简介

本仓库存储了与 Kalray 神经网络 API 兼容的 YOLOv4-CSP-S-Mish 模型。</br> 详情及正确使用方法请参阅 www.github.com/kalray/kann-models-zoo。</br>

内容

• ONNX: yolov4-csp-s-mish_608x608.optimized.onnx

参考文献注记

• YOLOv4: Optimal Speed and Accuracy of Object Detection, https://arxiv.org/pdf/2004.10934.pdf

仓库或链接参考

• 仓库: https://github.com/WongKinYiu/PyTorch_YOLOv4
• 配置文件: https://github.com/WongKinYiu/PyTorch_YOLOv4/blob/master/cfg/yolov4-csp-s-mish.cfg
• 权重: https://drive.google.com/file/d/1730MvuVhTttVJGk4ftN1zql9z7U4iQ6U/view?usp=sharing

BibTeX 条目和引用信息

@misc{bochkovskiy2020yolov4,
      title={YOLOv4: Optimal Speed and Accuracy of Object Detection}, 
      author={Alexey Bochkovskiy and Chien-Yao Wang and Hong-Yuan Mark Liao},
      year={2020},
      eprint={2004.10934},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}
@InProceedings{Wang_2021_CVPR,
    author    = {Wang, Chien-Yao and Bochkovskiy, Alexey and Liao, Hong-Yuan Mark},
    title     = {{Scaled-YOLOv4}: Scaling Cross Stage Partial Network},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2021},
    pages     = {13029-13038}
}