TDN: Temporal Difference Networks for Efficient Action Recognition (CVPR 2021)

News

[Mar 24, 2022] We present VideoMAE, a new SOTA on Kinetics, Something-Something, and AVA.
[Dec 1, 2021] We update the TDN-ResNet101 on SSV2 in model zoo.
[Mar 5, 2021] TDN has been accepted by CVPR 2021.
[Dec 26, 2020] We have released the PyTorch code of TDN.

Overview

We release the PyTorch code of the TDN(Temporal Difference Networks). This code is based on the TSN and TSM codebase. The core code to implement the Temporal Difference Module are ops/base_module.py and ops/tdn_net.py.

TL; DR. We generalize the idea of RGB difference to devise an efficient temporal difference module (TDM) for motion modeling in videos, and provide an alternative to 3D convolutions by systematically presenting principled and detailed module design.

• Prerequisites
• Data Preparation
• Model Zoo
• Testing
• Training

Prerequisites

The code is built with following libraries:

• Python 3.6 or higher
• PyTorch 1.4 or higher
• Torchvision
• TensorboardX
• tqdm
• scikit-learn
• ffmpeg
• decord

Data Preparation

We have successfully trained TDN on Kinetics400, UCF101, HMDB51, Something-Something-V1 and V2 with this codebase.

• The processing of Something-Something-V1 & V2 can be summarized into 3 steps:

  1. Extract frames from videos(you can use ffmpeg to get frames from video)
  2. Generate annotations needed for dataloader ("<path_to_frames> <frames_num> <video_class>" in annotations) The annotation usually includes train.txt and val.txt. The format of *.txt file is like:

     dataset_root/frames/video_1 num_frames label_1
     dataset_root/frames/video_2 num_frames label_2
     dataset_root/frames/video_3 num_frames label_3
     ...
     dataset_root/frames/video_N num_frames label_N
     

  3. Add the information to ops/dataset_configs.py.

• The processing of Kinetics400 can be summarized into 3 steps:

  1. We preprocess our data by resizing the short edge of video to 320px. You can refer to MMAction2 Data Benchmark for TSN and SlowOnly.
  2. Generate annotations needed for dataloader ("<path_to_video> <video_class>" in annotations) The annotation usually includes train.txt and val.txt. The format of *.txt file is like:

     dataset_root/video_1.mp4  label_1
     dataset_root/video_2.mp4  label_2
     dataset_root/video_3.mp4  label_3
     ...
     dataset_root/video_N.mp4  label_N
     

  3. Add the information to ops/dataset_configs.py.

  Note: We use decord to decode the Kinetics videos on the fly.

Model Zoo

Here we provide some off-the-shelf pretrained models. The accuracy might vary a little bit compared to the paper, since the raw video of Kinetics downloaded by users may have some differences.

Something-Something-V1

Something-Something-V2

Kinetics400

Testing

• For center crop single clip, the processing of testing can be summarized into 2 steps:
  1. Run the following testing scripts:

     CUDA_VISIBLE_DEVICES=0 python3 test_models_center_crop.py something \
     --archs='resnet50' --weights <your_checkpoint_path>  --test_segments=8  \
     --test_crops=1 --batch_size=16  --gpus 0 --output_dir <your_pkl_path> -j 4 --clip_index=0
     

  2. Run the following scripts to get result from the raw score:

     python3 pkl_to_results.py --num_clips 1 --test_crops 1 --output_dir <your_pkl_path>  
     

• For 3 crops, 10 clips, the processing of testing can be summarized into 2 steps:
  1. Run the following testing scripts for 10 times(clip_index from 0 to 9):

     CUDA_VISIBLE_DEVICES=0 python3 test_models_three_crops.py  kinetics \
     --archs='resnet50' --weights <your_checkpoint_path>  --test_segments=8 \
     --test_crops=3 --batch_size=16 --full_res --gpus 0 --output_dir <your_pkl_path>  \
     -j 4 --clip_index <your_clip_index>
     

  2. Run the following scripts to ensemble the raw score of the 30 views:

     python pkl_to_results.py --num_clips 10 --test_crops 3 --output_dir <your_pkl_path> 
     

Training

This implementation supports multi-gpu, DistributedDataParallel training, which is faster and simpler.

• For example, to train TDN-ResNet50 on Something-Something-V1 with 8 gpus, you can run:

  python -m torch.distributed.launch --master_port 12347 --nproc_per_node=8 \
              main.py  something  RGB --arch resnet50 --num_segments 8 --gd 20 --lr 0.01 \
              --lr_scheduler step --lr_steps  30 45 55 --epochs 60 --batch-size 8 \
              --wd 5e-4 --dropout 0.5 --consensus_type=avg --eval-freq=1 -j 4 --npb 
  

• For example, to train TDN-ResNet50 on Kinetics400 with 8 gpus, you can run:

  python -m torch.distributed.launch --master_port 12347 --nproc_per_node=8 \
          main.py  kinetics RGB --arch resnet50 --num_segments 8 --gd 20 --lr 0.02 \
          --lr_scheduler step  --lr_steps 50 75 90 --epochs 100 --batch-size 16 \
          --wd 1e-4 --dropout 0.5 --consensus_type=avg --eval-freq=1 -j 4 --npb 
  

Contact

[email protected]

Acknowledgements

We especially thank the contributors of the TSN and TSM codebase for providing helpful code.

License

This repository is released under the Apache-2.0. license as found in the LICENSE file.

Citation

If you think our work is useful, please feel free to cite our paper 😆 :

@InProceedings{Wang_2021_CVPR,
    author    = {Wang, Limin and Tong, Zhan and Ji, Bin and Wu, Gangshan},
    title     = {TDN: Temporal Difference Networks for Efficient Action Recognition},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2021},
    pages     = {1895-1904}
}