first commit

.gitignore

@@ -0,0 +1,13 @@
+# Folders
+__pycache__/
+build/
+*.egg-info
+
+
+# Files
+*.weights
+*.t7
+*.mp4
+*.avi
+*.so
+*.txt

README.md

@@ -0,0 +1 @@
+# deep_count

configs/deep_sort.yaml

@@ -0,0 +1,11 @@
+DEEPSORT:
+  REID_CKPT: "./deep_sort/deep/checkpoint/ckpt.t7"
+  REID_CKPT_Car: "./deep_sort/deep/checkpoint/ckpt_car.t7"
+  MAX_DIST: 0.2
+  MIN_CONFIDENCE: 0.3
+  NMS_MAX_OVERLAP: 1.0
+  MAX_IOU_DISTANCE: 0.7
+  MAX_AGE: 70
+  N_INIT: 3
+  NN_BUDGET: 100
+

configs/yolov3.yaml

@@ -0,0 +1,7 @@
+YOLOV3:
+  CFG: "./detector/YOLOv3/cfg/yolov4.cfg"
+  WEIGHT: "./detector/YOLOv3/weight/yolov4.weights"
+  CLASS_NAMES: "./detector/YOLOv3/cfg/coco.names"
+
+  SCORE_THRESH: 0.1
+  NMS_THRESH: 0.4

configs/yolov3_tiny.yaml

@@ -0,0 +1,7 @@
+YOLOV3:
+  CFG: "./detector/YOLOv3/cfg/yolov3-tiny.cfg"
+  WEIGHT: "./detector/YOLOv3/weight/yolov3-tiny.weights"
+  CLASS_NAMES: "./detector/YOLOv3/cfg/coco.names"
+
+  SCORE_THRESH: 0.5
+  NMS_THRESH: 0.4

configs/yolov4_onnx.yaml

@@ -0,0 +1,7 @@
+YOLOV4:
+  CFG: "./detector/YOLOv3/cfg/yolov4.cfg"
+  WEIGHT: "./detector/YOLOv3/weight/yolov4_1_3_416_416_static.onnx"
+  CLASS_NAMES: "./detector/YOLOv3/cfg/coco.names"
+
+  SCORE_THRESH: 0.1
+  NMS_THRESH: 0.4

configs/yolov4_trt.yaml

@@ -0,0 +1,7 @@
+YOLOV4:
+  CFG: "./detector/YOLOv3/cfg/yolov4.cfg"
+  WEIGHT: "./detector/YOLOv3/weight/yolov4.engine"
+  CLASS_NAMES: "./detector/YOLOv3/cfg/coco.names"
+
+  SCORE_THRESH: 0.4
+  NMS_THRESH: 0.4

dataset.py

@@ -0,0 +1,111 @@
+import cv2 
+import numpy as np 
+from threading import Thread
+import time
+import os
+class LoadStreams:  # multiple IP or RTSP cameras
+    def __init__(self, sources='streams.txt', img_size=640):
+        self.mode = 'images'
+        self.img_size = img_size
+        sources = [sources]
+
+        n = len(sources)
+        self.imgs = [None] * n
+        self.sources = sources
+        for i, s in enumerate(sources):
+            # Start the thread to read frames from the video stream
+            print('%g/%g: %s... ' % (i + 1, n, s), end='')
+            cap = cv2.VideoCapture(0 if s == '0' else s)
+            assert cap.isOpened(), 'Failed to open %s' % s
+            w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+            h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+            fps = cap.get(cv2.CAP_PROP_FPS) % 100
+            _, self.imgs[i] = cap.read()  # guarantee first frame
+            thread = Thread(target=self.update, args=([i, cap]), daemon=True)
+            print(' success (%gx%g at %.2f FPS).' % (w, h, fps))
+            thread.start()
+        print('')  # newline
+
+    def update(self, index, cap):
+        # Read next stream frame in a daemon thread
+        n = 0
+        while cap.isOpened():
+            n += 1
+            # _, self.imgs[index] = cap.read()
+            cap.grab()
+            if n == 4:  # read every 4th frame
+                _, self.imgs[index] = cap.retrieve()
+                n = 0
+            time.sleep(0.01)  # wait time
+
+    def __iter__(self):
+        self.count = -1
+        return self
+
+    def __next__(self):
+        self.count += 1
+        img0 = self.imgs.copy()
+        if cv2.waitKey(1) == ord('q'):  # q to quit
+            cv2.destroyAllWindows()
+            raise StopIteration
+        return self.sources, img0, None
+
+    def __len__(self):
+        return 0  # 1E12 frames = 32 streams at 30 FPS for 30 years
+
+
+
+class datasets:  # multiple IP or RTSP cameras
+    def __init__(self, sources='streams.txt', img_size=640):
+        self.mode = 'images'
+        self.img_size = img_size
+
+        if os.path.isfile(sources):
+            with open(sources, 'r') as f:
+                sources = [x.strip() for x in f.read().splitlines() if len(x.strip())]
+        else:
+            sources = [sources]
+
+        n = len(sources)
+        self.imgs = [None] * n
+        self.sources = sources
+        for i, s in enumerate(sources):
+            # Start the thread to read frames from the video stream
+            print('%g/%g: %s... ' % (i + 1, n, s), end='')
+            cap = cv2.VideoCapture(0 if s == '0' else s)
+            assert cap.isOpened(), 'Failed to open %s' % s
+            w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+            h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+            fps = cap.get(cv2.CAP_PROP_FPS) % 100
+            _, self.imgs[i] = cap.read()  # guarantee first frame
+            thread = Thread(target=self.update, args=([i, cap]), daemon=True)
+            print(' success (%gx%g at %.2f FPS).' % (w, h, fps))
+            thread.start()
+        print('')  # newline
+
+    def update(self, index, cap):
+        # Read next stream frame in a daemon thread
+        n = 0
+        while cap.isOpened():
+            n += 1
+            # _, self.imgs[index] = cap.read()
+            cap.grab()
+            if n == 1:  # read every 4th frame
+                _, self.imgs[index] = cap.retrieve()
+                n = 0
+            time.sleep(0.01)  # wait time
+
+    def __iter__(self):
+        self.count = -1
+        return self
+
+    def __next__(self):
+        self.count += 1
+        img0 = self.imgs.copy()
+        if cv2.waitKey(1) == ord('q'):  # q to quit
+            cv2.destroyAllWindows()
+            raise StopIteration
+        return self.sources, img0, None
+
+    def __len__(self):
+        return 0  # 1E12 frames = 32 streams at 30 FPS for 30 years

deep_sort/README.md

@@ -0,0 +1,3 @@
+# Deep Sort 
+
+This is the implemention of deep sort with pytorch.

deep_sort/__init__.py

@@ -0,0 +1,24 @@
+from deep_sort.deep_sort import DeepSort  #在我们执行import时，当前目录是不会变的（就算是执行子目录的文件），还是需要完整的包名。
+
+
+__all__ = ['DeepSort', 'build_tracker','build_tracker_car']  ##import * 的时候，防止导入过多的变量，把导入的限制在__all__中
+
+def build_tracker(cfg, use_cuda):
+    return DeepSort(cfg.DEEPSORT.REID_CKPT, 
+                max_dist=cfg.DEEPSORT.MAX_DIST, min_confidence=cfg.DEEPSORT.MIN_CONFIDENCE, 
+                nms_max_overlap=cfg.DEEPSORT.NMS_MAX_OVERLAP, max_iou_distance=cfg.DEEPSORT.MAX_IOU_DISTANCE, 
+                max_age=cfg.DEEPSORT.MAX_AGE, n_init=cfg.DEEPSORT.N_INIT, nn_budget=cfg.DEEPSORT.NN_BUDGET, use_cuda=use_cuda)
+
+
+def build_tracker_car(cfg, use_cuda):
+    return DeepSort(cfg.DEEPSORT.REID_CKPT_Car, 
+                max_dist=cfg.DEEPSORT.MAX_DIST, min_confidence=cfg.DEEPSORT.MIN_CONFIDENCE, 
+                nms_max_overlap=cfg.DEEPSORT.NMS_MAX_OVERLAP, max_iou_distance=cfg.DEEPSORT.MAX_IOU_DISTANCE, 
+                max_age=cfg.DEEPSORT.MAX_AGE, n_init=cfg.DEEPSORT.N_INIT, nn_budget=cfg.DEEPSORT.NN_BUDGET, use_cuda=use_cuda,num_class = 685)
+
+
+
+
+
+
+

deep_sort/deep/evaluate.py

@@ -0,0 +1,15 @@
+import torch
+
+features = torch.load("features.pth")
+qf = features["qf"]
+ql = features["ql"]
+gf = features["gf"]
+gl = features["gl"]
+
+scores = qf.mm(gf.t())
+res = scores.topk(5, dim=1)[1][:,0]
+top1correct = gl[res].eq(ql).sum().item()
+
+print("Acc top1:{:.3f}".format(top1correct/ql.size(0)))
+
+

deep_sort/deep/feature_extractor.py

@@ -0,0 +1,55 @@
+import torch
+import torchvision.transforms as transforms
+import numpy as np
+import cv2
+import logging
+
+from deep_sort.deep.model import Net
+
+class Extractor(object):
+    def __init__(self, model_path, use_cuda=True,num_class = 751):
+        self.net = Net(reid=True,num_classes = num_class)
+        self.device = "cuda" if torch.cuda.is_available() and use_cuda else "cpu"
+        state_dict = torch.load(model_path, map_location=lambda storage, loc: storage)['net_dict']
+        self.net.load_state_dict(state_dict)
+        logger = logging.getLogger("root.tracker")
+        logger.info("Loading weights from {}... Done!".format(model_path))
+        self.net.to(self.device)
+        self.size = (64, 128)
+        self.norm = transforms.Compose([
+            transforms.ToTensor(),
+            transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
+        ])
+
+
+
+    def _preprocess(self, im_crops):
+        """
+        TODO:
+            1. to float with scale from 0 to 1
+            2. resize to (64, 128) as Market1501 dataset did
+            3. concatenate to a numpy array
+            3. to torch Tensor
+            4. normalize
+        """
+        def _resize(im, size):
+            return cv2.resize(im.astype(np.float32)/255., size)
+
+        im_batch = torch.cat([self.norm(_resize(im, self.size)).unsqueeze(0) for im in im_crops], dim=0).float()
+        return im_batch
+
+
+    def __call__(self, im_crops):
+        im_batch = self._preprocess(im_crops)
+        with torch.no_grad():
+            im_batch = im_batch.to(self.device)
+            features = self.net(im_batch)
+        return features.cpu().numpy()
+
+
+if __name__ == '__main__':
+    img = cv2.imread("demo.jpg")[:,:,(2,1,0)]
+    extr = Extractor("checkpoint/ckpt.t7")
+    feature = extr(img)
+    print(feature.shape)
+

deep_sort/deep/model.py

@@ -0,0 +1,104 @@
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+class BasicBlock(nn.Module):
+    def __init__(self, c_in, c_out,is_downsample=False):
+        super(BasicBlock,self).__init__()
+        self.is_downsample = is_downsample
+        if is_downsample:
+            self.conv1 = nn.Conv2d(c_in, c_out, 3, stride=2, padding=1, bias=False)
+        else:
+            self.conv1 = nn.Conv2d(c_in, c_out, 3, stride=1, padding=1, bias=False)
+        self.bn1 = nn.BatchNorm2d(c_out)
+        self.relu = nn.ReLU(True)
+        self.conv2 = nn.Conv2d(c_out,c_out,3,stride=1,padding=1, bias=False)
+        self.bn2 = nn.BatchNorm2d(c_out)
+        if is_downsample:
+            self.downsample = nn.Sequential(
+                nn.Conv2d(c_in, c_out, 1, stride=2, bias=False),
+                nn.BatchNorm2d(c_out)
+            )
+        elif c_in != c_out:
+            self.downsample = nn.Sequential(
+                nn.Conv2d(c_in, c_out, 1, stride=1, bias=False),
+                nn.BatchNorm2d(c_out)
+            )
+            self.is_downsample = True
+
+    def forward(self,x):
+        y = self.conv1(x)
+        y = self.bn1(y)
+        y = self.relu(y)
+        y = self.conv2(y)
+        y = self.bn2(y)
+        if self.is_downsample:
+            x = self.downsample(x)
+        return F.relu(x.add(y),True)  ##残差网络在这
+
+def make_layers(c_in,c_out,repeat_times, is_downsample=False):
+    blocks = []
+    for i in range(repeat_times):
+        if i ==0:
+            blocks += [BasicBlock(c_in,c_out, is_downsample=is_downsample),]
+        else:
+            blocks += [BasicBlock(c_out,c_out),]
+    return nn.Sequential(*blocks)
+
+class Net(nn.Module):
+    def __init__(self, num_classes=751 ,reid=False):
+        super(Net,self).__init__()
+        # 3 128 64
+        self.conv = nn.Sequential(
+            nn.Conv2d(3,64,3,stride=1,padding=1),
+            nn.BatchNorm2d(64),
+            nn.ReLU(inplace=True),
+            # nn.Conv2d(32,32,3,stride=1,padding=1),
+            # nn.BatchNorm2d(32),
+            # nn.ReLU(inplace=True),
+            nn.MaxPool2d(3,2,padding=1),
+        )
+        # 32 64 32
+        self.layer1 = make_layers(64,64,2,False)
+        # 32 64 32
+        self.layer2 = make_layers(64,128,2,True)
+        # 64 32 16
+        self.layer3 = make_layers(128,256,2,True)
+        # 128 16 8
+        self.layer4 = make_layers(256,512,2,True)
+        # 256 8 4
+        self.avgpool = nn.AvgPool2d((8,4),1)
+        # 256 1 1 
+        self.reid = reid
+        self.classifier = nn.Sequential(
+            nn.Linear(512, 256),
+            nn.BatchNorm1d(256),
+            nn.ReLU(inplace=True),
+            nn.Dropout(),
+            nn.Linear(256, num_classes),
+        )
+
+    def forward(self, x):
+        x = self.conv(x)
+        x = self.layer1(x)
+        x = self.layer2(x)
+        x = self.layer3(x)
+        x = self.layer4(x)
+        x = self.avgpool(x)
+        x = x.view(x.size(0),-1)
+        # B x 128
+        if self.reid:
+            x = x.div(x.norm(p=2,dim=1,keepdim=True))
+            return x
+        # classifier
+        x = self.classifier(x)
+        return x
+
+
+if __name__ == '__main__':
+    net = Net()
+    x = torch.randn(4,3,128,64)
+    y = net(x)
+    # import ipdb; ipdb.set_trace()
+
+