PYSKL is a toolbox focusing on action recognition based on SKeLeton data with PYTorch. Various algorithms will be supported for skeleton-based action recognition. We build this project based on the OpenSource Project MMAction2.

This repo is the official implementation of PoseConv3D and STGCN++.

Skeleton-base Action Recognition Results on NTU-RGB+D-120

Supported Algorithms


git clone
cd pyskl
pip install -r requirements.txt
pip install -e .

Data Preparation

For data pre-processing, we estimate 2D skeletons with a two-stage pose estimator (Faster-RCNN + HRNet). For 3D skeletons, we follow the pre-processing procedure of CTR-GCN. Currently, we do not provide the pre-processing scripts. Instead, we directly provide the processed skeleton data as pickle files, which can be directly used in training and evaluation. You can use vis_skeleton to visualize the provided skeleton data.

Training & Testing

You can use following commands for training and testing. Basically, we support distribued training on a single server with multiple GPUs.

# Training
bash tools/ {config_name} {num_gpus} {other_options}
# Testing
bash tools/ {config_name} {checkpoint} {num_gpus} --out {output_file} --eval top_k_accuracy mean_class_accuracy

For specific examples, please go to the README for each specific algorithm we supported.


If you use PYSKL in your research or wish to refer to the baseline results published in the Model Zoo, please use the following BibTeX entry and the BibTex entry corresponding to the specific algorithm you used.

% Tech Report Coming Soon!
    title={PYSKL: a toolbox for skeleton-based video understanding},
    author={PYSKL Contributors},
    howpublished = {\url{}},


View Github