hjihye / hrnet

Implementation of HRNet

HRNet

Implementation of "Deep High-Resolution Representation Learning for Human Pose Estimation". This code is based on the "Simple Baselines for Human Pose Estimation and Tracking".

Trained model [COCO data,70 epoch] (https://drive.google.com/file/d/1H9dElsNDvA--ybbRANaaiLkajN6O0tHF/view?usp=sharing)

Results on COCO 2017 val (using 70 epoch trained model)

Arch	Input size	AP	AP .5	AP.75	AP(M)	AP(L)	AR	AR .5
HRNet_w32	256x192	39.8	73.5	38.5	37.6	45.1	54.6	84.4

Quick start

Installation

1. Install pytorch >= v1.0.0 following official instruction. Note that if you use pytorch's version < v1.0.0, you should following the instruction at https://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 COCOAPI:

   # COCOAPI=/path/to/clone/cocoapi
   git clone https://github.com/cocodataset/cocoapi.git $COCOAPI
   cd $COCOAPI/PythonAPI
   # Install into global site-packages
   make install
   # Alternatively, if you do not have permissions or prefer
   # not to install the COCO API into global site-packages
   python3 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.

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

   mkdir output 
   mkdir log
   

Data preparation

For COCO data, please download from COCO 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 from OneDrive or GoogleDrive. 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
                |-- ... 

Training and Testing

Training COCO 2017 training keypoints dataset

python train.py

Testing COCO 2017 validation keypoints dataset

python val.py

Evaluate results using COCOApi

python eval_coco.py