A minimal PyTorch implementation of YOLOv4.
Paper Yolo v4: https://arxiv.org/abs/2004.10934
Source code:https://github.com/AlexeyAB/darknet
More details: http://pjreddie.com/darknet/yolo/
Inference
Train
download model weight https://drive.google.com/open?id=1cewMfusmPjYWbrnuJRuKhPMwRe_b9PaT
python demo.py cfgfile weightfile imgfile
Convolution weight reshape
Mish activation
route number > 2
Maxpooling
yololayer
Reference:
https://github.com/eriklindernoren/PyTorch-YOLOv3
https://github.com/marvis/pytorch-caffe-darknet-convert
https://github.com/marvis/pytorch-yolo3
@article{yolov4,
title={YOLOv4: YOLOv4: Optimal Speed and Accuracy of Object Detection},
author={Alexey Bochkovskiy, Chien-Yao Wang, Hong-Yuan Mark Liao},
journal = {arXiv},
year={2020}
}
专知便捷查看
便捷下载,请关注专知公众号(点击上方蓝色专知关注)
后台回复“MTCME” 就可以获取《麻省理工学院马丁信托创业中心创业知识库》专知下载链接