VideoMAE Installation
The codebase is mainly built with following libraries:
Python 3.6 or higher
and
.
We can successfully reproduce the main results under two settings below:
Tesla A100 (40G): CUDA 11.1 + PyTorch 1.8.0 + torchvision 0.9.0
Tesla V100 (32G): CUDA 10.1 + PyTorch 1.6.0 + torchvision 0.7.0
DS_BUILD_OPS=1 pip install deepspeed
Note:
We recommend you to use PyTorch >= 1.8.0.
We observed accidental interrupt in the last epoch when conducted the pre-training experiments on V100 GPUs (PyTorch 1.6.0). This interrupt is caused by the scheduler of learning rate. We naively set --epochs 801 to walk away from issue :)