
+ # res = {img: feature for (img, feature) in zip(images, features)}
+ return features
+
+
+
+if __name__ == '__main__':
+ # Network Setup
+ if conf.testbackbone == 'resnet18':
+ model = resnet18().to(device)
+ else:
+ raise ValueError('Have not model {}'.format(conf.backbone))
+
+ print('load model {} '.format(conf.testbackbone))
+ # model = nn.DataParallel(model).to(conf.device)
+ model.load_state_dict(torch.load(conf.test_model, map_location=conf.device))
+ model.eval()
+
+ # images = unique_image(conf.test_list)
+ # images = [osp.join(conf.test_val, img) for img in images]
+ # print('images', images)
+ # images = ['./data/2250_train/val/6920616313186/6920616313186_6920616313186_20240220-124502_53d2e103-ae3a-4689-b745-9d8723b770fe_front_returnGood_70f75407b7ae_31_01.jpg']
+
+
+ # groups = group_image(conf.test_val, conf.test_batch_size) ##根据batch_size取图片
+ groups = group_image('img_test', 1) ##根据batch_size取图片, 默认batch_size = 8
+
+ feature_dict = dict()
+ for group in groups:
+ s = time.time()
+ features = featurize(group, conf.test_transform, model, conf.device)
+ e = time.time()
+ print('time: {}'.format(e - s))
+ # out = softmax(features, dim=1).argmax(dim=1)
+ # print('d >>> {}'. format(out))
+ # feature_dict.update(d)
diff --git a/contrast/model/__init__.py b/contrast/model/__init__.py
new file mode 100644
index 0000000..9eebc77
--- /dev/null
+++ b/contrast/model/__init__.py
@@ -0,0 +1 @@
+from .resnet_pre import resnet18, resnet34, resnet50, resnet14
diff --git a/contrast/model/__pycache__/__init__.cpython-38.pyc b/contrast/model/__pycache__/__init__.cpython-38.pyc
new file mode 100644
index 0000000..160bc37
Binary files /dev/null and b/contrast/model/__pycache__/__init__.cpython-38.pyc differ
diff --git a/contrast/model/__pycache__/__init__.cpython-39.pyc b/contrast/model/__pycache__/__init__.cpython-39.pyc
new file mode 100644
index 0000000..539ec67
Binary files /dev/null and b/contrast/model/__pycache__/__init__.cpython-39.pyc differ
diff --git a/contrast/model/__pycache__/resnet_pre.cpython-38.pyc b/contrast/model/__pycache__/resnet_pre.cpython-38.pyc
new file mode 100644
index 0000000..199085d
Binary files /dev/null and b/contrast/model/__pycache__/resnet_pre.cpython-38.pyc differ
diff --git a/contrast/model/__pycache__/resnet_pre.cpython-39.pyc b/contrast/model/__pycache__/resnet_pre.cpython-39.pyc
new file mode 100644
index 0000000..0301f55
Binary files /dev/null and b/contrast/model/__pycache__/resnet_pre.cpython-39.pyc differ
diff --git a/contrast/model/resnet_pre.py b/contrast/model/resnet_pre.py
new file mode 100644
index 0000000..5e52ad9
--- /dev/null
+++ b/contrast/model/resnet_pre.py
@@ -0,0 +1,462 @@
+import torch
+import torch.nn as nn
+from config import config as conf
+
+try:
+ from torch.hub import load_state_dict_from_url
+except ImportError:
+ from torch.utils.model_zoo import load_url as load_state_dict_from_url
+# from .utils import load_state_dict_from_url
+
+__all__ = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101',
+ 'resnet152', 'resnext50_32x4d', 'resnext101_32x8d',
+ 'wide_resnet50_2', 'wide_resnet101_2']
+
+model_urls = {
+ 'resnet18': 'https://download.pytorch.org/models/resnet18-5c106cde.pth',
+ 'resnet34': 'https://download.pytorch.org/models/resnet34-333f7ec4.pth',
+ 'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth',
+ 'resnet101': 'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth',
+ 'resnet152': 'https://download.pytorch.org/models/resnet152-b121ed2d.pth',
+ 'resnext50_32x4d': 'https://download.pytorch.org/models/resnext50_32x4d-7cdf4587.pth',
+ 'resnext101_32x8d': 'https://download.pytorch.org/models/resnext101_32x8d-8ba56ff5.pth',
+ 'wide_resnet50_2': 'https://download.pytorch.org/models/wide_resnet50_2-95faca4d.pth',
+ 'wide_resnet101_2': 'https://download.pytorch.org/models/wide_resnet101_2-32ee1156.pth',
+}
+
+
+def conv3x3(in_planes, out_planes, stride=1, groups=1, dilation=1):
+ """3x3 convolution with padding"""
+ return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
+ padding=dilation, groups=groups, bias=False, dilation=dilation)
+
+def conv1x1(in_planes, out_planes, stride=1):
+ """1x1 convolution"""
+ return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False)
+
+
+class SpatialAttention(nn.Module):
+ def __init__(self, kernel_size=7):
+ super(SpatialAttention, self).__init__()
+
+ assert kernel_size in (3, 7), 'kernel size must be 3 or 7'
+ padding = 3 if kernel_size == 7 else 1
+
+ self.conv1 = nn.Conv2d(2, 1, kernel_size, padding=padding, bias=False)
+ self.sigmoid = nn.Sigmoid()
+
+ def forward(self, x):
+ avg_out = torch.mean(x, dim=1, keepdim=True)
+ max_out, _ = torch.max(x, dim=1, keepdim=True)
+ x = torch.cat([avg_out, max_out], dim=1)
+ x = self.conv1(x)
+ return self.sigmoid(x)
+
+class BasicBlock(nn.Module):
+ expansion = 1
+
+ def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1,
+ base_width=64, dilation=1, norm_layer=None, cam=False, bam=False):
+ super(BasicBlock, self).__init__()
+ if norm_layer is None:
+ norm_layer = nn.BatchNorm2d
+ if groups != 1 or base_width != 64:
+ raise ValueError('BasicBlock only supports groups=1 and base_width=64')
+ if dilation > 1:
+ raise NotImplementedError("Dilation > 1 not supported in BasicBlock")
+ self.cam = cam
+ self.bam = bam
+ # Both self.conv1 and self.downsample layers downsample the input when stride != 1
+ self.conv1 = conv3x3(inplanes, planes, stride)
+ self.bn1 = norm_layer(planes)
+ self.relu = nn.ReLU(inplace=True)
+ self.conv2 = conv3x3(planes, planes)
+ self.bn2 = norm_layer(planes)
+ self.downsample = downsample
+ self.stride = stride
+ if self.cam:
+ if planes == 64:
+ self.globalAvgPool = nn.AvgPool2d(56, stride=1)
+ elif planes == 128:
+ self.globalAvgPool = nn.AvgPool2d(28, stride=1)
+ elif planes == 256:
+ self.globalAvgPool = nn.AvgPool2d(14, stride=1)
+ elif planes == 512:
+ self.globalAvgPool = nn.AvgPool2d(7, stride=1)
+
+ self.fc1 = nn.Linear(in_features=planes, out_features=round(planes / 16))
+ self.fc2 = nn.Linear(in_features=round(planes / 16), out_features=planes)
+ self.sigmod = nn.Sigmoid()
+ if self.bam:
+ self.bam = SpatialAttention()
+
+ def forward(self, x):
+ identity = x
+
+ out = self.conv1(x)
+ out = self.bn1(out)
+ out = self.relu(out)
+
+ out = self.conv2(out)
+ out = self.bn2(out)
+
+ if self.downsample is not None:
+ identity = self.downsample(x)
+
+ if self.cam:
+ ori_out = self.globalAvgPool(out)
+ out = out.view(out.size(0), -1)
+ out = self.fc1(out)
+ out = self.relu(out)
+ out = self.fc2(out)
+ out = self.sigmod(out)
+ out = out.view(out.size(0), out.size(-1), 1, 1)
+ out = out * ori_out
+
+ if self.bam:
+ out = out*self.bam(out)
+
+ out += identity
+ out = self.relu(out)
+
+ return out
+
+
+class Bottleneck(nn.Module):
+ # Bottleneck in torchvision places the stride for downsampling at 3x3 convolution(self.conv2)
+ # while original implementation places the stride at the first 1x1 convolution(self.conv1)
+ # according to "Deep residual learning for image recognition"https://arxiv.org/abs/1512.03385.
+ # This variant is also known as ResNet V1.5 and improves accuracy according to
+ # https://ngc.nvidia.com/catalog/model-scripts/nvidia:resnet_50_v1_5_for_pytorch.
+
+ expansion = 4
+
+ def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1,
+ base_width=64, dilation=1, norm_layer=None, cam=False, bam=False):
+ super(Bottleneck, self).__init__()
+ if norm_layer is None:
+ norm_layer = nn.BatchNorm2d
+ width = int(planes * (base_width / 64.)) * groups
+ self.cam = cam
+ self.bam = bam
+ # Both self.conv2 and self.downsample layers downsample the input when stride != 1
+ self.conv1 = conv1x1(inplanes, width)
+ self.bn1 = norm_layer(width)
+ self.conv2 = conv3x3(width, width, stride, groups, dilation)
+ self.bn2 = norm_layer(width)
+ self.conv3 = conv1x1(width, planes * self.expansion)
+ self.bn3 = norm_layer(planes * self.expansion)
+ self.relu = nn.ReLU(inplace=True)
+ self.downsample = downsample
+ self.stride = stride
+ if self.cam:
+ if planes == 64:
+ self.globalAvgPool = nn.AvgPool2d(56, stride=1)
+ elif planes == 128:
+ self.globalAvgPool = nn.AvgPool2d(28, stride=1)
+ elif planes == 256:
+ self.globalAvgPool = nn.AvgPool2d(14, stride=1)
+ elif planes == 512:
+ self.globalAvgPool = nn.AvgPool2d(7, stride=1)
+
+ self.fc1 = nn.Linear(planes * self.expansion, round(planes / 4))
+ self.fc2 = nn.Linear(round(planes / 4), planes * self.expansion)
+ self.sigmod = nn.Sigmoid()
+
+ def forward(self, x):
+ identity = x
+
+ out = self.conv1(x)
+ out = self.bn1(out)
+ out = self.relu(out)
+
+ out = self.conv2(out)
+ out = self.bn2(out)
+ out = self.relu(out)
+
+ out = self.conv3(out)
+ out = self.bn3(out)
+
+ if self.downsample is not None:
+ identity = self.downsample(x)
+
+ if self.cam:
+ ori_out = self.globalAvgPool(out)
+ out = out.view(out.size(0), -1)
+ out = self.fc1(out)
+ out = self.relu(out)
+ out = self.fc2(out)
+ out = self.sigmod(out)
+ out = out.view(out.size(0), out.size(-1), 1, 1)
+ out = out * ori_out
+ out += identity
+ out = self.relu(out)
+ return out
+
+
+class ResNet(nn.Module):
+
+ def __init__(self, block, layers, num_classes=conf.embedding_size, zero_init_residual=False,
+ groups=1, width_per_group=64, replace_stride_with_dilation=None,
+ norm_layer=None, scale=0.75):
+ super(ResNet, self).__init__()
+ if norm_layer is None:
+ norm_layer = nn.BatchNorm2d
+ self._norm_layer = norm_layer
+
+ self.inplanes = 64
+ self.dilation = 1
+ if replace_stride_with_dilation is None:
+ # each element in the tuple indicates if we should replace
+ # the 2x2 stride with a dilated convolution instead
+ replace_stride_with_dilation = [False, False, False]
+ if len(replace_stride_with_dilation) != 3:
+ raise ValueError("replace_stride_with_dilation should be None "
+ "or a 3-element tuple, got {}".format(replace_stride_with_dilation))
+ self.groups = groups
+ self.base_width = width_per_group
+ self.conv1 = nn.Conv2d(3, self.inplanes, kernel_size=7, stride=2, padding=3,
+ bias=False)
+ self.bn1 = norm_layer(self.inplanes)
+ self.relu = nn.ReLU(inplace=True)
+ self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
+ self.layer1 = self._make_layer(block, int(64*scale), layers[0])
+ self.layer2 = self._make_layer(block, int(128*scale), layers[1], stride=2,
+ dilate=replace_stride_with_dilation[0])
+ self.layer3 = self._make_layer(block, int(256*scale), layers[2], stride=2,
+ dilate=replace_stride_with_dilation[1])
+ self.layer4 = self._make_layer(block, int(512*scale), layers[3], stride=2,
+ dilate=replace_stride_with_dilation[2])
+ self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
+ self.fc = nn.Linear(int(512 * block.expansion*scale), num_classes)
+
+ for m in self.modules():
+ if isinstance(m, nn.Conv2d):
+ nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
+ elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
+ nn.init.constant_(m.weight, 1)
+ nn.init.constant_(m.bias, 0)
+
+ # Zero-initialize the last BN in each residual branch,
+ # so that the residual branch starts with zeros, and each residual block behaves like an identity.
+ # This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677
+ if zero_init_residual:
+ for m in self.modules():
+ if isinstance(m, Bottleneck):
+ nn.init.constant_(m.bn3.weight, 0)
+ elif isinstance(m, BasicBlock):
+ nn.init.constant_(m.bn2.weight, 0)
+
+ def _make_layer(self, block, planes, blocks, stride=1, dilate=False):
+ norm_layer = self._norm_layer
+ downsample = None
+ previous_dilation = self.dilation
+ if dilate:
+ self.dilation *= stride
+ stride = 1
+ if stride != 1 or self.inplanes != planes * block.expansion:
+ downsample = nn.Sequential(
+ conv1x1(self.inplanes, planes * block.expansion, stride),
+ norm_layer(planes * block.expansion),
+ )
+
+ layers = []
+ layers.append(block(self.inplanes, planes, stride, downsample, self.groups,
+ self.base_width, previous_dilation, norm_layer))
+ self.inplanes = planes * block.expansion
+ for _ in range(1, blocks):
+ layers.append(block(self.inplanes, planes, groups=self.groups,
+ base_width=self.base_width, dilation=self.dilation,
+ norm_layer=norm_layer))
+ return nn.Sequential(*layers)
+
+ def _forward_impl(self, x):
+ # See note [TorchScript super()]
+ x = self.conv1(x)
+ x = self.bn1(x)
+ x = self.relu(x)
+ x = self.maxpool(x)
+
+ x = self.layer1(x)
+ x = self.layer2(x)
+ x = self.layer3(x)
+ x = self.layer4(x)
+
+ # print('poolBefore', x.shape)
+ x = self.avgpool(x)
+ # print('poolAfter', x.shape)
+ x = torch.flatten(x, 1)
+ # print('fcBefore',x.shape)
+ x = self.fc(x)
+
+ # print('fcAfter',x.shape)
+
+ return x
+
+ def forward(self, x):
+ return self._forward_impl(x)
+
+
+# def _resnet(arch, block, layers, pretrained, progress, **kwargs):
+# model = ResNet(block, layers, **kwargs)
+# if pretrained:
+# state_dict = load_state_dict_from_url(model_urls[arch],
+# progress=progress)
+# model.load_state_dict(state_dict, strict=False)
+# return model
+def _resnet(arch, block, layers, pretrained, progress, **kwargs):
+ model = ResNet(block, layers, **kwargs)
+ if pretrained:
+ state_dict = load_state_dict_from_url(model_urls[arch],
+ progress=progress)
+
+ src_state_dict = state_dict
+ target_state_dict = model.state_dict()
+ skip_keys = []
+ # skip mismatch size tensors in case of pretraining
+ for k in src_state_dict.keys():
+ if k not in target_state_dict:
+ continue
+ if src_state_dict[k].size() != target_state_dict[k].size():
+ skip_keys.append(k)
+ for k in skip_keys:
+ del src_state_dict[k]
+ missing_keys, unexpected_keys = model.load_state_dict(src_state_dict, strict=False)
+
+ return model
+
+
+def resnet14(pretrained=True, progress=True, **kwargs):
+ r"""ResNet-14 model from
+ `"Deep Residual Learning for Image Recognition" `_
+
+ Args:
+ pretrained (bool): If True, returns a model pre-trained on ImageNet
+ progress (bool): If True, displays a progress bar of the download to stderr
+ """
+ return _resnet('resnet18', BasicBlock, [2, 1, 1, 2], pretrained, progress,
+ **kwargs)
+
+
+def resnet18(pretrained=True, progress=True, **kwargs):
+ r"""ResNet-18 model from
+ `"Deep Residual Learning for Image Recognition" `_
+
+ Args:
+ pretrained (bool): If True, returns a model pre-trained on ImageNet
+ progress (bool): If True, displays a progress bar of the download to stderr
+ """
+ return _resnet('resnet18', BasicBlock, [2, 2, 2, 2], pretrained, progress,
+ **kwargs)
+
+
+def resnet34(pretrained=False, progress=True, **kwargs):
+ r"""ResNet-34 model from
+ `"Deep Residual Learning for Image Recognition" `_
+
+ Args:
+ pretrained (bool): If True, returns a model pre-trained on ImageNet
+ progress (bool): If True, displays a progress bar of the download to stderr
+ """
+ return _resnet('resnet34', BasicBlock, [3, 4, 6, 3], pretrained, progress,
+ **kwargs)
+
+
+def resnet50(pretrained=False, progress=True, **kwargs):
+ r"""ResNet-50 model from
+ `"Deep Residual Learning for Image Recognition" `_
+
+ Args:
+ pretrained (bool): If True, returns a model pre-trained on ImageNet
+ progress (bool): If True, displays a progress bar of the download to stderr
+ """
+ return _resnet('resnet50', Bottleneck, [3, 4, 6, 3], pretrained, progress,
+ **kwargs)
+
+
+def resnet101(pretrained=False, progress=True, **kwargs):
+ r"""ResNet-101 model from
+ `"Deep Residual Learning for Image Recognition" `_
+
+ Args:
+ pretrained (bool): If True, returns a model pre-trained on ImageNet
+ progress (bool): If True, displays a progress bar of the download to stderr
+ """
+ return _resnet('resnet101', Bottleneck, [3, 4, 23, 3], pretrained, progress,
+ **kwargs)
+
+
+def resnet152(pretrained=False, progress=True, **kwargs):
+ r"""ResNet-152 model from
+ `"Deep Residual Learning for Image Recognition" `_
+
+ Args:
+ pretrained (bool): If True, returns a model pre-trained on ImageNet
+ progress (bool): If True, displays a progress bar of the download to stderr
+ """
+ return _resnet('resnet152', Bottleneck, [3, 8, 36, 3], pretrained, progress,
+ **kwargs)
+
+
+def resnext50_32x4d(pretrained=False, progress=True, **kwargs):
+ r"""ResNeXt-50 32x4d model from
+ `"Aggregated Residual Transformation for Deep Neural Networks" `_
+
+ Args:
+ pretrained (bool): If True, returns a model pre-trained on ImageNet
+ progress (bool): If True, displays a progress bar of the download to stderr
+ """
+ kwargs['groups'] = 32
+ kwargs['width_per_group'] = 4
+ return _resnet('resnext50_32x4d', Bottleneck, [3, 4, 6, 3],
+ pretrained, progress, **kwargs)
+
+
+def resnext101_32x8d(pretrained=False, progress=True, **kwargs):
+ r"""ResNeXt-101 32x8d model from
+ `"Aggregated Residual Transformation for Deep Neural Networks" `_
+
+ Args:
+ pretrained (bool): If True, returns a model pre-trained on ImageNet
+ progress (bool): If True, displays a progress bar of the download to stderr
+ """
+ kwargs['groups'] = 32
+ kwargs['width_per_group'] = 8
+ return _resnet('resnext101_32x8d', Bottleneck, [3, 4, 23, 3],
+ pretrained, progress, **kwargs)
+
+
+def wide_resnet50_2(pretrained=False, progress=True, **kwargs):
+ r"""Wide ResNet-50-2 model from
+ `"Wide Residual Networks" `_
+
+ The model is the same as ResNet except for the bottleneck number of channels
+ which is twice larger in every block. The number of channels in outer 1x1
+ convolutions is the same, e.g. last block in ResNet-50 has 2048-512-2048
+ channels, and in Wide ResNet-50-2 has 2048-1024-2048.
+
+ Args:
+ pretrained (bool): If True, returns a model pre-trained on ImageNet
+ progress (bool): If True, displays a progress bar of the download to stderr
+ """
+ kwargs['width_per_group'] = 64 * 2
+ return _resnet('wide_resnet50_2', Bottleneck, [3, 4, 6, 3],
+ pretrained, progress, **kwargs)
+
+
+def wide_resnet101_2(pretrained=False, progress=True, **kwargs):
+ r"""Wide ResNet-101-2 model from
+ `"Wide Residual Networks" `_
+
+ The model is the same as ResNet except for the bottleneck number of channels
+ which is twice larger in every block. The number of channels in outer 1x1
+ convolutions is the same, e.g. last block in ResNet-50 has 2048-512-2048
+ channels, and in Wide ResNet-50-2 has 2048-1024-2048.
+
+ Args:
+ pretrained (bool): If True, returns a model pre-trained on ImageNet
+ progress (bool): If True, displays a progress bar of the download to stderr
+ """
+ kwargs['width_per_group'] = 64 * 2
+ return _resnet('wide_resnet101_2', Bottleneck, [3, 4, 23, 3],
+ pretrained, progress, **kwargs)
diff --git a/tracking/contrast_one2one.py b/tracking/contrast_one2one.py
index bb7cc3f..1625275 100644
--- a/tracking/contrast_one2one.py
+++ b/tracking/contrast_one2one.py
@@ -34,6 +34,7 @@ import cv2
import os
import sys
import json
+import pickle
sys.path.append(r"D:\DetectTracking")
from tracking.utils.read_data import extract_data, read_tracking_output, read_deletedBarcode_file
@@ -213,9 +214,12 @@ def get_std_barcodeDict(bcdpath):
if ext not in IMG_FORMAT: continue
imgpaths.append(imgpath)
stdBarcodeDict[barcode].extend(imgpaths)
-
- with open('stdBarcodeDict.json', 'wb') as f:
- json.dump(stdBarcodeDict, f)
+
+ jsonpath = os.path.join(r'\\192.168.1.28\share\测试_202406\contrast\barcodes', f"{barcode}.pickle")
+ with open(jsonpath, 'wb') as f:
+ pickle.dump(stdBarcodeDict, f)
+
+ print(f"Barcode: {barcode}")