# YOLOv7-Pose-Bytetrack-STGCN

**Repository Path**: nicky208/YOLOv7-Pose-Bytetrack-STGCN

## Basic Information

- **Project Name**: YOLOv7-Pose-Bytetrack-STGCN
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2024-06-30
- **Last Updated**: 2024-06-30

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# YOLOv7-Pose-Bytetrack-STGCN

YOLOv7-POSE was used for key point detection, Bytetrack for tracking, and STGCN for fall and other behavior recognition.

 <img width="200" height="300" src="./utils/figures/kpt.png"> |    <img width="200" height="300"  src="./utils/figures/kpt+track.png"> |     <img width="200" height="300" src="./utils/figures/kpt+track+stgcn.png">
 
 Key point detection, run the command below:
```
python detect.py --weights "yolov7-w6-pose.pt" --kpt-label  --view-img
```
Key point detection+Bytetrack, run the command below:
```
python detect_track.py --weights "yolov7-w6-pose.pt" --kpt-label  --view-img
```
Key point detection+Bytetrack+STGCN, run the command below:
```
python detect_track_stgcn.py --weights "yolov7-w6-pose.pt" --kpt-label  --view-img
```
YOLO-Pose: [https://github.com/Bigtuo/YOLO-POSE-Bytetrack-STGCN]

# yolov7-pose
Implementation of "YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors"

Pose estimation implimentation is based on [YOLO-Pose](https://arxiv.org/abs/2204.06806). 

## Dataset preparison

[[Keypoints Labels of MS COCO 2017]](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/coco2017labels-keypoints.zip)

## Training

[yolov7-w6-person.pt](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-w6-person.pt)

``` shell
python -m torch.distributed.launch --nproc_per_node 8 --master_port 9527 train.py --data data/coco_kpts.yaml --cfg cfg/yolov7-w6-pose.yaml --weights weights/yolov7-w6-person.pt --batch-size 128 --img 960 --kpt-label --sync-bn --device 0,1,2,3,4,5,6,7 --name yolov7-w6-pose --hyp data/hyp.pose.yaml
```

## Deploy
TensorRT:[https://github.com/nanmi/yolov7-pose](https://github.com/nanmi/yolov7-pose)

## Testing

[yolov7-w6-pose.pt](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-w6-pose.pt)

``` shell
python test.py --data data/coco_kpts.yaml --img 960 --conf 0.001 --iou 0.65 --weights yolov7-w6-pose.pt --kpt-label
```

## Citation

```
@article{wang2022yolov7,
  title={{YOLOv7}: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors},
  author={Wang, Chien-Yao and Bochkovskiy, Alexey and Liao, Hong-Yuan Mark},
  journal={arXiv preprint arXiv:2207.02696},
  year={2022}
}
```

## Acknowledgements

<details><summary> <b>Expand</b> </summary>

* [https://github.com/AlexeyAB/darknet](https://github.com/AlexeyAB/darknet)
* [https://github.com/WongKinYiu/yolor](https://github.com/WongKinYiu/yolor)
* [https://github.com/WongKinYiu/PyTorch_YOLOv4](https://github.com/WongKinYiu/PyTorch_YOLOv4)
* [https://github.com/WongKinYiu/ScaledYOLOv4](https://github.com/WongKinYiu/ScaledYOLOv4)
* [https://github.com/Megvii-BaseDetection/YOLOX](https://github.com/Megvii-BaseDetection/YOLOX)
* [https://github.com/ultralytics/yolov3](https://github.com/ultralytics/yolov3)
* [https://github.com/ultralytics/yolov5](https://github.com/ultralytics/yolov5)
* [https://github.com/DingXiaoH/RepVGG](https://github.com/DingXiaoH/RepVGG)
* [https://github.com/JUGGHM/OREPA_CVPR2022](https://github.com/JUGGHM/OREPA_CVPR2022)
* [https://github.com/TexasInstruments/edgeai-yolov5/tree/yolo-pose](https://github.com/TexasInstruments/edgeai-yolov5/tree/yolo-pose)

</details>