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

If the weights of vit-base trained with dropout available? #277

Open
Cascol-Chen opened this issue Jul 22, 2023 · 1 comment
Open

If the weights of vit-base trained with dropout available? #277

Cascol-Chen opened this issue Jul 22, 2023 · 1 comment

Comments

@Cascol-Chen
Copy link

Thank you for your great work and codes.

I see that vit-base can be trained with or without dropout but currently most available checkpoints are trained without dropout. I wonder if those trained with dropout could be available.

@andsteing
Copy link
Collaborator

There are various checkpoints with and without dropout available from the paper How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers. See the following Colab to select different checkpoints:

https://colab.sandbox.google.com/github/google-research/vision_transformer/blob/main/vit_jax_augreg.ipynb

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