/PyTorch_YOLOv4

PyTorch implementation of YOLOv4

Primary LanguagePython

YOLOv4

This is PyTorch implementation of YOLOv4 which is based on ultralytics/yolov3.

development log

Expand

Pretrained Models & Comparison

Model Test Size APval AP50val AP75val APSval APMval APLval cfg weights
YOLOv4paspp 736 45.7% 64.2% 50.3% 27.4% 51.3% 58.6% cfg weights
YOLOv4pacsp-s 736 36.0% 54.2% 39.4% 18.7% 41.2% 48.0% cfg weights
YOLOv4pacsp 736 46.4% 64.8% 51.0% 28.5% 51.9% 59.5% cfg weights
YOLOv4pacsp-x 736 47.6% 66.1% 52.2% 29.9% 53.3% 61.5% cfg weights
YOLOv4pacsp-s-mish 736 37.4% 56.3% 40.0% 20.9% 43.0% 49.3% cfg weights
YOLOv4pacsp-mish 736 46.5% 65.7% 50.2% 30.0% 52.0% 59.4% cfg weights
YOLOv4pacsp-x-mish 736 48.5% 67.4% 52.7% 30.9% 54.0% 62.0% cfg weights
YOLOv4tiny 416 22.5% 39.3% 22.5% 7.4% 26.3% 34.8% cfg weights

Requirements

pip install -r requirements.txt

※ For running Mish models, please install https://github.com/thomasbrandon/mish-cuda

Training

python train.py --data coco2017.data --cfg yolov4-pacsp.cfg --weights '' --name yolov4-pacsp --img 640 640 640

Testing

python test_half.py --data coco2017.data --cfg yolov4-pacsp.cfg --weights yolov4-pacsp.pt --img 736 --iou-thr 0.7 --batch-size 8

Citation

@article{bochkovskiy2020yolov4,
  title={{YOLOv4}: Optimal Speed and Accuracy of Object Detection},
  author={Bochkovskiy, Alexey and Wang, Chien-Yao and Liao, Hong-Yuan Mark},
  journal={arXiv preprint arXiv:2004.10934},
  year={2020}
}
@inproceedings{wang2020cspnet,
  title={{CSPNet}: A New Backbone That Can Enhance Learning Capability of {CNN}},
  author={Wang, Chien-Yao and Mark Liao, Hong-Yuan and Wu, Yueh-Hua and Chen, Ping-Yang and Hsieh, Jun-Wei and Yeh, I-Hau},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  pages={390--391},
  year={2020}
}

Acknowledgements