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

About pre-training data #62

Open
ycsun1972 opened this issue Jun 5, 2022 · 2 comments
Open

About pre-training data #62

ycsun1972 opened this issue Jun 5, 2022 · 2 comments

Comments

@ycsun1972
Copy link

Hi, thanks for sharing your cool work!

Could you please provide the original captions and the Filtered web caption by ViT-L?

Thanks

@LiJunnan1992
Copy link
Contributor

Hi, the pre-training captions are already provided. Please refer to the "Pre-training datasets download" section.

@ycsun1972
Copy link
Author

ycsun1972 commented Jun 7, 2022

Hi, thanks for your reply.

Sorry I didn't express myself clearly.

What I’d like to ask is, did you use ViT-L to filter the original web captions? I only find the filtered synthetic caption by ViT-L.

Could you also provide the original web captions, without filtering?

Thanks.

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