Strong Augmentations

Introduction

This directory includes configs for training ST-GCN++ with strong spatial augmentations and 120 epochs. The augmentations we adopted include Random Rotating and Random Scaling.

Citation

@misc{duan2022pyskl,
    title={PYSKL: a toolbox for skeleton-based video understanding},
    author={PYSKL Contributors},
    howpublished = {\url{https://github.com/kennymckormick/pyskl}},
    year={2022}
}

Model Zoo

We release numerous checkpoints trained with various modalities, annotations on NTURGB+D and NTURGB+D 120. The accuracy of each modality links to the weight file.

Dataset	Annotation	GPUs	Joint Top1	Bone Top1	Joint Motion Top1	Bone-Motion Top1	Two-Stream Top1	Four Stream Top1
NTURGB+D XSub	Official 3D Skeleton	8	joint_config: 90.3	bone_config: 90.8	joint_motion_config: 88.3	bone_motion_config: 87.8	92.2	92.6
NTURGB+D XView	Official 3D Skeleton	8	joint_config: 96.6	bone_config: 95.9	joint_motion_config: 95.1	bone_motion_config: 93.7	97.1	97.4
NTURGB+D 120 XSub	Official 3D Skeleton	8	joint_config: 84.3	bone_config: 87.0	joint_motion_config: 82.2	bone_motion_config: 81.9	88.2	88.6
NTURGB+D 120 XSet	Official 3D Skeleton	8	joint_config: 86.7	bone_config: 88.3	joint_motion_config: 85.1	bone_motion_config: 84.4	90.1	90.8

Note

1. We use the linear-scaling learning rate (Initial LR ∝ Batch Size). If you change the training batch size, remember to change the initial LR proportionally.
2. For Two-Stream results, we adopt the 1 (Joint):1 (Bone) fusion. For Four-Stream results, we adopt the 2 (Joint):2 (Bone):1 (Joint Motion):1 (Bone Motion) fusion.

Training & Testing

Please refer to the README of ST-GCN++.