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

Train ViT-g/14 on Imagenet-1k from scratch #480

Open
QAQdev opened this issue Nov 9, 2024 · 0 comments
Open

Train ViT-g/14 on Imagenet-1k from scratch #480

QAQdev opened this issue Nov 9, 2024 · 0 comments

Comments

@QAQdev
Copy link

QAQdev commented Nov 9, 2024

Did anyone try to train ViT-g/14 on Imagenet-1k from scratch? I conformed to vitg14_pretrain.yaml but trained for 100 epochs.

I got even lower linear acc (70+%) than ViT-l/14 on Imagenet-1k from scratch, which is 82% in readme.

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

1 participant