Skip to content

Latest commit

 

History

History
130 lines (80 loc) · 3.79 KB

agcn.md

File metadata and controls

130 lines (80 loc) · 3.79 KB
Raw

简体中文 | English

AGCN

Contents

Introduction

We implemented Adaptive Graph Convolution Network to improve the accuracy of ST-GCN.

Data

Please refer to FSD-10 data download and preparation doc FSD-10

Please refer to NTU-RGBD data download and preparation doc NTU-RGBD

Train

Train on FSD-10

  • Train AGCN on FSD-10 scripts:
python3.7 main.py -c configs/recognition/agcn/agcn_fsd.yaml
  • Turn off valid when training, as validation dataset is not available for the competition.

Train on NTU-RGBD

  • Train AGCN on NTU-RGBD scripts:
python3.7 -B -m paddle.distributed.launch --gpus="0,1,2,3"  --log_dir=log_agcn  main.py  --validate -c configs/recognition/agcn/agcn_ntucs.yaml
  • config file agcn_ntucs.yaml corresponding to the config of AGCN on NTU-RGB+D dataset with cross-subject splits.

Test

Test onf FSD-10

  • Test scripts：
python3.7 main.py --test -c configs/recognition/agcn/agcn_fsd.yaml  -w output/AGCN/AGCN_epoch_00100.pdparams

  • Specify the config file with -c, specify the weight path with -w.

  • Evaluation results will be saved in submission.csv file, final score can be obtained in competition website.

Accuracy on FSD-10 dataset:

Test_Data Top-1 checkpoints
Test_A 90.66 AGCN_fsd.pdparams
Test_B 88.66 -

Test on NTU-RGB+D

  • Test scripts：
python3.7 main.py --test -c configs/recognition/agcn/agcn_ntucs.yaml -w output/AGCN/AGCN_best.pdparams
  • Specify the config file with -c, specify the weight path with -w.

Accuracy on NTU-RGB+D dataset:

split Top-1 checkpoints
cross-subject 83.27 AGCN_ntucs.pdparams

Inference

export inference model

To get model architecture file AGCN.pdmodel and parameters file AGCN.pdiparams, use:

python3.7 tools/export_model.py -c configs/recognition/agcn/agcn_fsd.yaml \
                                -p data/AGCN_fsd.pdparams \
                                -o inference/AGCN

infer

python3.7 tools/predict.py --input_file data/fsd10/example_skeleton.npy \
                           --config configs/recognition/agcn/agcn_fsd.yaml \
                           --model_file inference/AGCN/AGCN.pdmodel \
                           --params_file inference/AGCN/AGCN.pdiparams \
                           --use_gpu=True \
                           --use_tensorrt=False

example of logs:

Current video file: data/fsd10/example_skeleton.npy
        top-1 class: 0
        top-1 score: 0.8932635188102722

Reference