vision icon indicating copy to clipboard operation
vision copied to clipboard

Include implementation of MViTV2-B and MViTV2-L models

Open jsilter opened this issue 1 year ago • 2 comments

🚀 The feature, motivation and pitch

Currently Pytorch includes an implementation of MViTV2-S, showing that the model is useful. MViTV2-B and MViTV2-L are even more powerful. Weights are publicly available at https://github.com/facebookresearch/SlowFast/blob/main/projects/mvitv2/README.md.

Alternatives

The SlowFast library has an implementation but it's hard to use outside of the slowfast library. Would be much much easier to have something built in to pytorch.

Additional context

No response

jsilter avatar Oct 03 '24 18:10 jsilter

I think this might be more appropriate for https://github.com/pytorch/vision

colesbury avatar Oct 07 '24 16:10 colesbury

Hi @jsilter , thanks for the feature request. We're not planning on adding more models to torchvision at this time, sorry.

NicolasHug avatar Oct 11 '24 11:10 NicolasHug