DPM-based framework

Prerequisites

• Python >= 3.6

• PyTorch >= 1.1.0

• PyYAML, tqdm, tensorboardX

• We provide the dependency file of our experimental environment, you can install all dependencies by creating a new anaconda virtual environment and running pip install -r requirements.txt

• Run pip install -e torchlight

Data Preparation

Download datasets.

There are 3 datasets to download:

• NTU RGB+D 60 Skeleton
• NTU RGB+D 120 Skeleton
• NW-UCLA

NTU RGB+D 60 and 120

1. Request dataset here: http://rose1.ntu.edu.sg/Datasets/actionRecognition.asp
2. Download the skeleton-only datasets:
   1. nturgbd_skeletons_s001_to_s017.zip (NTU RGB+D 60)
   2. nturgbd_skeletons_s018_to_s032.zip (NTU RGB+D 120)
   3. Extract above files to ./data/nturgbd_raw

NW-UCLA

1. Download dataset from here
2. Move all_sqe to ./data/NW-UCLA

Data Processing

Directory Structure

Put downloaded data into the following directory structure:

- data/
  - NW-UCLA/
    - all_sqe
      ... # raw data of NW-UCLA
  - ntu/
  - ntu120/
  - nturgbd_raw/
    - nturgb+d_skeletons/     # from `nturgbd_skeletons_s001_to_s017.zip`
      ...
    - nturgb+d_skeletons120/  # from `nturgbd_skeletons_s018_to_s032.zip`
      ...

Generating Data

• Generate NTU RGB+D 60 or NTU RGB+D 120 dataset:

 cd ./data/ntu # or cd ./data/ntu120
 # Get skeleton of each performer
 python get_raw_skes_data.py
 # Remove the bad skeleton 
 python get_raw_denoised_data.py
 # Transform the skeleton to the center of the first frame
 python seq_transformation.py

Training & Testing

Training

• To train model on NTU RGB+D 60/120 with bone or motion modalities, setting bone arguments in the config file default.yaml or in the command line.

# Example: training on NTU RGB+D 120 cross subject under bone modality
python main_ddpm2.py --config config/nturgbd120-cross-subject/default.yaml --train_feeder_args bone=True --test_feeder_args bone=True --work-dir work_dir/ntu120/csub/gcn_bone --device 0

• To train model on NW-UCLA with others modalities, you need to modify data_path in train_feeder_args and test_feeder_args to "bone" or "motion" or "bone motion", and run

python main_ddpm2.py --config config/ucla/default.yaml --work-dir work_dir/ucla/gcn_xxx --device 0

Testing

• To test the trained models saved in <work_dir>, run the following command:

python main.py --config <work_dir>/config.yaml --work-dir <work_dir> --phase test --save-score True --weights <work_dir>/xxx.pt --device 0

• To ensemble the results of different modalities, run

# Example: ensemble six streams of GCN on NTU RGB+D cross subject
python ensemble.py --dataset ntu/csub --joint-dir work_dir/ntu/csub/joint ... --joint-curl-dir work_dir/ntu/csub/mask ...