This repository contains a two-stage-tracker. The detections generated by YOLOv5, a family of object detection architectures and models pretrained on the COCO dataset, are passed to a Deep Sort algorithm which tracks the objects. It can track any object that your Yolov5 model was trained to detect. (clone the above yolov5 and deepsort repository inside the root directory)
- Yolov5 training on Custom Data (link to external repository)
- DeepSort deep descriptor training (link to external repository)
- Yolov5 deep_sort pytorch evaluation
- Clone the repository recursively:
git clone --recurse-submodules https://github.com/mikel-brostrom/Yolov5_DeepSort_Pytorch.git
If you already cloned and forgot to use --recurse-submodules
you can run git submodule update --init
- Make sure that you fulfill all the requirements: Python 3.8 or later with all requirements.txt dependencies installed, including torch>=1.7. To install, run:
- incase if you face any torch issue try to install torch=1.9.1
pip install -r requirements.txt
Tracking can be run on most video formats
$ python track.py --source 0 # webcam
img.jpg # image
vid.mp4 # video
path/ # directory
path/*.jpg # glob
'https://youtu.be/Zgi9g1ksQHc' # YouTube
'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP stream
There is a clear trade-off between model inference speed and accuracy. In order to make it possible to fulfill your inference speed/accuracy needs you can select a Yolov5 family model for automatic download
$ python track.py --source 0 --yolo_model yolov5n.pt --img 640
yolov5s.pt
yolov5m.pt
yolov5l.pt
yolov5x.pt --img 1280
...
Choose a ReID model based on your needs from this ReID model zoo
$ python track.py --source 0 --deep_sort_model osnet_x1_0
nasnsetmobile
resnext101_32x8d
...
By default the tracker tracks all MS COCO classes.
If you only want to track persons I recommend you to get, crowdhuman weight file these weights for increased performance
python3 track.py --source 0 --yolo_model yolov5/weights/crowdhuman_yolov5m.pt --classes 0 # tracks persons, only