Repository files navigation

• [2021/04/12] Welcome to check out our recent work on bottom-up pose estimation (CVPR 2021)HRNet-DEKR!
• [2020/07/05]A very nice blog from Towards Data Science introducing HRNet and HigherHRNet for human pose estimation.
• [2020/03/13] A longer version is accepted by TPAMI:Deep High-Resolution Representation Learning for Visual Recognition. It includes more HRNet applications, and the codes are available:semantic segmentation,objection detection,facial landmark detection, andimage classification.
• [2020/02/01] We have added demo code for HRNet. ThanksAlex Simes.
• Visualization code for showing the pose estimation results. Thanks Depu!
• [2019/08/27] HigherHRNet is now onArXiv, which is a bottom-up approach for human pose estimation powerd by HRNet. We will also release code and models atHigher-HRNet-Human-Pose-Estimation, stay tuned!
• Our new workHigh-Resolution Representations for Labeling Pixels and Regions is available atHRNet. Our HRNet has been applied to a wide range of vision tasks, such asimage classification,objection detection,semantic segmentation andfacial landmark.

This is an official pytorch implementation ofDeep High-Resolution Representation Learning for Human Pose Estimation.In this work, we are interested in the human pose estimation problem with a focus on learning reliable high-resolution representations. Most existing methodsrecover high-resolution representations from low-resolution representations produced by a high-to-low resolution network. Instead, our proposed networkmaintains high-resolution representations through the whole process.We start from a high-resolution subnetwork as the first stage, gradually add high-to-low resolution subnetworks one by one to form more stages, and connect the mutli-resolution subnetworksin parallel. We conductrepeated multi-scale fusions such that each of the high-to-low resolution representations receives information from other parallel representations over and over, leading to rich high-resolution representations. As a result, the predicted keypoint heatmap is potentially more accurate and spatially more precise. We empirically demonstrate the effectiveness of our network through the superior pose estimation results over two benchmark datasets: the COCO keypoint detection dataset and the MPII Human Pose dataset.

• Flip test is used.
• Input size is 256x256
• pose_resnet_[50,101,152] is our previous work ofSimple Baselines for Human Pose Estimation and Tracking

• Flip test is used.
• Person detector has person AP of 56.4 on COCO val2017 dataset.
• pose_resnet_[50,101,152] is our previous work ofSimple Baselines for Human Pose Estimation and Tracking.
• GFLOPs is for convolution and linear layers only.

• Flip test is used.
• Person detector has person AP of 60.9 on COCO test-dev2017 dataset.
• pose_resnet_152 is our previous work ofSimple Baselines for Human Pose Estimation and Tracking.
• GFLOPs is for convolution and linear layers only.
• pose_hrnet_w48* means using additional data fromAI challenger for training.

The code is developed using python 3.6 on Ubuntu 16.04. NVIDIA GPUs are needed. The code is developed and tested using 4 NVIDIA P100 GPU cards. Other platforms or GPU cards are not fully tested.

1. Install pytorch >= v1.0.0 followingofficial instruction.Note that if you use pytorch's version < v1.0.0, you should following the instruction athttps://github.com/Microsoft/human-pose-estimation.pytorch to disable cudnn's implementations of BatchNorm layer. We encourage you to use higher pytorch's version(>=v1.0.0)

2. Clone this repo, and we'll call the directory that you cloned as ${POSE_ROOT}.

3. Install dependencies:

   pip install -r requirements.txt

4. Make libs:

   cd ${POSE_ROOT}/libmake

5. InstallCOCOAPI:

   # COCOAPI=/path/to/clone/cocoapigit clone https://github.com/cocodataset/cocoapi.git $COCOAPIcd $COCOAPI/PythonAPI# Install into global site-packagesmake install# Alternatively, if you do not have permissions or prefer# not to install the COCO API into global site-packagespython3 setup.py install --user

   Note that instructions like # COCOAPI=/path/to/install/cocoapi indicate that you should pick a path where you'd like to have the software cloned and then set an environment variable (COCOAPI in this case) accordingly.

6. Init output(training model output directory) and log(tensorboard log directory) directory:

   mkdir output mkdir log

   Your directory tree should look like this:

   ${POSE_ROOT}├── data├── experiments├── lib├── log├── models├── output├── tools ├── README.md└── requirements.txt

7. Download pretrained models from our model zoo(GoogleDrive orOneDrive)

   ${POSE_ROOT} `-- models     `-- pytorch         |-- imagenet         |   |-- hrnet_w32-36af842e.pth         |   |-- hrnet_w48-8ef0771d.pth         |   |-- resnet50-19c8e357.pth         |   |-- resnet101-5d3b4d8f.pth         |   `-- resnet152-b121ed2d.pth         |-- pose_coco         |   |-- pose_hrnet_w32_256x192.pth         |   |-- pose_hrnet_w32_384x288.pth         |   |-- pose_hrnet_w48_256x192.pth         |   |-- pose_hrnet_w48_384x288.pth         |   |-- pose_resnet_101_256x192.pth         |   |-- pose_resnet_101_384x288.pth         |   |-- pose_resnet_152_256x192.pth         |   |-- pose_resnet_152_384x288.pth         |   |-- pose_resnet_50_256x192.pth         |   `-- pose_resnet_50_384x288.pth         `-- pose_mpii             |-- pose_hrnet_w32_256x256.pth             |-- pose_hrnet_w48_256x256.pth             |-- pose_resnet_101_256x256.pth             |-- pose_resnet_152_256x256.pth             `-- pose_resnet_50_256x256.pth

For MPII data, please download fromMPII Human Pose Dataset. The original annotation files are in matlab format. We have converted them into json format, you also need to download them fromOneDrive orGoogleDrive.Extract them under {POSE_ROOT}/data, and make them look like this:

${POSE_ROOT}|-- data`-- |-- mpii    `-- |-- annot        |   |-- gt_valid.mat        |   |-- test.json        |   |-- train.json        |   |-- trainval.json        |   `-- valid.json        `-- images            |-- 000001163.jpg            |-- 000003072.jpg

For COCO data, please download fromCOCO download, 2017 Train/Val is needed for COCO keypoints training and validation. We also provide person detection result of COCO val2017 and test-dev2017 to reproduce our multi-person pose estimation results. Please download fromOneDrive orGoogleDrive.Download and extract them under {POSE_ROOT}/data, and make them look like this:

${POSE_ROOT}|-- data`-- |-- coco    `-- |-- annotations        |   |-- person_keypoints_train2017.json        |   `-- person_keypoints_val2017.json        |-- person_detection_results        |   |-- COCO_val2017_detections_AP_H_56_person.json        |   |-- COCO_test-dev2017_detections_AP_H_609_person.json        `-- images            |-- train2017            |   |-- 000000000009.jpg            |   |-- 000000000025.jpg            |   |-- 000000000030.jpg            |   |-- ...             `-- val2017                |-- 000000000139.jpg                |-- 000000000285.jpg                |-- 000000000632.jpg                |-- ...

python tools/test.py \    --cfg experiments/mpii/hrnet/w32_256x256_adam_lr1e-3.yaml \    TEST.MODEL_FILE models/pytorch/pose_mpii/pose_hrnet_w32_256x256.pth

python tools/train.py \    --cfg experiments/mpii/hrnet/w32_256x256_adam_lr1e-3.yaml

python tools/test.py \    --cfg experiments/coco/hrnet/w32_256x192_adam_lr1e-3.yaml \    TEST.MODEL_FILE models/pytorch/pose_coco/pose_hrnet_w32_256x192.pth \    TEST.USE_GT_BBOX False

python tools/train.py \    --cfg experiments/coco/hrnet/w32_256x192_adam_lr1e-3.yaml \

python visualization/plot_coco.py \    --prediction output/coco/w48_384x288_adam_lr1e-3/results/keypoints_val2017_results_0.json \    --save-path visualization/results

Many other dense prediction tasks, such as segmentation, face alignment and object detection, etc. have been benefited by HRNet. More information can be found atHigh-Resolution Networks.

mmpose
ModelScope (中文）
timm

If you use our code or models in your research, please cite with:

@inproceedings{sun2019deep,  title={Deep High-Resolution Representation Learning for Human Pose Estimation},  author={Sun, Ke and Xiao, Bin and Liu, Dong and Wang, Jingdong},  booktitle={CVPR},  year={2019}}@inproceedings{xiao2018simple,    author={Xiao, Bin and Wu, Haiping and Wei, Yichen},    title={Simple Baselines for Human Pose Estimation and Tracking},    booktitle = {European Conference on Computer Vision (ECCV)},    year = {2018}}@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}}