Pytorchvideo Versions Save

This release includes several significant new features, bug fixes and tutorials New additions include the following,

Models

• Multi-Scale Vision Transformers (MViT) along with it's model builders and associated pre-trained models in the model zoo. MViT is a new state of the art vision transformer model that beats the existing baselines all while requiring lesser compute resources.
• Audio Visual SlowFast Model - This would enable you to work with Audio and Video Modalities simultaneously
• Video action detection Resnet model and associated pre-trained models in the model zoo.

Transform

• AugMix
• MixUp and CutMix
• and more

Simply, adding AugMix and MixUp transforms to your existing training recipes should boost your models baseline accuracy.

Datasets

• Ava dataset and it's associated benchmarks and tutorials

https://ai.facebook.com/blog/pytorchvideo-a-deep-learning-library-for-video-understanding/