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

force_image_size does not work for eva models #783

Open
yxchng opened this issue Jan 6, 2024 · 3 comments
Open

force_image_size does not work for eva models #783

yxchng opened this issue Jan 6, 2024 · 3 comments
Labels
enhancement New feature or request

Comments

@yxchng
Copy link

yxchng commented Jan 6, 2024

setting force_image_size to 672 still give model with default 336 input size

@rwightman
Copy link
Collaborator

I never got around to hooking that up to timm based models. It's possible, but requires a bit of extra code to handle the resizing properly....

@rwightman rwightman added the enhancement New feature or request label Jan 8, 2024
@yxchng
Copy link
Author

yxchng commented Jul 12, 2024

@rwightman any update on this?

@rwightman
Copy link
Collaborator

rwightman commented Jul 12, 2024

@yxchng I actually do have some work in progress right now in timm to address huggingface/pytorch-image-models#2190 (adding a set_input_size()) fn to vit, that would allow this to work, I don't think I can rely on the @ pretrained load resize that's already there for timm weights

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

No branches or pull requests

2 participants