YOLOv4

This is PyTorch implementation of YOLOv4 which is based on ultralytics/yolov5.

development log

Expand

2020-08-29 - support deformable kernel.
2020-08-24 - support channel last training/testing.
2020-08-16 - design CSPPRN.
2020-08-15 - design deeper model. csp-p6-mish
2020-08-11 - support HarDNet. hard39-pacsp hard68-pacsp hard85-pacsp
2020-08-10 - add DDP training.
2020-08-06 - support DCN, DCNv2. yolov4-dcn
2020-08-01 - add pytorch hub.
2020-07-31 - support ResNet, ResNeXt, CSPResNet, CSPResNeXt. r50-pacsp x50-pacsp cspr50-pacsp cspx50-pacsp
2020-07-28 - support SAM. yolov4-pacsp-sam
2020-07-24 - update api.
2020-07-23 - support CUDA accelerated Mish activation function.
2020-07-19 - support and training tiny YOLOv4. yolov4-tiny
2020-07-15 - design and training conditional YOLOv4. yolov4-pacsp-conditional
2020-07-13 - support MixUp data augmentation.
2020-07-03 - design new stem layers.
2020-06-16 - support floating16 of GPU inference.
2020-06-14 - convert .pt to .weights for darknet fine-tuning.
2020-06-13 - update multi-scale training strategy.
2020-06-12 - design scaled YOLOv4 follow ultralytics. yolov4-pacsp-s yolov4-pacsp-m yolov4-pacsp-l yolov4-pacsp-x
2020-06-07 - design scaling methods for CSP-based models. yolov4-pacsp-25 yolov4-pacsp-75
2020-06-03 - update COCO2014 to COCO2017.
2020-05-30 - update FPN neck to CSPFPN. yolov4-yocsp yolov4-yocsp-mish
2020-05-24 - update neck of YOLOv4 to CSPPAN. yolov4-pacsp yolov4-pacsp-mish
2020-05-15 - training YOLOv4 with Mish activation function. yolov4-yospp-mish yolov4-paspp-mish
2020-05-08 - design and training YOLOv4 with FPN neck. yolov4-yospp
2020-05-01 - training YOLOv4 with Leaky activation function using PyTorch. yolov4-paspp

Pretrained Models & Comparison

Model	Test Size	AP^val	AP₅₀^val	AP₇₅^val	AP_S^val	AP_M^val	AP_L^val	yaml	weights
YOLOv4_s-mish	672	40.3%	59.4%	43.8%	23.9%	45.3%	52.2%	yaml	weights
YOLOv4_m-mish	672	44.7%	64.0%	48.7%	28.3%	50.2%	57.7%	yaml	weights
YOLOv4_l-mish	672	48.1%	66.8%	52.6%	31.9%	53.3%	61.0%	yaml	weights
YOLOv4_x-mish	672	49.8%	68.4%	54.4%	32.7%	55.3%	63.6%	yaml	weights

YOLOv4_x-mish	TTA	51.2%	69.1%	56.1%	35.6%	56.3%	64.9%	yaml	weights

CSP_p6-mish	960	51.7%	70.2%	56.5%	34.5%	56.3%	66.0%	-	-
CSP_p6-mish	TTA	52.7%	70.4%	57.8%	37.1%	57.3%	66.6%	-	-

CSP_p6-mish	1280	53.1%	71.2%	57.9%	37.6%	57.3%	66.3%	-	-
CSP_p6-mish	TTA	53.8%	71.4%	59.0%	38.3%	58.2%	67.7%	-	-

Model	Test Size	AP^test	AP₅₀^test	AP₇₅^test	AP_S^test	AP_M^test	AP_L^test	batch1 throughput
CSP_p6-mish	1280	53.3%	71.3%	58.2%	35.3%	56.9%	64.8%	30 fps
CSP_p6-mish	TTA	54.0%	71.5%	59.2%	36.3%	57.7%	66.0%	-

Requirements

pip install -r requirements.txt

Training

python train.py --data coco.yaml --cfg yolov4l-mish.yaml --weights ''

※ Please also install https://github.com/thomasbrandon/mish-cuda

Testing

python test.py --img 672 --conf 0.001 --batch 32 --data coco.yaml --weights weights/yolov4l-mish.pt

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}
}

yytzsy / pytorch_yolov4 Goto Github PK

pytorch_yolov4's Introduction

YOLOv4

development log

Pretrained Models & Comparison

Requirements

Training

Testing

Citation

Acknowledgements

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent