start

.env

@@ -0,0 +1 @@
+secret_key='super secret key'

deep_sort_torch/.gitignore

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

deep_sort_torch/.gitmodules

@@ -0,0 +1,6 @@
+[submodule "thirdparty/fast-reid"]
+	path = thirdparty/fast-reid
+	url = https://github.com/JDAI-CV/fast-reid.git
+[submodule "thirdparty/mmdetection"]
+	path = thirdparty/mmdetection
+	url = https://github.com/open-mmlab/mmdetection.git

deep_sort_torch/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2020 Ziqiang
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

deep_sort_torch/README.md

@@ -0,0 +1,170 @@
+# Deep Sort with PyTorch
+
+![](demo/demo.gif)
+
+## Update(1-1-2020)
+Changes
+- fix bugs
+- refactor code
+- accerate detection by adding nms on gpu
+
+## Latest Update(07-22)
+Changes
+- bug fix (Thanks @JieChen91 and @yingsen1 for bug reporting).  
+- using batch for feature extracting for each frame, which lead to a small speed up.  
+- code improvement.
+
+Futher improvement direction  
+- Train detector on specific dataset rather than the official one.
+- Retrain REID model on pedestrain dataset for better performance.
+- Replace YOLOv3 detector with advanced ones.
+
+**Any contributions to this repository is welcome!**
+
+
+## Introduction
+This is an implement of MOT tracking algorithm deep sort. Deep sort is basicly the same with sort but added a CNN model to extract features in image of human part bounded by a detector. This CNN model is indeed a RE-ID model and the detector used in [PAPER](https://arxiv.org/abs/1703.07402) is FasterRCNN , and the original source code is [HERE](https://github.com/nwojke/deep_sort).  
+However in original code, the CNN model is implemented with tensorflow, which I'm not familier with. SO I re-implemented the CNN feature extraction model with PyTorch, and changed the CNN model a little bit. Also, I use **YOLOv3** to generate bboxes instead of FasterRCNN.
+
+## Dependencies
+- python 3 (python2 not sure)
+- numpy
+- scipy
+- opencv-python
+- sklearn
+- torch >= 0.4
+- torchvision >= 0.1
+- pillow
+- vizer
+- edict
+
+## Quick Start
+0. Check all dependencies installed
+```bash
+pip install -r requirements.txt
+```
+for user in china, you can specify pypi source to accelerate install like:
+```bash
+pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
+```
+
+1. Clone this repository
+```
+git clone [email protected]:ZQPei/deep_sort_pytorch.git
+```
+
+2. Download YOLOv3 parameters
+```
+cd detector/YOLOv3/weight/
+wget https://pjreddie.com/media/files/yolov3.weights
+wget https://pjreddie.com/media/files/yolov3-tiny.weights
+cd ../../../
+```
+
+3. Download deepsort parameters ckpt.t7
+```
+cd deep_sort/deep/checkpoint
+# download ckpt.t7 from
+https://drive.google.com/drive/folders/1xhG0kRH1EX5B9_Iz8gQJb7UNnn_riXi6 to this folder
+cd ../../../
+```  
+
+4. Compile nms module
+```bash
+cd detector/YOLOv3/nms
+sh build.sh
+cd ../../..
+```
+
+Notice:
+If compiling failed, the simplist way is to **Upgrade your pytorch >= 1.1 and torchvision >= 0.3" and you can avoid the troublesome compiling problems which are most likely caused by either `gcc version too low` or `libraries missing`.
+
+5. (Optional) Prepare third party submodules
+
+[fast-reid](https://github.com/JDAI-CV/fast-reid)
+
+This library supports bagtricks, AGW and other mainstream ReID methods through providing an fast-reid adapter.
+
+to prepare our bundled fast-reid, then follow instructions in its README to install it.
+
+Please refer to `configs/fastreid.yaml` for a sample of using fast-reid. See [Model Zoo](https://github.com/JDAI-CV/fast-reid/blob/master/docs/MODEL_ZOO.md) for available methods and trained models.
+
+[MMDetection](https://github.com/open-mmlab/mmdetection)
+
+This library supports Faster R-CNN and other mainstream detection methods through providing an MMDetection adapter.
+
+to prepare our bundled MMDetection, then follow instructions in its README to install it.
+
+Please refer to `configs/mmdet.yaml` for a sample of using MMDetection. See [Model Zoo](https://github.com/open-mmlab/mmdetection/blob/master/docs/model_zoo.md) for available methods and trained models.
+
+Run
+
+```
+git submodule update --init --recursive
+```
+
+
+6. Run demo
+```
+usage: deepsort.py [-h]
+                   [--fastreid]
+                   [--config_fastreid CONFIG_FASTREID]
+                   [--mmdet]
+                   [--config_mmdetection CONFIG_MMDETECTION]
+                   [--config_detection CONFIG_DETECTION]
+                   [--config_deepsort CONFIG_DEEPSORT] [--display]
+                   [--frame_interval FRAME_INTERVAL]
+                   [--display_width DISPLAY_WIDTH]
+                   [--display_height DISPLAY_HEIGHT] [--save_path SAVE_PATH]
+                   [--cpu] [--camera CAM]
+                   VIDEO_PATH         
+
+# yolov3 + deepsort
+python deepsort.py [VIDEO_PATH]
+
+# yolov3_tiny + deepsort
+python deepsort.py [VIDEO_PATH] --config_detection ./configs/yolov3_tiny.yaml
+
+# yolov3 + deepsort on webcam
+python3 deepsort.py /dev/video0 --camera 0
+
+# yolov3_tiny + deepsort on webcam
+python3 deepsort.py /dev/video0 --config_detection ./configs/yolov3_tiny.yaml --camera 0
+
+# fast-reid + deepsort
+python deepsort.py [VIDEO_PATH] --fastreid [--config_fastreid ./configs/fastreid.yaml]
+
+# MMDetection + deepsort
+python deepsort.py [VIDEO_PATH] --mmdet [--config_mmdetection ./configs/mmdet.yaml]
+```
+Use `--display` to enable display.  
+Results will be saved to `./output/results.avi` and `./output/results.txt`.
+
+All files above can also be accessed from BaiduDisk!  
+linker：[BaiduDisk](https://pan.baidu.com/s/1YJ1iPpdFTlUyLFoonYvozg)
+passwd：fbuw
+
+## Training the RE-ID model
+The original model used in paper is in original_model.py, and its parameter here [original_ckpt.t7](https://drive.google.com/drive/folders/1xhG0kRH1EX5B9_Iz8gQJb7UNnn_riXi6).  
+
+To train the model, first you need download [Market1501](http://www.liangzheng.com.cn/Project/project_reid.html) dataset or [Mars](http://www.liangzheng.com.cn/Project/project_mars.html) dataset.  
+
+Then you can try [train.py](deep_sort/deep/train.py) to train your own parameter and evaluate it using [test.py](deep_sort/deep/test.py) and [evaluate.py](deep_sort/deep/evalute.py).
+![train.jpg](deep_sort/deep/train.jpg)
+
+## Demo videos and images
+[demo.avi](https://drive.google.com/drive/folders/1xhG0kRH1EX5B9_Iz8gQJb7UNnn_riXi6)
+[demo2.avi](https://drive.google.com/drive/folders/1xhG0kRH1EX5B9_Iz8gQJb7UNnn_riXi6)
+
+![1.jpg](demo/1.jpg)
+![2.jpg](demo/2.jpg)
+
+
+## References
+- paper: [Simple Online and Realtime Tracking with a Deep Association Metric](https://arxiv.org/abs/1703.07402)
+
+- code: [nwojke/deep_sort](https://github.com/nwojke/deep_sort)
+
+- paper: [YOLOv3](https://pjreddie.com/media/files/papers/YOLOv3.pdf)
+
+- code: [Joseph Redmon/yolov3](https://pjreddie.com/darknet/yolo/)

deep_sort_torch/configs/deep_sort.yaml

@@ -0,0 +1,10 @@
+DEEPSORT:
+  REID_CKPT: "./deep_sort/deep/checkpoint/ckpt.t7"
+  MAX_DIST: 0.2
+  MIN_CONFIDENCE: 0.3
+  NMS_MAX_OVERLAP: 0.5
+  MAX_IOU_DISTANCE: 0.7
+  MAX_AGE: 70
+  N_INIT: 3
+  NN_BUDGET: 100
+  

deep_sort_torch/configs/fastreid.yaml

@@ -0,0 +1,3 @@
+FASTREID:
+  CFG: "thirdparty/fast-reid/configs/Market1501/bagtricks_R50.yml"
+  CHECKPOINT: "deep_sort/deep/checkpoint/market_bot_R50.pth"

deep_sort_torch/configs/mmdet.yaml

@@ -0,0 +1,5 @@
+MMDET:
+  CFG: "thirdparty/mmdetection/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py"
+  CHECKPOINT: "detector/MMDet/weight/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth"
+
+  SCORE_THRESH: 0.5

deep_sort_torch/configs/yolov3.yaml

@@ -0,0 +1,7 @@
+YOLOV3:
+  CFG: "./detector/YOLOv3/cfg/yolo_v3.cfg"
+  WEIGHT: "./detector/YOLOv3/weight/yolov3.weights"
+  CLASS_NAMES: "./detector/YOLOv3/cfg/coco.names"
+
+  SCORE_THRESH: 0.5
+  NMS_THRESH: 0.4

deep_sort_torch/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

deep_sort_torch/deep_sort/README.md

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

deep_sort_torch/deep_sort/__init__.py

@@ -0,0 +1,28 @@
+from .deep_sort import DeepSort
+
+
+__all__ = ['DeepSort', 'build_tracker']
+
+
+def build_tracker(cfg, use_cuda):
+    if cfg.USE_FASTREID:
+        return DeepSort(model_path=cfg.FASTREID.CHECKPOINT, model_config=cfg.FASTREID.CFG, 
+                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)
+
+    else:
+        return DeepSort(model_path=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)
+    
+
+
+
+
+
+
+
+
+

deep_sort_torch/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_torch/deep_sort/deep/feature_extractor.py

@@ -0,0 +1,95 @@
+import torch
+import torchvision.transforms as transforms
+import numpy as np
+import cv2
+import logging
+
+from .model import Net
+# from .fastreid.config import get_cfg
+# from .fastreid.engine import DefaultTrainer
+# from .fastreid.utils.checkpoint import Checkpointer
+
+class Extractor(object):
+    def __init__(self, model_path, use_cuda=True):
+        self.net = Net(reid=True)
+        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()
+
+class FastReIDExtractor(object):
+    def __init__(self, model_config, model_path, use_cuda=True):
+        cfg = get_cfg()
+        cfg.merge_from_file(model_config)
+        cfg.MODEL.BACKBONE.PRETRAIN = False
+        self.net = DefaultTrainer.build_model(cfg)
+        self.device = "cuda" if torch.cuda.is_available() and use_cuda else "cpu"
+
+        Checkpointer(self.net).load(model_path)
+        logger = logging.getLogger("root.tracker")
+        logger.info("Loading weights from {}... Done!".format(model_path))
+        self.net.to(self.device)
+        self.net.eval()
+        height, width = cfg.INPUT.SIZE_TEST
+        self.size = (width, height)
+        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):
+        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_torch/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)
+
+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()
+
+

deep_sort_torch/deep_sort/deep/original_model.py

@@ -0,0 +1,106 @@
+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)
+
+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=625 ,reid=False):
+        super(Net,self).__init__()
+        # 3 128 64
+        self.conv = nn.Sequential(
+            nn.Conv2d(3,32,3,stride=1,padding=1),
+            nn.BatchNorm2d(32),
+            nn.ELU(inplace=True),
+            nn.Conv2d(32,32,3,stride=1,padding=1),
+            nn.BatchNorm2d(32),
+            nn.ELU(inplace=True),
+            nn.MaxPool2d(3,2,padding=1),
+        )
+        # 32 64 32
+        self.layer1 = make_layers(32,32,2,False)
+        # 32 64 32
+        self.layer2 = make_layers(32,64,2,True)
+        # 64 32 16
+        self.layer3 = make_layers(64,128,2,True)
+        # 128 16 8
+        self.dense = nn.Sequential(
+            nn.Dropout(p=0.6),
+            nn.Linear(128*16*8, 128),
+            nn.BatchNorm1d(128),
+            nn.ELU(inplace=True)
+        )
+        # 256 1 1 
+        self.reid = reid
+        self.batch_norm = nn.BatchNorm1d(128)
+        self.classifier = nn.Sequential(
+            nn.Linear(128, num_classes),
+        )
+    
+    def forward(self, x):
+        x = self.conv(x)
+        x = self.layer1(x)
+        x = self.layer2(x)
+        x = self.layer3(x)
+
+        x = x.view(x.size(0),-1)
+        if self.reid:
+            x = self.dense[0](x)
+            x = self.dense[1](x)
+            x = x.div(x.norm(p=2,dim=1,keepdim=True))
+            return x
+        x = self.dense(x)
+        # B x 128
+        # classifier
+        x = self.classifier(x)
+        return x
+
+
+if __name__ == '__main__':
+    net = Net(reid=True)
+    x = torch.randn(4,3,128,64)
+    y = net(x)
+    import ipdb; ipdb.set_trace()
+
+

deep_sort_torch/deep_sort/deep/test.py

@@ -0,0 +1,77 @@
+import torch
+import torch.backends.cudnn as cudnn
+import torchvision
+
+import argparse
+import os
+
+from model import Net
+
+parser = argparse.ArgumentParser(description="Train on market1501")
+parser.add_argument("--data-dir",default='data',type=str)
+parser.add_argument("--no-cuda",action="store_true")
+parser.add_argument("--gpu-id",default=0,type=int)
+args = parser.parse_args()
+
+# device
+device = "cuda:{}".format(args.gpu_id) if torch.cuda.is_available() and not args.no_cuda else "cpu"
+if torch.cuda.is_available() and not args.no_cuda:
+    cudnn.benchmark = True
+
+# data loader
+root = args.data_dir
+query_dir = os.path.join(root,"query")
+gallery_dir = os.path.join(root,"gallery")
+transform = torchvision.transforms.Compose([
+    torchvision.transforms.Resize((128,64)),
+    torchvision.transforms.ToTensor(),
+    torchvision.transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
+])
+queryloader = torch.utils.data.DataLoader(
+    torchvision.datasets.ImageFolder(query_dir, transform=transform),
+    batch_size=64, shuffle=False
+)
+galleryloader = torch.utils.data.DataLoader(
+    torchvision.datasets.ImageFolder(gallery_dir, transform=transform),
+    batch_size=64, shuffle=False
+)
+
+# net definition
+net = Net(reid=True)
+assert os.path.isfile("./checkpoint/ckpt.t7"), "Error: no checkpoint file found!"
+print('Loading from checkpoint/ckpt.t7')
+checkpoint = torch.load("./checkpoint/ckpt.t7")
+net_dict = checkpoint['net_dict']
+net.load_state_dict(net_dict, strict=False)
+net.eval()
+net.to(device)
+
+# compute features
+query_features = torch.tensor([]).float()
+query_labels = torch.tensor([]).long()
+gallery_features = torch.tensor([]).float()
+gallery_labels = torch.tensor([]).long()
+
+with torch.no_grad():
+    for idx,(inputs,labels) in enumerate(queryloader):
+        inputs = inputs.to(device)
+        features = net(inputs).cpu()
+        query_features = torch.cat((query_features, features), dim=0)
+        query_labels = torch.cat((query_labels, labels))
+
+    for idx,(inputs,labels) in enumerate(galleryloader):
+        inputs = inputs.to(device)
+        features = net(inputs).cpu()
+        gallery_features = torch.cat((gallery_features, features), dim=0)
+        gallery_labels = torch.cat((gallery_labels, labels))
+
+gallery_labels -= 2
+
+# save features
+features = {
+    "qf": query_features,
+    "ql": query_labels,
+    "gf": gallery_features,
+    "gl": gallery_labels
+}
+torch.save(features,"features.pth")

deep_sort_torch/deep_sort/deep/train.py

@@ -0,0 +1,189 @@
+import argparse
+import os
+import time
+
+import numpy as np
+import matplotlib.pyplot as plt
+import torch
+import torch.backends.cudnn as cudnn
+import torchvision
+
+from model import Net
+
+parser = argparse.ArgumentParser(description="Train on market1501")
+parser.add_argument("--data-dir",default='data',type=str)
+parser.add_argument("--no-cuda",action="store_true")
+parser.add_argument("--gpu-id",default=0,type=int)
+parser.add_argument("--lr",default=0.1, type=float)
+parser.add_argument("--interval",'-i',default=20,type=int)
+parser.add_argument('--resume', '-r',action='store_true')
+args = parser.parse_args()
+
+# device
+device = "cuda:{}".format(args.gpu_id) if torch.cuda.is_available() and not args.no_cuda else "cpu"
+if torch.cuda.is_available() and not args.no_cuda:
+    cudnn.benchmark = True
+
+# data loading
+root = args.data_dir
+train_dir = os.path.join(root,"train")
+test_dir = os.path.join(root,"test")
+transform_train = torchvision.transforms.Compose([
+    torchvision.transforms.RandomCrop((128,64),padding=4),
+    torchvision.transforms.RandomHorizontalFlip(),
+    torchvision.transforms.ToTensor(),
+    torchvision.transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
+])
+transform_test = torchvision.transforms.Compose([
+    torchvision.transforms.Resize((128,64)),
+    torchvision.transforms.ToTensor(),
+    torchvision.transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
+])
+trainloader = torch.utils.data.DataLoader(
+    torchvision.datasets.ImageFolder(train_dir, transform=transform_train),
+    batch_size=64,shuffle=True
+)
+testloader = torch.utils.data.DataLoader(
+    torchvision.datasets.ImageFolder(test_dir, transform=transform_test),
+    batch_size=64,shuffle=True
+)
+num_classes = max(len(trainloader.dataset.classes), len(testloader.dataset.classes))
+
+# net definition
+start_epoch = 0
+net = Net(num_classes=num_classes)
+if args.resume:
+    assert os.path.isfile("./checkpoint/ckpt.t7"), "Error: no checkpoint file found!"
+    print('Loading from checkpoint/ckpt.t7')
+    checkpoint = torch.load("./checkpoint/ckpt.t7")
+    # import ipdb; ipdb.set_trace()
+    net_dict = checkpoint['net_dict']
+    net.load_state_dict(net_dict)
+    best_acc = checkpoint['acc']
+    start_epoch = checkpoint['epoch']
+net.to(device)
+
+# loss and optimizer
+criterion = torch.nn.CrossEntropyLoss()
+optimizer = torch.optim.SGD(net.parameters(), args.lr, momentum=0.9, weight_decay=5e-4)
+best_acc = 0.
+
+# train function for each epoch
+def train(epoch):
+    print("\nEpoch : %d"%(epoch+1))
+    net.train()
+    training_loss = 0.
+    train_loss = 0.
+    correct = 0
+    total = 0
+    interval = args.interval
+    start = time.time()
+    for idx, (inputs, labels) in enumerate(trainloader):
+        # forward
+        inputs,labels = inputs.to(device),labels.to(device)
+        outputs = net(inputs)
+        loss = criterion(outputs, labels)
+
+        # backward
+        optimizer.zero_grad()
+        loss.backward()
+        optimizer.step()
+
+        # accumurating
+        training_loss += loss.item()
+        train_loss += loss.item()
+        correct += outputs.max(dim=1)[1].eq(labels).sum().item()
+        total += labels.size(0)
+
+        # print 
+        if (idx+1)%interval == 0:
+            end = time.time()
+            print("[progress:{:.1f}%]time:{:.2f}s Loss:{:.5f} Correct:{}/{} Acc:{:.3f}%".format(
+                100.*(idx+1)/len(trainloader), end-start, training_loss/interval, correct, total, 100.*correct/total
+            ))
+            training_loss = 0.
+            start = time.time()
+    
+    return train_loss/len(trainloader), 1.- correct/total
+
+def test(epoch):
+    global best_acc
+    net.eval()
+    test_loss = 0.
+    correct = 0
+    total = 0
+    start = time.time()
+    with torch.no_grad():
+        for idx, (inputs, labels) in enumerate(testloader):
+            inputs, labels = inputs.to(device), labels.to(device)
+            outputs = net(inputs)
+            loss = criterion(outputs, labels)
+
+            test_loss += loss.item()
+            correct += outputs.max(dim=1)[1].eq(labels).sum().item()
+            total += labels.size(0)
+        
+        print("Testing ...")
+        end = time.time()
+        print("[progress:{:.1f}%]time:{:.2f}s Loss:{:.5f} Correct:{}/{} Acc:{:.3f}%".format(
+                100.*(idx+1)/len(testloader), end-start, test_loss/len(testloader), correct, total, 100.*correct/total
+            ))
+
+    # saving checkpoint
+    acc = 100.*correct/total
+    if acc > best_acc:
+        best_acc = acc
+        print("Saving parameters to checkpoint/ckpt.t7")
+        checkpoint = {
+            'net_dict':net.state_dict(),
+            'acc':acc,
+            'epoch':epoch,
+        }
+        if not os.path.isdir('checkpoint'):
+            os.mkdir('checkpoint')
+        torch.save(checkpoint, './checkpoint/ckpt.t7')
+
+    return test_loss/len(testloader), 1.- correct/total
+
+# plot figure
+x_epoch = []
+record = {'train_loss':[], 'train_err':[], 'test_loss':[], 'test_err':[]}
+fig = plt.figure()
+ax0 = fig.add_subplot(121, title="loss")
+ax1 = fig.add_subplot(122, title="top1err")
+def draw_curve(epoch, train_loss, train_err, test_loss, test_err):
+    global record
+    record['train_loss'].append(train_loss)
+    record['train_err'].append(train_err)
+    record['test_loss'].append(test_loss)
+    record['test_err'].append(test_err)
+
+    x_epoch.append(epoch)
+    ax0.plot(x_epoch, record['train_loss'], 'bo-', label='train')
+    ax0.plot(x_epoch, record['test_loss'], 'ro-', label='val')
+    ax1.plot(x_epoch, record['train_err'], 'bo-', label='train')
+    ax1.plot(x_epoch, record['test_err'], 'ro-', label='val')
+    if epoch == 0:
+        ax0.legend()
+        ax1.legend()
+    fig.savefig("train.jpg")
+
+# lr decay
+def lr_decay():
+    global optimizer
+    for params in optimizer.param_groups:
+        params['lr'] *= 0.1
+        lr = params['lr']
+        print("Learning rate adjusted to {}".format(lr))
+
+def main():
+    for epoch in range(start_epoch, start_epoch+40):
+        train_loss, train_err = train(epoch)
+        test_loss, test_err = test(epoch)
+        draw_curve(epoch, train_loss, train_err, test_loss, test_err)
+        if (epoch+1)%20==0:
+            lr_decay()
+
+
+if __name__ == '__main__':
+    main()

deep_sort_torch/deep_sort/deep_sort.py

@@ -0,0 +1,117 @@
+import numpy as np
+import torch
+
+from .deep.feature_extractor import Extractor, FastReIDExtractor
+from .sort.nn_matching import NearestNeighborDistanceMetric
+from .sort.preprocessing import non_max_suppression
+from .sort.detection import Detection
+from .sort.tracker import Tracker
+
+
+__all__ = ['DeepSort']
+
+
+class DeepSort(object):
+    def __init__(self, model_path, model_config=None, 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, use_cuda=True):
+        self.min_confidence = min_confidence
+        self.nms_max_overlap = nms_max_overlap
+
+        if model_config is None:
+            self.extractor = Extractor(model_path, use_cuda=use_cuda)
+        else:
+            self.extractor = FastReIDExtractor(model_config, model_path, use_cuda=use_cuda)
+
+        max_cosine_distance = max_dist
+        metric = NearestNeighborDistanceMetric("cosine", max_cosine_distance, nn_budget)
+        self.tracker = Tracker(metric, max_iou_distance=max_iou_distance, max_age=max_age, n_init=n_init)
+
+    def update(self, bbox_xywh, confidences, ori_img):
+        self.height, self.width = ori_img.shape[:2]
+        # generate detections
+        features = self._get_features(bbox_xywh, ori_img)
+        bbox_tlwh = self._xywh_to_tlwh(bbox_xywh)
+        detections = [Detection(bbox_tlwh[i], conf, features[i]) for i,conf in enumerate(confidences) if conf>self.min_confidence]
+
+        # run on non-maximum supression
+        boxes = np.array([d.tlwh for d in detections])
+        scores = np.array([d.confidence for d in detections])
+        indices = non_max_suppression(boxes, self.nms_max_overlap, scores)
+        detections = [detections[i] for i in indices]
+
+        # update tracker
+        self.tracker.predict()
+        self.tracker.update(detections)
+
+        # output bbox identities
+        outputs = []
+        for track in self.tracker.tracks:
+            if not track.is_confirmed() or track.time_since_update > 1:
+                continue
+            box = track.to_tlwh()
+            x1,y1,x2,y2 = self._tlwh_to_xyxy(box)
+            track_id = track.track_id
+            outputs.append(np.array([x1,y1,x2,y2,track_id], dtype=np.int))
+        if len(outputs) > 0:
+            outputs = np.stack(outputs,axis=0)
+        return outputs
+
+
+    """
+    TODO:
+        Convert bbox from xc_yc_w_h to xtl_ytl_w_h
+    Thanks [email protected] for reporting this bug!
+    """
+    @staticmethod
+    def _xywh_to_tlwh(bbox_xywh):
+        if isinstance(bbox_xywh, np.ndarray):
+            bbox_tlwh = bbox_xywh.copy()
+        elif isinstance(bbox_xywh, torch.Tensor):
+            bbox_tlwh = bbox_xywh.clone()
+        bbox_tlwh[:,0] = bbox_xywh[:,0] - bbox_xywh[:,2]/2.
+        bbox_tlwh[:,1] = bbox_xywh[:,1] - bbox_xywh[:,3]/2.
+        return bbox_tlwh
+
+
+    def _xywh_to_xyxy(self, bbox_xywh):
+        x,y,w,h = bbox_xywh
+        x1 = max(int(x-w/2),0)
+        x2 = min(int(x+w/2),self.width-1)
+        y1 = max(int(y-h/2),0)
+        y2 = min(int(y+h/2),self.height-1)
+        return x1,y1,x2,y2
+
+    def _tlwh_to_xyxy(self, bbox_tlwh):
+        """
+        TODO:
+            Convert bbox from xtl_ytl_w_h to xc_yc_w_h
+        Thanks [email protected] for reporting this bug!
+        """
+        x,y,w,h = bbox_tlwh
+        x1 = max(int(x),0)
+        x2 = min(int(x+w),self.width-1)
+        y1 = max(int(y),0)
+        y2 = min(int(y+h),self.height-1)
+        return x1,y1,x2,y2
+
+    def _xyxy_to_tlwh(self, bbox_xyxy):
+        x1,y1,x2,y2 = bbox_xyxy
+
+        t = x1
+        l = y1
+        w = int(x2-x1)
+        h = int(y2-y1)
+        return t,l,w,h
+    
+    def _get_features(self, bbox_xywh, ori_img):
+        im_crops = []
+        for box in bbox_xywh:
+            x1,y1,x2,y2 = self._xywh_to_xyxy(box)
+            im = ori_img[y1:y2,x1:x2]
+            im_crops.append(im)
+        if im_crops:
+            features = self.extractor(im_crops)
+        else:
+            features = np.array([])
+        return features
+
+

deep_sort_torch/deep_sort/sort/detection.py

@@ -0,0 +1,49 @@
+# vim: expandtab:ts=4:sw=4
+import numpy as np
+
+
+class Detection(object):
+    """
+    This class represents a bounding box detection in a single image.
+
+    Parameters
+    ----------
+    tlwh : array_like
+        Bounding box in format `(x, y, w, h)`.
+    confidence : float
+        Detector confidence score.
+    feature : array_like
+        A feature vector that describes the object contained in this image.
+
+    Attributes
+    ----------
+    tlwh : ndarray
+        Bounding box in format `(top left x, top left y, width, height)`.
+    confidence : ndarray
+        Detector confidence score.
+    feature : ndarray | NoneType
+        A feature vector that describes the object contained in this image.
+
+    """
+
+    def __init__(self, tlwh, confidence, feature):
+        self.tlwh = np.asarray(tlwh, dtype=np.float)
+        self.confidence = float(confidence)
+        self.feature = np.asarray(feature, dtype=np.float32)
+
+    def to_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
+
+    def to_xyah(self):
+        """Convert bounding box to format `(center x, center y, aspect ratio,
+        height)`, where the aspect ratio is `width / height`.
+        """
+        ret = self.tlwh.copy()
+        ret[:2] += ret[2:] / 2
+        ret[2] /= ret[3]
+        return ret

deep_sort_torch/deep_sort/sort/iou_matching.py

@@ -0,0 +1,81 @@
+# vim: expandtab:ts=4:sw=4
+from __future__ import absolute_import
+import numpy as np
+from . import linear_assignment
+
+
+def iou(bbox, candidates):
+    """Computer intersection over union.
+
+    Parameters
+    ----------
+    bbox : ndarray
+        A bounding box in format `(top left x, top left y, width, height)`.
+    candidates : ndarray
+        A matrix of candidate bounding boxes (one per row) in the same format
+        as `bbox`.
+
+    Returns
+    -------
+    ndarray
+        The intersection over union in [0, 1] between the `bbox` and each
+        candidate. A higher score means a larger fraction of the `bbox` is
+        occluded by the candidate.
+
+    """
+    bbox_tl, bbox_br = bbox[:2], bbox[:2] + bbox[2:]
+    candidates_tl = candidates[:, :2]
+    candidates_br = candidates[:, :2] + candidates[:, 2:]
+
+    tl = np.c_[np.maximum(bbox_tl[0], candidates_tl[:, 0])[:, np.newaxis],
+               np.maximum(bbox_tl[1], candidates_tl[:, 1])[:, np.newaxis]]
+    br = np.c_[np.minimum(bbox_br[0], candidates_br[:, 0])[:, np.newaxis],
+               np.minimum(bbox_br[1], candidates_br[:, 1])[:, np.newaxis]]
+    wh = np.maximum(0., br - tl)
+
+    area_intersection = wh.prod(axis=1)
+    area_bbox = bbox[2:].prod()
+    area_candidates = candidates[:, 2:].prod(axis=1)
+    return area_intersection / (area_bbox + area_candidates - area_intersection)
+
+
+def iou_cost(tracks, detections, track_indices=None,
+             detection_indices=None):
+    """An intersection over union distance metric.
+
+    Parameters
+    ----------
+    tracks : List[deep_sort.track.Track]
+        A list of tracks.
+    detections : List[deep_sort.detection.Detection]
+        A list of detections.
+    track_indices : Optional[List[int]]
+        A list of indices to tracks that should be matched. Defaults to
+        all `tracks`.
+    detection_indices : Optional[List[int]]
+        A list of indices to detections that should be matched. Defaults
+        to all `detections`.
+
+    Returns
+    -------
+    ndarray
+        Returns a cost matrix of shape
+        len(track_indices), len(detection_indices) where entry (i, j) is
+        `1 - iou(tracks[track_indices[i]], detections[detection_indices[j]])`.
+
+    """
+    if track_indices is None:
+        track_indices = np.arange(len(tracks))
+    if detection_indices is None:
+        detection_indices = np.arange(len(detections))
+
+    cost_matrix = np.zeros((len(track_indices), len(detection_indices)))
+    for row, track_idx in enumerate(track_indices):
+        if tracks[track_idx].time_since_update > 1:
+            cost_matrix[row, :] = linear_assignment.INFTY_COST
+            continue
+
+        bbox = tracks[track_idx].to_tlwh()
+        candidates = np.asarray([detections[i].tlwh for i in detection_indices])
+        cost_matrix[row, :] = 1. - iou(bbox, candidates)
+    return cost_matrix

deep_sort_torch/deep_sort/sort/kalman_filter.py

@@ -0,0 +1,229 @@
+# vim: expandtab:ts=4:sw=4
+import numpy as np
+import scipy.linalg
+
+
+"""
+Table for the 0.95 quantile of the chi-square distribution with N degrees of
+freedom (contains values for N=1, ..., 9). Taken from MATLAB/Octave's chi2inv
+function and used as Mahalanobis gating threshold.
+"""
+chi2inv95 = {
+    1: 3.8415,
+    2: 5.9915,
+    3: 7.8147,
+    4: 9.4877,
+    5: 11.070,
+    6: 12.592,
+    7: 14.067,
+    8: 15.507,
+    9: 16.919}
+
+
+class KalmanFilter(object):
+    """
+    A simple Kalman filter for tracking bounding boxes in image space.
+
+    The 8-dimensional state space
+
+        x, y, a, h, vx, vy, va, vh
+
+    contains the bounding box center position (x, y), aspect ratio a, height h,
+    and their respective velocities.
+
+    Object motion follows a constant velocity model. The bounding box location
+    (x, y, a, h) is taken as direct observation of the state space (linear
+    observation model).
+
+    """
+
+    def __init__(self):
+        ndim, dt = 4, 1.
+
+        # Create Kalman filter model matrices.
+        self._motion_mat = np.eye(2 * ndim, 2 * ndim)
+        for i in range(ndim):
+            self._motion_mat[i, ndim + i] = dt
+        self._update_mat = np.eye(ndim, 2 * ndim)
+
+        # Motion and observation uncertainty are chosen relative to the current
+        # state estimate. These weights control the amount of uncertainty in
+        # the model. This is a bit hacky.
+        self._std_weight_position = 1. / 20
+        self._std_weight_velocity = 1. / 160
+
+    def initiate(self, measurement):
+        """Create track from unassociated measurement.
+
+        Parameters
+        ----------
+        measurement : ndarray
+            Bounding box coordinates (x, y, a, h) with center position (x, y),
+            aspect ratio a, and height h.
+
+        Returns
+        -------
+        (ndarray, ndarray)
+            Returns the mean vector (8 dimensional) and covariance matrix (8x8
+            dimensional) of the new track. Unobserved velocities are initialized
+            to 0 mean.
+
+        """
+        mean_pos = measurement
+        mean_vel = np.zeros_like(mean_pos)
+        mean = np.r_[mean_pos, mean_vel]
+
+        std = [
+            2 * self._std_weight_position * measurement[3],
+            2 * self._std_weight_position * measurement[3],
+            1e-2,
+            2 * self._std_weight_position * measurement[3],
+            10 * self._std_weight_velocity * measurement[3],
+            10 * self._std_weight_velocity * measurement[3],
+            1e-5,
+            10 * self._std_weight_velocity * measurement[3]]
+        covariance = np.diag(np.square(std))
+        return mean, covariance
+
+    def predict(self, mean, covariance):
+        """Run Kalman filter prediction step.
+
+        Parameters
+        ----------
+        mean : ndarray
+            The 8 dimensional mean vector of the object state at the previous
+            time step.
+        covariance : ndarray
+            The 8x8 dimensional covariance matrix of the object state at the
+            previous time step.
+
+        Returns
+        -------
+        (ndarray, ndarray)
+            Returns the mean vector and covariance matrix of the predicted
+            state. Unobserved velocities are initialized to 0 mean.
+
+        """
+        std_pos = [
+            self._std_weight_position * mean[3],
+            self._std_weight_position * mean[3],
+            1e-2,
+            self._std_weight_position * mean[3]]
+        std_vel = [
+            self._std_weight_velocity * mean[3],
+            self._std_weight_velocity * mean[3],
+            1e-5,
+            self._std_weight_velocity * mean[3]]
+        motion_cov = np.diag(np.square(np.r_[std_pos, std_vel]))
+
+        mean = np.dot(self._motion_mat, mean)
+        covariance = np.linalg.multi_dot((
+            self._motion_mat, covariance, self._motion_mat.T)) + motion_cov
+
+        return mean, covariance
+
+    def project(self, mean, covariance):
+        """Project state distribution to measurement space.
+
+        Parameters
+        ----------
+        mean : ndarray
+            The state's mean vector (8 dimensional array).
+        covariance : ndarray
+            The state's covariance matrix (8x8 dimensional).
+
+        Returns
+        -------
+        (ndarray, ndarray)
+            Returns the projected mean and covariance matrix of the given state
+            estimate.
+
+        """
+        std = [
+            self._std_weight_position * mean[3],
+            self._std_weight_position * mean[3],
+            1e-1,
+            self._std_weight_position * mean[3]]
+        innovation_cov = np.diag(np.square(std))
+
+        mean = np.dot(self._update_mat, mean)
+        covariance = np.linalg.multi_dot((
+            self._update_mat, covariance, self._update_mat.T))
+        return mean, covariance + innovation_cov
+
+    def update(self, mean, covariance, measurement):
+        """Run Kalman filter correction step.
+
+        Parameters
+        ----------
+        mean : ndarray
+            The predicted state's mean vector (8 dimensional).
+        covariance : ndarray
+            The state's covariance matrix (8x8 dimensional).
+        measurement : ndarray
+            The 4 dimensional measurement vector (x, y, a, h), where (x, y)
+            is the center position, a the aspect ratio, and h the height of the
+            bounding box.
+
+        Returns
+        -------
+        (ndarray, ndarray)
+            Returns the measurement-corrected state distribution.
+
+        """
+        projected_mean, projected_cov = self.project(mean, covariance)
+
+        chol_factor, lower = scipy.linalg.cho_factor(
+            projected_cov, lower=True, check_finite=False)
+        kalman_gain = scipy.linalg.cho_solve(
+            (chol_factor, lower), np.dot(covariance, self._update_mat.T).T,
+            check_finite=False).T
+        innovation = measurement - projected_mean
+
+        new_mean = mean + np.dot(innovation, kalman_gain.T)
+        new_covariance = covariance - np.linalg.multi_dot((
+            kalman_gain, projected_cov, kalman_gain.T))
+        return new_mean, new_covariance
+
+    def gating_distance(self, mean, covariance, measurements,
+                        only_position=False):
+        """Compute gating distance between state distribution and measurements.
+
+        A suitable distance threshold can be obtained from `chi2inv95`. If
+        `only_position` is False, the chi-square distribution has 4 degrees of
+        freedom, otherwise 2.
+
+        Parameters
+        ----------
+        mean : ndarray
+            Mean vector over the state distribution (8 dimensional).
+        covariance : ndarray
+            Covariance of the state distribution (8x8 dimensional).
+        measurements : ndarray
+            An Nx4 dimensional matrix of N measurements, each in
+            format (x, y, a, h) where (x, y) is the bounding box center
+            position, a the aspect ratio, and h the height.
+        only_position : Optional[bool]
+            If True, distance computation is done with respect to the bounding
+            box center position only.
+
+        Returns
+        -------
+        ndarray
+            Returns an array of length N, where the i-th element contains the
+            squared Mahalanobis distance between (mean, covariance) and
+            `measurements[i]`.
+
+        """
+        mean, covariance = self.project(mean, covariance)
+        if only_position:
+            mean, covariance = mean[:2], covariance[:2, :2]
+            measurements = measurements[:, :2]
+
+        cholesky_factor = np.linalg.cholesky(covariance)
+        d = measurements - mean
+        z = scipy.linalg.solve_triangular(
+            cholesky_factor, d.T, lower=True, check_finite=False,
+            overwrite_b=True)
+        squared_maha = np.sum(z * z, axis=0)
+        return squared_maha

deep_sort_torch/deep_sort/sort/linear_assignment.py

@@ -0,0 +1,192 @@
+# vim: expandtab:ts=4:sw=4
+from __future__ import absolute_import
+import numpy as np
+# from sklearn.utils.linear_assignment_ import linear_assignment
+from scipy.optimize import linear_sum_assignment as linear_assignment
+from . import kalman_filter
+
+
+INFTY_COST = 1e+5
+
+
+def min_cost_matching(
+        distance_metric, max_distance, tracks, detections, track_indices=None,
+        detection_indices=None):
+    """Solve linear assignment problem.
+
+    Parameters
+    ----------
+    distance_metric : Callable[List[Track], List[Detection], List[int], List[int]) -> ndarray
+        The distance metric is given a list of tracks and detections as well as
+        a list of N track indices and M detection indices. The metric should
+        return the NxM dimensional cost matrix, where element (i, j) is the
+        association cost between the i-th track in the given track indices and
+        the j-th detection in the given detection_indices.
+    max_distance : float
+        Gating threshold. Associations with cost larger than this value are
+        disregarded.
+    tracks : List[track.Track]
+        A list of predicted tracks at the current time step.
+    detections : List[detection.Detection]
+        A list of detections at the current time step.
+    track_indices : List[int]
+        List of track indices that maps rows in `cost_matrix` to tracks in
+        `tracks` (see description above).
+    detection_indices : List[int]
+        List of detection indices that maps columns in `cost_matrix` to
+        detections in `detections` (see description above).
+
+    Returns
+    -------
+    (List[(int, int)], List[int], List[int])
+        Returns a tuple with the following three entries:
+        * A list of matched track and detection indices.
+        * A list of unmatched track indices.
+        * A list of unmatched detection indices.
+
+    """
+    if track_indices is None:
+        track_indices = np.arange(len(tracks))
+    if detection_indices is None:
+        detection_indices = np.arange(len(detections))
+
+    if len(detection_indices) == 0 or len(track_indices) == 0:
+        return [], track_indices, detection_indices  # Nothing to match.
+
+    cost_matrix = distance_metric(
+        tracks, detections, track_indices, detection_indices)
+    cost_matrix[cost_matrix > max_distance] = max_distance + 1e-5
+
+    row_indices, col_indices = linear_assignment(cost_matrix)
+
+    matches, unmatched_tracks, unmatched_detections = [], [], []
+    for col, detection_idx in enumerate(detection_indices):
+        if col not in col_indices:
+            unmatched_detections.append(detection_idx)
+    for row, track_idx in enumerate(track_indices):
+        if row not in row_indices:
+            unmatched_tracks.append(track_idx)
+    for row, col in zip(row_indices, col_indices):
+        track_idx = track_indices[row]
+        detection_idx = detection_indices[col]
+        if cost_matrix[row, col] > max_distance:
+            unmatched_tracks.append(track_idx)
+            unmatched_detections.append(detection_idx)
+        else:
+            matches.append((track_idx, detection_idx))
+    return matches, unmatched_tracks, unmatched_detections
+
+
+def matching_cascade(
+        distance_metric, max_distance, cascade_depth, tracks, detections,
+        track_indices=None, detection_indices=None):
+    """Run matching cascade.
+
+    Parameters
+    ----------
+    distance_metric : Callable[List[Track], List[Detection], List[int], List[int]) -> ndarray
+        The distance metric is given a list of tracks and detections as well as
+        a list of N track indices and M detection indices. The metric should
+        return the NxM dimensional cost matrix, where element (i, j) is the
+        association cost between the i-th track in the given track indices and
+        the j-th detection in the given detection indices.
+    max_distance : float
+        Gating threshold. Associations with cost larger than this value are
+        disregarded.
+    cascade_depth: int
+        The cascade depth, should be se to the maximum track age.
+    tracks : List[track.Track]
+        A list of predicted tracks at the current time step.
+    detections : List[detection.Detection]
+        A list of detections at the current time step.
+    track_indices : Optional[List[int]]
+        List of track indices that maps rows in `cost_matrix` to tracks in
+        `tracks` (see description above). Defaults to all tracks.
+    detection_indices : Optional[List[int]]
+        List of detection indices that maps columns in `cost_matrix` to
+        detections in `detections` (see description above). Defaults to all
+        detections.
+
+    Returns
+    -------
+    (List[(int, int)], List[int], List[int])
+        Returns a tuple with the following three entries:
+        * A list of matched track and detection indices.
+        * A list of unmatched track indices.
+        * A list of unmatched detection indices.
+
+    """
+    if track_indices is None:
+        track_indices = list(range(len(tracks)))
+    if detection_indices is None:
+        detection_indices = list(range(len(detections)))
+
+    unmatched_detections = detection_indices
+    matches = []
+    for level in range(cascade_depth):
+        if len(unmatched_detections) == 0:  # No detections left
+            break
+
+        track_indices_l = [
+            k for k in track_indices
+            if tracks[k].time_since_update == 1 + level
+        ]
+        if len(track_indices_l) == 0:  # Nothing to match at this level
+            continue
+
+        matches_l, _, unmatched_detections = \
+            min_cost_matching(
+                distance_metric, max_distance, tracks, detections,
+                track_indices_l, unmatched_detections)
+        matches += matches_l
+    unmatched_tracks = list(set(track_indices) - set(k for k, _ in matches))
+    return matches, unmatched_tracks, unmatched_detections
+
+
+def gate_cost_matrix(
+        kf, cost_matrix, tracks, detections, track_indices, detection_indices,
+        gated_cost=INFTY_COST, only_position=False):
+    """Invalidate infeasible entries in cost matrix based on the state
+    distributions obtained by Kalman filtering.
+
+    Parameters
+    ----------
+    kf : The Kalman filter.
+    cost_matrix : ndarray
+        The NxM dimensional cost matrix, where N is the number of track indices
+        and M is the number of detection indices, such that entry (i, j) is the
+        association cost between `tracks[track_indices[i]]` and
+        `detections[detection_indices[j]]`.
+    tracks : List[track.Track]
+        A list of predicted tracks at the current time step.
+    detections : List[detection.Detection]
+        A list of detections at the current time step.
+    track_indices : List[int]
+        List of track indices that maps rows in `cost_matrix` to tracks in
+        `tracks` (see description above).
+    detection_indices : List[int]
+        List of detection indices that maps columns in `cost_matrix` to
+        detections in `detections` (see description above).
+    gated_cost : Optional[float]
+        Entries in the cost matrix corresponding to infeasible associations are
+        set this value. Defaults to a very large value.
+    only_position : Optional[bool]
+        If True, only the x, y position of the state distribution is considered
+        during gating. Defaults to False.
+
+    Returns
+    -------
+    ndarray
+        Returns the modified cost matrix.
+
+    """
+    gating_dim = 2 if only_position else 4
+    gating_threshold = kalman_filter.chi2inv95[gating_dim]
+    measurements = np.asarray(
+        [detections[i].to_xyah() for i in detection_indices])
+    for row, track_idx in enumerate(track_indices):
+        track = tracks[track_idx]
+        gating_distance = kf.gating_distance(
+            track.mean, track.covariance, measurements, only_position)
+        cost_matrix[row, gating_distance > gating_threshold] = gated_cost
+    return cost_matrix

deep_sort_torch/deep_sort/sort/nn_matching.py

@@ -0,0 +1,177 @@
+# vim: expandtab:ts=4:sw=4
+import numpy as np
+
+
+def _pdist(a, b):
+    """Compute pair-wise squared distance between points in `a` and `b`.
+
+    Parameters
+    ----------
+    a : array_like
+        An NxM matrix of N samples of dimensionality M.
+    b : array_like
+        An LxM matrix of L samples of dimensionality M.
+
+    Returns
+    -------
+    ndarray
+        Returns a matrix of size len(a), len(b) such that eleement (i, j)
+        contains the squared distance between `a[i]` and `b[j]`.
+
+    """
+    a, b = np.asarray(a), np.asarray(b)
+    if len(a) == 0 or len(b) == 0:
+        return np.zeros((len(a), len(b)))
+    a2, b2 = np.square(a).sum(axis=1), np.square(b).sum(axis=1)
+    r2 = -2. * np.dot(a, b.T) + a2[:, None] + b2[None, :]
+    r2 = np.clip(r2, 0., float(np.inf))
+    return r2
+
+
+def _cosine_distance(a, b, data_is_normalized=False):
+    """Compute pair-wise cosine distance between points in `a` and `b`.
+
+    Parameters
+    ----------
+    a : array_like
+        An NxM matrix of N samples of dimensionality M.
+    b : array_like
+        An LxM matrix of L samples of dimensionality M.
+    data_is_normalized : Optional[bool]
+        If True, assumes rows in a and b are unit length vectors.
+        Otherwise, a and b are explicitly normalized to lenght 1.
+
+    Returns
+    -------
+    ndarray
+        Returns a matrix of size len(a), len(b) such that eleement (i, j)
+        contains the squared distance between `a[i]` and `b[j]`.
+
+    """
+    if not data_is_normalized:
+        a = np.asarray(a) / np.linalg.norm(a, axis=1, keepdims=True)
+        b = np.asarray(b) / np.linalg.norm(b, axis=1, keepdims=True)
+    return 1. - np.dot(a, b.T)
+
+
+def _nn_euclidean_distance(x, y):
+    """ Helper function for nearest neighbor distance metric (Euclidean).
+
+    Parameters
+    ----------
+    x : ndarray
+        A matrix of N row-vectors (sample points).
+    y : ndarray
+        A matrix of M row-vectors (query points).
+
+    Returns
+    -------
+    ndarray
+        A vector of length M that contains for each entry in `y` the
+        smallest Euclidean distance to a sample in `x`.
+
+    """
+    distances = _pdist(x, y)
+    return np.maximum(0.0, distances.min(axis=0))
+
+
+def _nn_cosine_distance(x, y):
+    """ Helper function for nearest neighbor distance metric (cosine).
+
+    Parameters
+    ----------
+    x : ndarray
+        A matrix of N row-vectors (sample points).
+    y : ndarray
+        A matrix of M row-vectors (query points).
+
+    Returns
+    -------
+    ndarray
+        A vector of length M that contains for each entry in `y` the
+        smallest cosine distance to a sample in `x`.
+
+    """
+    distances = _cosine_distance(x, y)
+    return distances.min(axis=0)
+
+
+class NearestNeighborDistanceMetric(object):
+    """
+    A nearest neighbor distance metric that, for each target, returns
+    the closest distance to any sample that has been observed so far.
+
+    Parameters
+    ----------
+    metric : str
+        Either "euclidean" or "cosine".
+    matching_threshold: float
+        The matching threshold. Samples with larger distance are considered an
+        invalid match.
+    budget : Optional[int]
+        If not None, fix samples per class to at most this number. Removes
+        the oldest samples when the budget is reached.
+
+    Attributes
+    ----------
+    samples : Dict[int -> List[ndarray]]
+        A dictionary that maps from target identities to the list of samples
+        that have been observed so far.
+
+    """
+
+    def __init__(self, metric, matching_threshold, budget=None):
+
+
+        if metric == "euclidean":
+            self._metric = _nn_euclidean_distance
+        elif metric == "cosine":
+            self._metric = _nn_cosine_distance
+        else:
+            raise ValueError(
+                "Invalid metric; must be either 'euclidean' or 'cosine'")
+        self.matching_threshold = matching_threshold
+        self.budget = budget
+        self.samples = {}
+
+    def partial_fit(self, features, targets, active_targets):
+        """Update the distance metric with new data.
+
+        Parameters
+        ----------
+        features : ndarray
+            An NxM matrix of N features of dimensionality M.
+        targets : ndarray
+            An integer array of associated target identities.
+        active_targets : List[int]
+            A list of targets that are currently present in the scene.
+
+        """
+        for feature, target in zip(features, targets):
+            self.samples.setdefault(target, []).append(feature)
+            if self.budget is not None:
+                self.samples[target] = self.samples[target][-self.budget:]
+        self.samples = {k: self.samples[k] for k in active_targets}
+
+    def distance(self, features, targets):
+        """Compute distance between features and targets.
+
+        Parameters
+        ----------
+        features : ndarray
+            An NxM matrix of N features of dimensionality M.
+        targets : List[int]
+            A list of targets to match the given `features` against.
+
+        Returns
+        -------
+        ndarray
+            Returns a cost matrix of shape len(targets), len(features), where
+            element (i, j) contains the closest squared distance between
+            `targets[i]` and `features[j]`.
+
+        """
+        cost_matrix = np.zeros((len(targets), len(features)))
+        for i, target in enumerate(targets):
+            cost_matrix[i, :] = self._metric(self.samples[target], features)
+        return cost_matrix

deep_sort_torch/deep_sort/sort/preprocessing.py

@@ -0,0 +1,73 @@
+# vim: expandtab:ts=4:sw=4
+import numpy as np
+import cv2
+
+
+def non_max_suppression(boxes, max_bbox_overlap, scores=None):
+    """Suppress overlapping detections.
+
+    Original code from [1]_ has been adapted to include confidence score.
+
+    .. [1] http://www.pyimagesearch.com/2015/02/16/
+           faster-non-maximum-suppression-python/
+
+    Examples
+    --------
+
+        >>> boxes = [d.roi for d in detections]
+        >>> scores = [d.confidence for d in detections]
+        >>> indices = non_max_suppression(boxes, max_bbox_overlap, scores)
+        >>> detections = [detections[i] for i in indices]
+
+    Parameters
+    ----------
+    boxes : ndarray
+        Array of ROIs (x, y, width, height).
+    max_bbox_overlap : float
+        ROIs that overlap more than this values are suppressed.
+    scores : Optional[array_like]
+        Detector confidence score.
+
+    Returns
+    -------
+    List[int]
+        Returns indices of detections that have survived non-maxima suppression.
+
+    """
+    if len(boxes) == 0:
+        return []
+
+    boxes = boxes.astype(np.float)
+    pick = []
+
+    x1 = boxes[:, 0]
+    y1 = boxes[:, 1]
+    x2 = boxes[:, 2] + boxes[:, 0]
+    y2 = boxes[:, 3] + boxes[:, 1]
+
+    area = (x2 - x1 + 1) * (y2 - y1 + 1)
+    if scores is not None:
+        idxs = np.argsort(scores)
+    else:
+        idxs = np.argsort(y2)
+
+    while len(idxs) > 0:
+        last = len(idxs) - 1
+        i = idxs[last]
+        pick.append(i)
+
+        xx1 = np.maximum(x1[i], x1[idxs[:last]])
+        yy1 = np.maximum(y1[i], y1[idxs[:last]])
+        xx2 = np.minimum(x2[i], x2[idxs[:last]])
+        yy2 = np.minimum(y2[i], y2[idxs[:last]])
+
+        w = np.maximum(0, xx2 - xx1 + 1)
+        h = np.maximum(0, yy2 - yy1 + 1)
+
+        overlap = (w * h) / area[idxs[:last]]
+
+        idxs = np.delete(
+            idxs, np.concatenate(
+                ([last], np.where(overlap > max_bbox_overlap)[0])))
+
+    return pick

deep_sort_torch/deep_sort/sort/track.py

@@ -0,0 +1,166 @@
+# vim: expandtab:ts=4:sw=4
+
+
+class TrackState:
+    """
+    Enumeration type for the single target track state. Newly created tracks are
+    classified as `tentative` until enough evidence has been collected. Then,
+    the track state is changed to `confirmed`. Tracks that are no longer alive
+    are classified as `deleted` to mark them for removal from the set of active
+    tracks.
+
+    """
+
+    Tentative = 1
+    Confirmed = 2
+    Deleted = 3
+
+
+class Track:
+    """
+    A single target track with state space `(x, y, a, h)` and associated
+    velocities, where `(x, y)` is the center of the bounding box, `a` is the
+    aspect ratio and `h` is the height.
+
+    Parameters
+    ----------
+    mean : ndarray
+        Mean vector of the initial state distribution.
+    covariance : ndarray
+        Covariance matrix of the initial state distribution.
+    track_id : int
+        A unique track identifier.
+    n_init : int
+        Number of consecutive detections before the track is confirmed. The
+        track state is set to `Deleted` if a miss occurs within the first
+        `n_init` frames.
+    max_age : int
+        The maximum number of consecutive misses before the track state is
+        set to `Deleted`.
+    feature : Optional[ndarray]
+        Feature vector of the detection this track originates from. If not None,
+        this feature is added to the `features` cache.
+
+    Attributes
+    ----------
+    mean : ndarray
+        Mean vector of the initial state distribution.
+    covariance : ndarray
+        Covariance matrix of the initial state distribution.
+    track_id : int
+        A unique track identifier.
+    hits : int
+        Total number of measurement updates.
+    age : int
+        Total number of frames since first occurance.
+    time_since_update : int
+        Total number of frames since last measurement update.
+    state : TrackState
+        The current track state.
+    features : List[ndarray]
+        A cache of features. On each measurement update, the associated feature
+        vector is added to this list.
+
+    """
+
+    def __init__(self, mean, covariance, track_id, n_init, max_age,
+                 feature=None):
+        self.mean = mean
+        self.covariance = covariance
+        self.track_id = track_id
+        self.hits = 1
+        self.age = 1
+        self.time_since_update = 0
+
+        self.state = TrackState.Tentative
+        self.features = []
+        if feature is not None:
+            self.features.append(feature)
+
+        self._n_init = n_init
+        self._max_age = max_age
+
+    def to_tlwh(self):
+        """Get current position in bounding box format `(top left x, top left y,
+        width, height)`.
+
+        Returns
+        -------
+        ndarray
+            The bounding box.
+
+        """
+        ret = self.mean[:4].copy()
+        ret[2] *= ret[3]
+        ret[:2] -= ret[2:] / 2
+        return ret
+
+    def to_tlbr(self):
+        """Get current position in bounding box format `(min x, miny, max x,
+        max y)`.
+
+        Returns
+        -------
+        ndarray
+            The bounding box.
+
+        """
+        ret = self.to_tlwh()
+        ret[2:] = ret[:2] + ret[2:]
+        return ret
+
+    def predict(self, kf):
+        """Propagate the state distribution to the current time step using a
+        Kalman filter prediction step.
+
+        Parameters
+        ----------
+        kf : kalman_filter.KalmanFilter
+            The Kalman filter.
+
+        """
+        self.mean, self.covariance = kf.predict(self.mean, self.covariance)
+        self.age += 1
+        self.time_since_update += 1
+
+    def update(self, kf, detection):
+        """Perform Kalman filter measurement update step and update the feature
+        cache.
+
+        Parameters
+        ----------
+        kf : kalman_filter.KalmanFilter
+            The Kalman filter.
+        detection : Detection
+            The associated detection.
+
+        """
+        self.mean, self.covariance = kf.update(
+            self.mean, self.covariance, detection.to_xyah())
+        self.features.append(detection.feature)
+
+        self.hits += 1
+        self.time_since_update = 0
+        if self.state == TrackState.Tentative and self.hits >= self._n_init:
+            self.state = TrackState.Confirmed
+
+    def mark_missed(self):
+        """Mark this track as missed (no association at the current time step).
+        """
+        if self.state == TrackState.Tentative:
+            self.state = TrackState.Deleted
+        elif self.time_since_update > self._max_age:
+            self.state = TrackState.Deleted
+
+    def is_tentative(self):
+        """Returns True if this track is tentative (unconfirmed).
+        """
+        return self.state == TrackState.Tentative
+
+    def is_confirmed(self):
+        """Returns True if this track is confirmed."""
+        return self.state == TrackState.Confirmed
+
+    def is_deleted(self):
+        """Returns True if this track is dead and should be deleted."""
+        return self.state == TrackState.Deleted

deep_sort_torch/deep_sort/sort/tracker.py

@@ -0,0 +1,138 @@
+# vim: expandtab:ts=4:sw=4
+from __future__ import absolute_import
+import numpy as np
+from . import kalman_filter
+from . import linear_assignment
+from . import iou_matching
+from .track import Track
+
+
+class Tracker:
+    """
+    This is the multi-target tracker.
+
+    Parameters
+    ----------
+    metric : nn_matching.NearestNeighborDistanceMetric
+        A distance metric for measurement-to-track association.
+    max_age : int
+        Maximum number of missed misses before a track is deleted.
+    n_init : int
+        Number of consecutive detections before the track is confirmed. The
+        track state is set to `Deleted` if a miss occurs within the first
+        `n_init` frames.
+
+    Attributes
+    ----------
+    metric : nn_matching.NearestNeighborDistanceMetric
+        The distance metric used for measurement to track association.
+    max_age : int
+        Maximum number of missed misses before a track is deleted.
+    n_init : int
+        Number of frames that a track remains in initialization phase.
+    kf : kalman_filter.KalmanFilter
+        A Kalman filter to filter target trajectories in image space.
+    tracks : List[Track]
+        The list of active tracks at the current time step.
+
+    """
+
+    def __init__(self, metric, max_iou_distance=0.7, max_age=70, n_init=3):
+        self.metric = metric
+        self.max_iou_distance = max_iou_distance
+        self.max_age = max_age
+        self.n_init = n_init
+
+        self.kf = kalman_filter.KalmanFilter()
+        self.tracks = []
+        self._next_id = 1
+
+    def predict(self):
+        """Propagate track state distributions one time step forward.
+
+        This function should be called once every time step, before `update`.
+        """
+        for track in self.tracks:
+            track.predict(self.kf)
+
+    def update(self, detections):
+        """Perform measurement update and track management.
+
+        Parameters
+        ----------
+        detections : List[deep_sort.detection.Detection]
+            A list of detections at the current time step.
+
+        """
+        # Run matching cascade.
+        matches, unmatched_tracks, unmatched_detections = \
+            self._match(detections)
+
+        # Update track set.
+        for track_idx, detection_idx in matches:
+            self.tracks[track_idx].update(
+                self.kf, detections[detection_idx])
+        for track_idx in unmatched_tracks:
+            self.tracks[track_idx].mark_missed()
+        for detection_idx in unmatched_detections:
+            self._initiate_track(detections[detection_idx])
+        self.tracks = [t for t in self.tracks if not t.is_deleted()]
+
+        # Update distance metric.
+        active_targets = [t.track_id for t in self.tracks if t.is_confirmed()]
+        features, targets = [], []
+        for track in self.tracks:
+            if not track.is_confirmed():
+                continue
+            features += track.features
+            targets += [track.track_id for _ in track.features]
+            track.features = []
+        self.metric.partial_fit(
+            np.asarray(features), np.asarray(targets), active_targets)
+
+    def _match(self, detections):
+
+        def gated_metric(tracks, dets, track_indices, detection_indices):
+            features = np.array([dets[i].feature for i in detection_indices])
+            targets = np.array([tracks[i].track_id for i in track_indices])
+            cost_matrix = self.metric.distance(features, targets)
+            cost_matrix = linear_assignment.gate_cost_matrix(
+                self.kf, cost_matrix, tracks, dets, track_indices,
+                detection_indices)
+
+            return cost_matrix
+
+        # Split track set into confirmed and unconfirmed tracks.
+        confirmed_tracks = [
+            i for i, t in enumerate(self.tracks) if t.is_confirmed()]
+        unconfirmed_tracks = [
+            i for i, t in enumerate(self.tracks) if not t.is_confirmed()]
+
+        # Associate confirmed tracks using appearance features.
+        matches_a, unmatched_tracks_a, unmatched_detections = \
+            linear_assignment.matching_cascade(
+                gated_metric, self.metric.matching_threshold, self.max_age,
+                self.tracks, detections, confirmed_tracks)
+
+        # Associate remaining tracks together with unconfirmed tracks using IOU.
+        iou_track_candidates = unconfirmed_tracks + [
+            k for k in unmatched_tracks_a if
+            self.tracks[k].time_since_update == 1]
+        unmatched_tracks_a = [
+            k for k in unmatched_tracks_a if
+            self.tracks[k].time_since_update != 1]
+        matches_b, unmatched_tracks_b, unmatched_detections = \
+            linear_assignment.min_cost_matching(
+                iou_matching.iou_cost, self.max_iou_distance, self.tracks,
+                detections, iou_track_candidates, unmatched_detections)
+
+        matches = matches_a + matches_b
+        unmatched_tracks = list(set(unmatched_tracks_a + unmatched_tracks_b))
+        return matches, unmatched_tracks, unmatched_detections
+
+    def _initiate_track(self, detection):
+        mean, covariance = self.kf.initiate(detection.to_xyah())
+        self.tracks.append(Track(
+            mean, covariance, self._next_id, self.n_init, self.max_age,
+            detection.feature))
+        self._next_id += 1

deep_sort_torch/deepsort.py

@@ -0,0 +1,172 @@
+import os
+import cv2
+import time
+import argparse
+import torch
+import warnings
+import numpy as np
+import sys
+
+sys.path.append(os.path.join(os.path.dirname(__file__), 'thirdparty/fast-reid'))
+
+
+from detector import build_detector
+from deep_sort import build_tracker
+from utils.draw import draw_boxes
+from utils.parser import get_config
+from utils.log import get_logger
+from utils.io import write_results
+
+
+
+class VideoTracker(object):
+    def __init__(self, cfg, args, video_path):
+        self.cfg = cfg
+        self.args = args
+        self.video_path = video_path
+        self.logger = get_logger("root")
+
+        use_cuda = args.use_cuda and torch.cuda.is_available()
+        if not use_cuda:
+            warnings.warn("Running in cpu mode which maybe very slow!", UserWarning)
+
+        if args.display:
+            cv2.namedWindow("test", cv2.WINDOW_NORMAL)
+            cv2.resizeWindow("test", args.display_width, args.display_height)
+
+        if args.cam != -1:
+            print("Using webcam " + str(args.cam))
+            self.vdo = cv2.VideoCapture(args.cam)
+        else:
+            self.vdo = cv2.VideoCapture()
+        self.detector = build_detector(cfg, use_cuda=use_cuda)
+        self.deepsort = build_tracker(cfg, use_cuda=use_cuda)
+        self.class_names = self.detector.class_names
+
+    def __enter__(self):
+        if self.args.cam != -1:
+            ret, frame = self.vdo.read()
+            assert ret, "Error: Camera error"
+            self.im_width = frame.shape[0]
+            self.im_height = frame.shape[1]
+
+        else:
+            assert os.path.isfile(self.video_path), "Path error"
+            self.vdo.open(self.video_path)
+            self.im_width = int(self.vdo.get(cv2.CAP_PROP_FRAME_WIDTH))
+            self.im_height = int(self.vdo.get(cv2.CAP_PROP_FRAME_HEIGHT))
+            assert self.vdo.isOpened()
+
+        if self.args.save_path:
+            os.makedirs(self.args.save_path, exist_ok=True)
+
+            # path of saved video and results
+            self.save_video_path = os.path.join(self.args.save_path, "results.avi")
+            self.save_results_path = os.path.join(self.args.save_path, "results.txt")
+
+            # create video writer
+            fourcc = cv2.VideoWriter_fourcc(*'MJPG')
+            self.writer = cv2.VideoWriter(self.save_video_path, fourcc, 20, (self.im_width, self.im_height))
+
+            # logging
+            self.logger.info("Save results to {}".format(self.args.save_path))
+
+        return self
+
+    def __exit__(self, exc_type, exc_value, exc_traceback):
+        if exc_type:
+            print(exc_type, exc_value, exc_traceback)
+
+    def run(self):
+        results = []
+        idx_frame = 0
+        while self.vdo.grab():
+            idx_frame += 1
+            if idx_frame % self.args.frame_interval:
+                continue
+
+            start = time.time()
+            _, ori_im = self.vdo.retrieve()
+            im = cv2.cvtColor(ori_im, cv2.COLOR_BGR2RGB)
+
+            # do detection
+            bbox_xywh, cls_conf, cls_ids = self.detector(im)
+
+            # select person class
+            mask = cls_ids == 0
+
+            bbox_xywh = bbox_xywh[mask]
+            # bbox dilation just in case bbox too small, delete this line if using a better pedestrian detector
+            bbox_xywh[:, 3:] *= 1.2
+            cls_conf = cls_conf[mask]
+
+            # do tracking
+            outputs = self.deepsort.update(bbox_xywh, cls_conf, im)
+
+            # draw boxes for visualization
+            if len(outputs) > 0:
+                bbox_tlwh = []
+                bbox_xyxy = outputs[:, :4]
+                identities = outputs[:, -1]
+                ori_im = draw_boxes(ori_im, bbox_xyxy, identities)
+
+                for bb_xyxy in bbox_xyxy:
+                    bbox_tlwh.append(self.deepsort._xyxy_to_tlwh(bb_xyxy))
+
+                results.append((idx_frame - 1, bbox_tlwh, identities))
+
+            end = time.time()
+
+            if self.args.display:
+                cv2.imshow("test", ori_im)
+                cv2.waitKey(1)
+
+            if self.args.save_path:
+                self.writer.write(ori_im)
+
+            # save results
+            write_results(self.save_results_path, results, 'mot')
+
+            # logging
+            self.logger.info("time: {:.03f}s, fps: {:.03f}, detection numbers: {}, tracking numbers: {}" \
+                             .format(end - start, 1 / (end - start), bbox_xywh.shape[0], len(outputs)))
+
+
+def parse_args():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("VIDEO_PATH", type=str)
+    parser.add_argument("--config_mmdetection", type=str, default="./configs/mmdet.yaml")
+    parser.add_argument("--config_detection", type=str, default="./configs/yolov3.yaml")
+    parser.add_argument("--config_deepsort", type=str, default="./configs/deep_sort.yaml")
+    parser.add_argument("--config_fastreid", type=str, default="./configs/fastreid.yaml")
+    parser.add_argument("--fastreid", action="store_true")
+    parser.add_argument("--mmdet", action="store_true")
+    # parser.add_argument("--ignore_display", dest="display", action="store_false", default=True)
+    parser.add_argument("--display", action="store_true")
+    parser.add_argument("--frame_interval", type=int, default=1)
+    parser.add_argument("--display_width", type=int, default=800)
+    parser.add_argument("--display_height", type=int, default=600)
+    parser.add_argument("--save_path", type=str, default="./output/")
+    parser.add_argument("--cpu", dest="use_cuda", action="store_false", default=True)
+    parser.add_argument("--camera", action="store", dest="cam", type=int, default="-1")
+    return parser.parse_args()
+
+
+if __name__ == "__main__":
+    args = parse_args()
+    cfg = get_config()
+    if args.mmdet:
+        cfg.merge_from_file(args.config_mmdetection)
+        cfg.USE_MMDET = True
+    else:
+        cfg.merge_from_file(args.config_detection)
+        cfg.USE_MMDET = False
+    cfg.merge_from_file(args.config_deepsort)
+    if args.fastreid:
+        cfg.merge_from_file(args.config_fastreid)
+        cfg.USE_FASTREID = True
+    else:
+        cfg.USE_FASTREID = False
+
+    with VideoTracker(cfg, args, video_path=args.VIDEO_PATH) as vdo_trk:
+        vdo_trk.run()

deep_sort_torch/detector/MMDet/__init__.py

@@ -0,0 +1,2 @@
+from .detector import MMDet
+__all__ = ['MMDet']

deep_sort_torch/detector/MMDet/detector.py

@@ -0,0 +1,55 @@
+import logging
+import numpy as np
+import torch
+
+from mmdet.apis import init_detector, inference_detector
+from .mmdet_utils import xyxy_to_xywh
+
+class MMDet(object):
+    def __init__(self, cfg_file, checkpoint_file, score_thresh=0.7,
+                is_xywh=False, use_cuda=True):
+        # net definition
+        self.device = "cuda" if use_cuda else "cpu"
+        self.net = init_detector(cfg_file, checkpoint_file, device=self.device)
+        logger = logging.getLogger("root.detector")
+        logger.info('Loading weights from %s... Done!' % (checkpoint_file))
+
+        #constants
+        self.score_thresh = score_thresh
+        self.use_cuda = use_cuda
+        self.is_xywh = is_xywh
+        self.class_names = self.net.CLASSES
+        self.num_classes = len(self.class_names)
+
+    def __call__(self, ori_img):
+        # forward
+        bbox_result = inference_detector(self.net, ori_img)
+        bboxes = np.vstack(bbox_result)
+
+        if len(bboxes) == 0:
+            bbox = np.array([]).reshape([0, 4])
+            cls_conf = np.array([])
+            cls_ids = np.array([])
+            return bbox, cls_conf, cls_ids
+
+        bbox = bboxes[:, :4]
+        cls_conf = bboxes[:, 4]
+        cls_ids = [
+            np.full(bbox.shape[0], i, dtype=np.int32)
+            for i, bbox in enumerate(bbox_result)
+        ]
+        cls_ids = np.concatenate(cls_ids)
+
+        selected_idx = cls_conf > self.score_thresh
+        bbox = bbox[selected_idx, :]
+        cls_conf = cls_conf[selected_idx]
+        cls_ids = cls_ids[selected_idx]
+
+        if self.is_xywh:
+            bbox = xyxy_to_xywh(bbox)
+
+        return bbox, cls_conf, cls_ids
+
+
+            
+

deep_sort_torch/detector/MMDet/mmdet_utils.py

@@ -0,0 +1,15 @@
+import torch
+import numpy as np
+
+def xyxy_to_xywh(boxes_xyxy):
+    if isinstance(boxes_xyxy, torch.Tensor):
+        boxes_xywh = boxes_xyxy.clone()
+    elif isinstance(boxes_xyxy, np.ndarray):
+        boxes_xywh = boxes_xyxy.copy()
+
+    boxes_xywh[:, 0] = (boxes_xyxy[:, 0] + boxes_xyxy[:, 2]) / 2.
+    boxes_xywh[:, 1] = (boxes_xyxy[:, 1] + boxes_xyxy[:, 3]) / 2.
+    boxes_xywh[:, 2] = boxes_xyxy[:, 2] - boxes_xyxy[:, 0]
+    boxes_xywh[:, 3] = boxes_xyxy[:, 3] - boxes_xyxy[:, 1]
+
+    return boxes_xywh

deep_sort_torch/detector/YOLOv3/README.md

@@ -0,0 +1,11 @@
+# YOLOv3 for detection
+
+This is an implemention of YOLOv3 with only the forward part.
+
+If you want to train YOLOv3 on your custom dataset, please search `YOLOv3` on github.
+
+## Quick forward
+```bash
+cd YOLOv3
+python 
+```

deep_sort_torch/detector/YOLOv3/__init__.py

@@ -0,0 +1,9 @@
+import sys
+sys.path.append("detector/YOLOv3")
+
+
+from .detector import YOLOv3
+__all__ = ['YOLOv3']
+
+
+

deep_sort_torch/detector/YOLOv3/cfg.py

@@ -0,0 +1,248 @@
+import torch
+from .yolo_utils import convert2cpu
+
+
+def parse_cfg(cfgfile):
+    blocks = []
+    fp = open(cfgfile)
+    block = None
+    line = fp.readline()
+    while line != '':
+        line = line.rstrip()
+        if line == '' or line[0] == '#':
+            line = fp.readline()
+            continue
+        elif line[0] == '[':
+            if block:
+                blocks.append(block)
+            block = dict()
+            block['type'] = line.lstrip('[').rstrip(']')
+            # set default value
+            if block['type'] == 'convolutional':
+                block['batch_normalize'] = 0
+        else:
+            key, value = line.split('=')
+            key = key.strip()
+            if key == 'type':
+                key = '_type'
+            value = value.strip()
+            block[key] = value
+        line = fp.readline()
+
+    if block:
+        blocks.append(block)
+    fp.close()
+    return blocks
+
+
+def print_cfg(blocks):
+    print('layer     filters    size              input                output');
+    prev_width = 416
+    prev_height = 416
+    prev_filters = 3
+    out_filters = []
+    out_widths = []
+    out_heights = []
+    ind = -2
+    for block in blocks:
+        ind += 1
+        if block['type'] == 'net':
+            prev_width = int(block['width'])
+            prev_height = int(block['height'])
+            continue
+        elif block['type'] == 'convolutional':
+            filters = int(block['filters'])
+            kernel_size = int(block['size'])
+            stride = int(block['stride'])
+            is_pad = int(block['pad'])
+            pad = (kernel_size - 1) // 2 if is_pad else 0
+            width = (prev_width + 2 * pad - kernel_size) // stride + 1
+            height = (prev_height + 2 * pad - kernel_size) // stride + 1
+            print('%5d %-6s %4d  %d x %d / %d   %3d x %3d x%4d   ->   %3d x %3d x%4d' % (
+            ind, 'conv', filters, kernel_size, kernel_size, stride, prev_width, prev_height, prev_filters, width,
+            height, filters))
+            prev_width = width
+            prev_height = height
+            prev_filters = filters
+            out_widths.append(prev_width)
+            out_heights.append(prev_height)
+            out_filters.append(prev_filters)
+        elif block['type'] == 'maxpool':
+            pool_size = int(block['size'])
+            stride = int(block['stride'])
+            width = prev_width // stride
+            height = prev_height // stride
+            print('%5d %-6s       %d x %d / %d   %3d x %3d x%4d   ->   %3d x %3d x%4d' % (
+            ind, 'max', pool_size, pool_size, stride, prev_width, prev_height, prev_filters, width, height, filters))
+            prev_width = width
+            prev_height = height
+            prev_filters = filters
+            out_widths.append(prev_width)
+            out_heights.append(prev_height)
+            out_filters.append(prev_filters)
+        elif block['type'] == 'avgpool':
+            width = 1
+            height = 1
+            print('%5d %-6s                   %3d x %3d x%4d   ->  %3d' % (
+            ind, 'avg', prev_width, prev_height, prev_filters, prev_filters))
+            prev_width = width
+            prev_height = height
+            prev_filters = filters
+            out_widths.append(prev_width)
+            out_heights.append(prev_height)
+            out_filters.append(prev_filters)
+        elif block['type'] == 'softmax':
+            print('%5d %-6s                                    ->  %3d' % (ind, 'softmax', prev_filters))
+            out_widths.append(prev_width)
+            out_heights.append(prev_height)
+            out_filters.append(prev_filters)
+        elif block['type'] == 'cost':
+            print('%5d %-6s                                     ->  %3d' % (ind, 'cost', prev_filters))
+            out_widths.append(prev_width)
+            out_heights.append(prev_height)
+            out_filters.append(prev_filters)
+        elif block['type'] == 'reorg':
+            stride = int(block['stride'])
+            filters = stride * stride * prev_filters
+            width = prev_width // stride
+            height = prev_height // stride
+            print('%5d %-6s             / %d   %3d x %3d x%4d   ->   %3d x %3d x%4d' % (
+            ind, 'reorg', stride, prev_width, prev_height, prev_filters, width, height, filters))
+            prev_width = width
+            prev_height = height
+            prev_filters = filters
+            out_widths.append(prev_width)
+            out_heights.append(prev_height)
+            out_filters.append(prev_filters)
+        elif block['type'] == 'upsample':
+            stride = int(block['stride'])
+            filters = prev_filters
+            width = prev_width * stride
+            height = prev_height * stride
+            print('%5d %-6s           * %d   %3d x %3d x%4d   ->   %3d x %3d x%4d' % (
+            ind, 'upsample', stride, prev_width, prev_height, prev_filters, width, height, filters))
+            prev_width = width
+            prev_height = height
+            prev_filters = filters
+            out_widths.append(prev_width)
+            out_heights.append(prev_height)
+            out_filters.append(prev_filters)
+        elif block['type'] == 'route':
+            layers = block['layers'].split(',')
+            layers = [int(i) if int(i) > 0 else int(i) + ind for i in layers]
+            if len(layers) == 1:
+                print('%5d %-6s %d' % (ind, 'route', layers[0]))
+                prev_width = out_widths[layers[0]]
+                prev_height = out_heights[layers[0]]
+                prev_filters = out_filters[layers[0]]
+            elif len(layers) == 2:
+                print('%5d %-6s %d %d' % (ind, 'route', layers[0], layers[1]))
+                prev_width = out_widths[layers[0]]
+                prev_height = out_heights[layers[0]]
+                assert (prev_width == out_widths[layers[1]])
+                assert (prev_height == out_heights[layers[1]])
+                prev_filters = out_filters[layers[0]] + out_filters[layers[1]]
+            out_widths.append(prev_width)
+            out_heights.append(prev_height)
+            out_filters.append(prev_filters)
+        elif block['type'] in ['region', 'yolo']:
+            print('%5d %-6s' % (ind, 'detection'))
+            out_widths.append(prev_width)
+            out_heights.append(prev_height)
+            out_filters.append(prev_filters)
+        elif block['type'] == 'shortcut':
+            from_id = int(block['from'])
+            from_id = from_id if from_id > 0 else from_id + ind
+            print('%5d %-6s %d' % (ind, 'shortcut', from_id))
+            prev_width = out_widths[from_id]
+            prev_height = out_heights[from_id]
+            prev_filters = out_filters[from_id]
+            out_widths.append(prev_width)
+            out_heights.append(prev_height)
+            out_filters.append(prev_filters)
+        elif block['type'] == 'connected':
+            filters = int(block['output'])
+            print('%5d %-6s                            %d  ->  %3d' % (ind, 'connected', prev_filters, filters))
+            prev_filters = filters
+            out_widths.append(1)
+            out_heights.append(1)
+            out_filters.append(prev_filters)
+        else:
+            print('unknown type %s' % (block['type']))
+
+
+def load_conv(buf, start, conv_model):
+    num_w = conv_model.weight.numel()
+    num_b = conv_model.bias.numel()
+    # print("start: {}, num_w: {}, num_b: {}".format(start, num_w, num_b))
+    # by ysyun, use .view_as()
+    conv_model.bias.data.copy_(torch.from_numpy(buf[start:start + num_b]).view_as(conv_model.bias.data));
+    start = start + num_b
+    conv_model.weight.data.copy_(torch.from_numpy(buf[start:start + num_w]).view_as(conv_model.weight.data));
+    start = start + num_w
+    return start
+
+
+def save_conv(fp, conv_model):
+    if conv_model.bias.is_cuda:
+        convert2cpu(conv_model.bias.data).numpy().tofile(fp)
+        convert2cpu(conv_model.weight.data).numpy().tofile(fp)
+    else:
+        conv_model.bias.data.numpy().tofile(fp)
+        conv_model.weight.data.numpy().tofile(fp)
+
+
+def load_conv_bn(buf, start, conv_model, bn_model):
+    num_w = conv_model.weight.numel()
+    num_b = bn_model.bias.numel()
+    bn_model.bias.data.copy_(torch.from_numpy(buf[start:start + num_b]));
+    start = start + num_b
+    bn_model.weight.data.copy_(torch.from_numpy(buf[start:start + num_b]));
+    start = start + num_b
+    bn_model.running_mean.copy_(torch.from_numpy(buf[start:start + num_b]));
+    start = start + num_b
+    bn_model.running_var.copy_(torch.from_numpy(buf[start:start + num_b]));
+    start = start + num_b
+    # conv_model.weight.data.copy_(torch.from_numpy(buf[start:start+num_w])); start = start + num_w
+    conv_model.weight.data.copy_(torch.from_numpy(buf[start:start + num_w]).view_as(conv_model.weight.data));
+    start = start + num_w
+    return start
+
+
+def save_conv_bn(fp, conv_model, bn_model):
+    if bn_model.bias.is_cuda:
+        convert2cpu(bn_model.bias.data).numpy().tofile(fp)
+        convert2cpu(bn_model.weight.data).numpy().tofile(fp)
+        convert2cpu(bn_model.running_mean).numpy().tofile(fp)
+        convert2cpu(bn_model.running_var).numpy().tofile(fp)
+        convert2cpu(conv_model.weight.data).numpy().tofile(fp)
+    else:
+        bn_model.bias.data.numpy().tofile(fp)
+        bn_model.weight.data.numpy().tofile(fp)
+        bn_model.running_mean.numpy().tofile(fp)
+        bn_model.running_var.numpy().tofile(fp)
+        conv_model.weight.data.numpy().tofile(fp)
+
+
+def load_fc(buf, start, fc_model):
+    num_w = fc_model.weight.numel()
+    num_b = fc_model.bias.numel()
+    fc_model.bias.data.copy_(torch.from_numpy(buf[start:start + num_b]));
+    start = start + num_b
+    fc_model.weight.data.copy_(torch.from_numpy(buf[start:start + num_w]));
+    start = start + num_w
+    return start
+
+
+def save_fc(fp, fc_model):
+    fc_model.bias.data.numpy().tofile(fp)
+    fc_model.weight.data.numpy().tofile(fp)
+
+
+if __name__ == '__main__':
+    import sys
+
+    blocks = parse_cfg('cfg/yolo.cfg')
+    if len(sys.argv) == 2:
+        blocks = parse_cfg(sys.argv[1])
+    print_cfg(blocks)

deep_sort_torch/detector/YOLOv3/cfg/coco.data

@@ -0,0 +1,5 @@
+train  = coco_train.txt
+valid  = coco_test.txt
+names = data/coco.names
+backup = backup
+gpus  = 0,1,2,3

deep_sort_torch/detector/YOLOv3/cfg/coco.names

@@ -0,0 +1,80 @@
+person
+bicycle
+car
+motorbike
+aeroplane
+bus
+train
+truck
+boat
+traffic light
+fire hydrant
+stop sign
+parking meter
+bench
+bird
+cat
+dog
+horse
+sheep
+cow
+elephant
+bear
+zebra
+giraffe
+backpack
+umbrella
+handbag
+tie
+suitcase
+frisbee
+skis
+snowboard
+sports ball
+kite
+baseball bat
+baseball glove
+skateboard
+surfboard
+tennis racket
+bottle
+wine glass
+cup
+fork
+knife
+spoon
+bowl
+banana
+apple
+sandwich
+orange
+broccoli
+carrot
+hot dog
+pizza
+donut
+cake
+chair
+sofa
+pottedplant
+bed
+diningtable
+toilet
+tvmonitor
+laptop
+mouse
+remote
+keyboard
+cell phone
+microwave
+oven
+toaster
+sink
+refrigerator
+book
+clock
+vase
+scissors
+teddy bear
+hair drier
+toothbrush

deep_sort_torch/detector/YOLOv3/cfg/darknet19_448.cfg

@@ -0,0 +1,200 @@
+[net]
+batch=128
+subdivisions=4
+height=448
+width=448
+max_crop=512
+channels=3
+momentum=0.9
+decay=0.0005
+
+learning_rate=0.001
+policy=poly
+power=4
+max_batches=100000
+
+angle=7
+hue = .1
+saturation=.75
+exposure=.75
+aspect=.75
+
+[convolutional]
+batch_normalize=1
+filters=32
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+filters=1000
+size=1
+stride=1
+pad=1
+activation=linear
+
+[avgpool]
+
+[softmax]
+groups=1
+
+[cost]
+type=sse
+

deep_sort_torch/detector/YOLOv3/cfg/tiny-yolo-voc.cfg

@@ -0,0 +1,134 @@
+[net]
+batch=64
+subdivisions=8
+width=416
+height=416
+channels=3
+momentum=0.9
+decay=0.0005
+angle=0
+saturation = 1.5
+exposure = 1.5
+hue=.1
+
+learning_rate=0.001
+max_batches = 40200
+policy=steps
+steps=-1,100,20000,30000
+scales=.1,10,.1,.1
+
+[convolutional]
+batch_normalize=1
+filters=16
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=32
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=1
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+###########
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=125
+activation=linear
+
+[region]
+anchors = 1.08,1.19,  3.42,4.41,  6.63,11.38,  9.42,5.11,  16.62,10.52
+bias_match=1
+classes=20
+coords=4
+num=5
+softmax=1
+jitter=.2
+rescore=1
+
+object_scale=5
+noobject_scale=1
+class_scale=1
+coord_scale=1
+
+absolute=1
+thresh = .6
+random=1

deep_sort_torch/detector/YOLOv3/cfg/tiny-yolo.cfg

@@ -0,0 +1,140 @@
+[net]
+# Training
+# batch=64
+# subdivisions=2
+# Testing
+batch=1
+subdivisions=1
+width=416
+height=416
+channels=3
+momentum=0.9
+decay=0.0005
+angle=0
+saturation = 1.5
+exposure = 1.5
+hue=.1
+
+learning_rate=0.001
+burn_in=1000
+max_batches = 500200
+policy=steps
+steps=400000,450000
+scales=.1,.1
+
+[convolutional]
+batch_normalize=1
+filters=16
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=32
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=1
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+###########
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=512
+activation=leaky
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=425
+activation=linear
+
+[region]
+anchors =  0.57273, 0.677385, 1.87446, 2.06253, 3.33843, 5.47434, 7.88282, 3.52778, 9.77052, 9.16828
+bias_match=1
+classes=80
+coords=4
+num=5
+softmax=1
+jitter=.2
+rescore=0
+
+object_scale=5
+noobject_scale=1
+class_scale=1
+coord_scale=1
+
+absolute=1
+thresh = .6
+random=1
+

deep_sort_torch/detector/YOLOv3/cfg/voc.data

@@ -0,0 +1,5 @@
+train  = data/voc_train.txt
+valid  = data/2007_test.txt
+names = data/voc.names
+backup = backup
+gpus  = 3

deep_sort_torch/detector/YOLOv3/cfg/voc.names

@@ -0,0 +1,20 @@
+aeroplane
+bicycle
+bird
+boat
+bottle
+bus
+car
+cat
+chair
+cow
+diningtable
+dog
+horse
+motorbike
+person
+pottedplant
+sheep
+sofa
+train
+tvmonitor

deep_sort_torch/detector/YOLOv3/cfg/voc_gaotie.data

@@ -0,0 +1,5 @@
+train  = data/gaotie_trainval.txt
+valid  = data/gaotie_test.txt
+names = data/voc.names
+backup = backup
+gpus  = 3

deep_sort_torch/detector/YOLOv3/cfg/yolo-voc.cfg

@@ -0,0 +1,258 @@
+[net]
+# Testing
+batch=64
+subdivisions=8
+# Training
+# batch=64
+# subdivisions=8
+height=416
+width=416
+channels=3
+momentum=0.9
+decay=0.0005
+angle=0
+saturation = 1.5
+exposure = 1.5
+hue=.1
+
+learning_rate=0.001
+burn_in=1000
+max_batches = 80200
+policy=steps
+steps=-1,500,40000,60000
+scales=0.1,10,.1,.1
+
+[convolutional]
+batch_normalize=1
+filters=32
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+
+#######
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[route]
+layers=-9
+
+[convolutional]
+batch_normalize=1
+size=1
+stride=1
+pad=1
+filters=64
+activation=leaky
+
+[reorg]
+stride=2
+
+[route]
+layers=-1,-4
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=125
+activation=linear
+
+
+[region]
+anchors =  1.3221, 1.73145, 3.19275, 4.00944, 5.05587, 8.09892, 9.47112, 4.84053, 11.2364, 10.0071
+bias_match=1
+classes=20
+coords=4
+num=5
+softmax=1
+jitter=.3
+rescore=1
+
+object_scale=5
+noobject_scale=1
+class_scale=1
+coord_scale=1
+
+absolute=1
+thresh = .6
+random=1

deep_sort_torch/detector/YOLOv3/cfg/yolo.cfg

@@ -0,0 +1,258 @@
+[net]
+# Testing
+batch=1
+subdivisions=1
+# Training
+# batch=64
+# subdivisions=8
+width=416
+height=416
+channels=3
+momentum=0.9
+decay=0.0005
+angle=0
+saturation = 1.5
+exposure = 1.5
+hue=.1
+
+learning_rate=0.001
+burn_in=1000
+max_batches = 500200
+policy=steps
+steps=400000,450000
+scales=.1,.1
+
+[convolutional]
+batch_normalize=1
+filters=32
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+
+#######
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[route]
+layers=-9
+
+[convolutional]
+batch_normalize=1
+size=1
+stride=1
+pad=1
+filters=64
+activation=leaky
+
+[reorg]
+stride=2
+
+[route]
+layers=-1,-4
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=425
+activation=linear
+
+
+[region]
+anchors =  0.57273, 0.677385, 1.87446, 2.06253, 3.33843, 5.47434, 7.88282, 3.52778, 9.77052, 9.16828
+bias_match=1
+classes=80
+coords=4
+num=5
+softmax=1
+jitter=.3
+rescore=1
+
+object_scale=5
+noobject_scale=1
+class_scale=1
+coord_scale=1
+
+absolute=1
+thresh = .6
+random=1

deep_sort_torch/detector/YOLOv3/cfg/yolo_v3.cfg

@@ -0,0 +1,789 @@
+[net]
+# Testing
+#batch=1
+#subdivisions=1
+# Training
+batch=16
+subdivisions=4
+width=416
+height=416
+channels=3
+momentum=0.9
+decay=0.0005
+angle=0
+saturation = 1.5
+exposure = 1.5
+hue=.1
+
+learning_rate=0.001
+burn_in=1000
+max_batches = 500200
+policy=steps
+steps=20,25
+scales=.1,.1
+
+[convolutional]
+batch_normalize=1
+filters=32
+size=3
+stride=1
+pad=1
+activation=leaky
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=3
+stride=2
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=32
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=2
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=2
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=2
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=2
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[shortcut]
+from=-3
+activation=linear
+
+######################
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=255
+activation=linear
+
+
+[yolo]
+mask = 6,7,8
+anchors = 10,13,  16,30,  33,23,  30,61,  62,45,  59,119,  116,90,  156,198,  373,326
+classes=80
+num=9
+jitter=.3
+ignore_thresh = .5
+truth_thresh = 1
+random=1
+
+
+[route]
+layers = -4
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[upsample]
+stride=2
+
+[route]
+layers = -1, 61
+
+
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=512
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=512
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=512
+activation=leaky
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=255
+activation=linear
+
+
+[yolo]
+mask = 3,4,5
+anchors = 10,13,  16,30,  33,23,  30,61,  62,45,  59,119,  116,90,  156,198,  373,326
+classes=80
+num=9
+jitter=.3
+ignore_thresh = .5
+truth_thresh = 1
+random=1
+
+
+
+[route]
+layers = -4
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[upsample]
+stride=2
+
+[route]
+layers = -1, 36
+
+
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=256
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=256
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=256
+activation=leaky
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=255
+activation=linear
+
+
+[yolo]
+mask = 0,1,2
+anchors = 10,13,  16,30,  33,23,  30,61,  62,45,  59,119,  116,90,  156,198,  373,326
+classes=80
+num=9
+jitter=.3
+ignore_thresh = .5
+truth_thresh = 1
+random=1
+

deep_sort_torch/detector/YOLOv3/cfg/yolov3-tiny.cfg

@@ -0,0 +1,182 @@
+[net]
+# Testing
+batch=1
+subdivisions=1
+# Training
+# batch=64
+# subdivisions=2
+width=416
+height=416
+channels=3
+momentum=0.9
+decay=0.0005
+angle=0
+saturation = 1.5
+exposure = 1.5
+hue=.1
+
+learning_rate=0.001
+burn_in=1000
+max_batches = 500200
+policy=steps
+steps=400000,450000
+scales=.1,.1
+
+[convolutional]
+batch_normalize=1
+filters=16
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=32
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=1
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+###########
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=255
+activation=linear
+
+
+
+[yolo]
+mask = 3,4,5
+anchors = 10,14,  23,27,  37,58,  81,82,  135,169,  344,319
+classes=80
+num=6
+jitter=.3
+ignore_thresh = .7
+truth_thresh = 1
+random=1
+
+[route]
+layers = -4
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[upsample]
+stride=2
+
+[route]
+layers = -1, 8
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=255
+activation=linear
+
+[yolo]
+mask = 0,1,2
+anchors = 10,14,  23,27,  37,58,  81,82,  135,169,  344,319
+classes=80
+num=6
+jitter=.3
+ignore_thresh = .7
+truth_thresh = 1
+random=1