by HRNet

Train the HRNet model on ImageNet

530 Stars 116 Forks Last release: Not found MIT License 38 Commits 0 Releases

Available items

No Items, yet!

The developer of this repository has not created any items for sale yet. Need a bug fixed? Help with integration? A different license? Create a request here:

High-resolution networks (HRNets) for Image classification


  • [2020/03/13] Our paper is accepted by TPAMI: Deep High-Resolution Representation Learning for Visual Recognition.

  • Per request, we provide two small HRNet models. #parameters and GFLOPs are similar to ResNet18. The segmentation resutls using the two small models are also available at

  • TensoFlow implemenation available at Thanks VictorLi!

  • ONNX export enabled after fixing issues. Thanks Baowen Bao!


This is the official code of high-resolution representations for ImageNet classification. We augment the HRNet with a classification head shown in the figure below. First, the four-resolution feature maps are fed into a bottleneck and the number of output channels are increased to 128, 256, 512, and 1024, respectively. Then, we downsample the high-resolution representations by a 2-strided 3x3 convolution outputting 256 channels and add them to the representations of the second-high-resolution representations. This process is repeated two times to get 1024 channels over the small resolution. Last, we transform 1024 channels to 2048 channels through a 1x1 convolution, followed by a global average pooling operation. The output 2048-dimensional representation is fed into the classifier.

ImageNet pretrained models

HRNetV2 ImageNet pretrained models are now available!

| model |#Params | GFLOPs |top-1 error| top-5 error| Link | | :--: | :--: | :--: | :--: | :--: | :--: | | HRNet-W18-C-Small-v1 | 13.2M | 1.49 | 27.7% | 9.3% |OneDrive/BaiduYun(Access Code:v3sw) | HRNet-W18-C-Small-v2 | 15.6M | 2.42 | 24.9% | 7.6% |OneDrive/BaiduYun(Access Code:bnc9) | HRNet-W18-C | 21.3M | 3.99 | 23.2% | 6.6% |OneDrive/BaiduYun(Access Code:r5xn)| | HRNet-W30-C | 37.7M | 7.55 | 21.8% | 5.8% |OneDrive/BaiduYun(Access Code:ajc1)| | HRNet-W32-C | 41.2M | 8.31 | 21.5% | 5.8% |OneDrive/BaiduYun(Access Code:itc1)|| | HRNet-W40-C | 57.6M | 11.8 | 21.1% | 5.5% |OneDrive/BaiduYun(Access Code:i58x)| | HRNet-W44-C | 67.1M | 13.9 | 21.1% | 5.6% |OneDrive/BaiduYun(Access Code:3imd)| | HRNet-W48-C | 77.5M | 16.1 | 20.7% | 5.5% |OneDrive/BaiduYun(Access Code:68g2)| | HRNet-W64-C | 128.1M | 26.9 | 20.5% | 5.4% |OneDrive/BaiduYun(Access Code:6kw4)|

Quick start


  1. Install PyTorch=0.4.1 following the official instructions
  2. git clone
  3. Install dependencies: pip install -r requirements.txt

Data preparation

You can follow the Pytorch implementation:

The data should be under ./data/imagenet/images/.

Train and test

Please specify the configuration file.

For example, train the HRNet-W18 on ImageNet with a batch size of 128 on 4 GPUs:

python tools/ --cfg experiments/cls_hrnet_w18_sgd_lr5e-2_wd1e-4_bs32_x100.yaml

For example, test the HRNet-W18 on ImageNet on 4 GPUs:

python tools/ --cfg experiments/cls_hrnet_w18_sgd_lr5e-2_wd1e-4_bs32_x100.yaml --testModel hrnetv2_w18_imagenet_pretrained.pth

Other applications of HRNet


If you find this work or code is helpful in your research, please cite: ```` @inproceedings{SunXLW19, title={Deep High-Resolution Representation Learning for Human Pose Estimation}, author={Ke Sun and Bin Xiao and Dong Liu and Jingdong Wang}, booktitle={CVPR}, year={2019} }

@article{WangSCJDZLMTWLX19, title={Deep High-Resolution Representation Learning for Visual Recognition}, author={Jingdong Wang and Ke Sun and Tianheng Cheng and Borui Jiang and Chaorui Deng and Yang Zhao and Dong Liu and Yadong Mu and Mingkui Tan and Xinggang Wang and Wenyu Liu and Bin Xiao}, journal = {TPAMI} year={2019} } ````


[1] Deep High-Resolution Representation Learning for Visual Recognition. Jingdong Wang, Ke Sun, Tianheng Cheng, Borui Jiang, Chaorui Deng, Yang Zhao, Dong Liu, Yadong Mu, Mingkui Tan, Xinggang Wang, Wenyu Liu, Bin Xiao. Accepted by TPAMI. download

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.