| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| PyTorchVideo Version 0.1.3 source code.tar.gz | 2021-08-31 | 3.8 MB | |
| PyTorchVideo Version 0.1.3 source code.zip | 2021-08-31 | 4.0 MB | |
| README.md | 2021-08-31 | 2.0 kB | |
| Totals: 3 Items | 7.8 MB | 0 | |
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
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