hardnet.md

HarDNet

• 论文：HarDNet: A Low Memory Traffic Network

• 官方项目：PingoLH/Pytorch-HarDNet

• 模型代码：hardnet.py

• 验证集数据处理：

  # 图像后端：pil
  # 输入图像大小：224x224
  transforms = T.Compose([
      T.Resize(256),
      T.CenterCrop(224),
      T.ToTensor(),
      T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
  ])

• 模型细节：

  Model	Model Name	Params (M)	FLOPs (G)	Top-1 (%)	Top-5 (%)	Pretrained Model
  HarDNet-68	hardnet_68	17.6	4.3	76.48	93.01	Download
  HarDNet-85	hardnet_85	36.7	9.1	78.04	93.89	Download
  HarDNet-39-ds	hardnet_39_ds	3.5	0.4	72.08	90.43	Download
  HarDNet-68-ds	hardnet_68_ds	4.2	0.8	74.29	91.87	Download

• 引用：

  @misc{chao2019hardnet,
      title={HarDNet: A Low Memory Traffic Network}, 
      author={Ping Chao and Chao-Yang Kao and Yu-Shan Ruan and Chien-Hsiang Huang and Youn-Long Lin},
      year={2019},
      eprint={1909.00948},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
  }