Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Any Plans for release Swin-V2 Gaint? #182

Open
ckddls1321 opened this issue Mar 14, 2022 · 1 comment
Open

Any Plans for release Swin-V2 Gaint? #182

ckddls1321 opened this issue Mar 14, 2022 · 1 comment

Comments

@ckddls1321
Copy link

I'm very interested in training giant model.

Especially, trying to reproduce Swin-V2-G.

Does MS-Asia will have plan to release Swin-V2 codes?
Or could you guide me to how to impl Swin-V2-G novel sequential operation?

  1. Which way should I choose to re-impl Swin-V2-G novel sequential operation?
  • By activation checkpoint?
  • By custom autograd that enables FWD/BWD sequential operation?
@lapp0
Copy link

lapp0 commented Apr 21, 2022

Swin-V2 Giant has been implemented in timm huggingface/pytorch-image-models#1150

If you train a Swin-V2-G model, please submit a PR on the linked repo!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants