This is the official code of High-Resolution Representations for Object Detection. We extend the high-resolution representation (HRNet) [1] by augmenting the high-resolution representation by aggregating the (upsampled) representations from all the parallel convolutions, leading to stronger representations. We build a multi-level representation from the high resolution and apply it to the Faster R-CNN, Mask R-CNN and Cascade R-CNN framework. This proposed approach achieves superior results to existing single-model networks on COCO object detection. The code is based on maskrcnn-benchmark

HRNetV2 ImageNet pretrained models are now available! Codes and pretrained models are in HRNets for Image Classification

All models are trained on COCO train2017 set and evaluated on COCO val2017 set. Detailed settings or configurations are in configs/hrnet.

Note: Models are trained with the newly released code and the results have minor differences with that in the paper. Current results will be updated soon and more models and results are comming. All models are trained on COCO train2017 set and evaluated on COCO val2017 set. Detailed settings or configurations are in configs/hrnet.

Our HRNets will obtain larger gain when training with more iterations.

1. Install PyTorch 1.0 following the official instructions

2. Install pycocotools

git clone https://github.com/cocodataset/cocoapi.git \
 && cd cocoapi/PythonAPI \
 && python setup.py build_ext install \
 && cd ../../

3. Install HRNet-MaskRCNN-Benchmark

git clone https://github.com/HRNet/HRNet-MaskRCNN-Benchmark.git
cd HRNet-MaskRCNN-Benchmark
python setup.py build develop
pip install -r requirements.txt

for more details, see INSTALL.md

cd HRNet-MaskRCNN-Benchmark
# Download pretrained models into this folder
mkdir hrnetv2_pretrained

Please specify the configuration file in configs (learning rate should be adjusted when the number of GPUs is changed).

python -m torch.distributed.launch --nproc_per_node <GPU NUMS> tools/train_net.py --config-file <CONFIG FILE>

# example (4 gpus)
python -m torch.distributed.launch --nproc_per_node 4 tools/train_net.py --config-file configs/hrnet/e2e_faster_rcnn_hrnet_w18_1x.yaml

python -m torch.distributed.launch --nproc_per_node <GPU NUMS> tools/test_net.py --config-file <CONFIG-FILE> MODEL.WEIGHT <WEIGHT>

#example (4gpus)
python -m torch.distributed.launch --nproc_per_node 4 tools/test_net.py --config-file configs/hrnet/e2e_faster_rcnn_hrnet_w18_1x.yaml MODEL.WEIGHT FasterR-CNN-HR18-1x.pth

NOTE: If you meet some problems, you may find a solution in issues of official maskrcnn-benchmark or submit a new issue in our repo.

• Human pose estimation
• Semantic segmentation
• Facial landmark detection
• Image classification
• Object detection(based on mmdetection)

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{SunZJCXLMWLW19,
  title={High-Resolution Representations for Labeling Pixels and Regions},
  author={Ke Sun and Yang Zhao and Borui Jiang and Tianheng Cheng and Bin Xiao 
  and Dong Liu and Yadong Mu and Xinggang Wang and Wenyu Liu and Jingdong Wang},
  journal   = {CoRR},
  volume    = {abs/1904.04514},
  year={2019}
}

[1] Deep High-Resolution Representation Learning for Human Pose Estimation. Ke Sun, Bin Xiao, Dong Liu, and Jingdong Wang. CVPR 2019. download

[2] Cascade R-CNN: Delving into High Quality Object Detection. Zhaowei Cai, and Nuno Vasconcetos. CVPR 2018.