Installation

The codebase is mainly built with following libraries:

Python 3.8 or higher
PyTorch and torchvision.
We can successfully reproduce the main results under this setting:
Tesla A100 (40G): CUDA 11.1 + PyTorch 1.8.0 + torchvision 0.9.0
timm==0.4.12
~~deepspeed==0.5.8 DS_BUILD_OPS=1 pip install deepspeed~~
TensorboardX
decord
einops
PyAV pip install av

Note:

We recommend you to use PyTorch >= 1.8.0.
We observed accidental interrupt in the last epoch when enabled deepspeed. Therefore, we disable the option of deepspeed in the released version.