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

Interpolate pos encode for altclip #30635

Closed

Conversation

bhuvanmdev
Copy link
Contributor

What does this PR do?

Adds interpolate_pos_encode and a test case for the said feature for the model altclip.

Fixes #30579 (altclip)

Who can review?

@amyeroberts

@bhuvanmdev
Copy link
Contributor Author

This is my first open-source contribution, so any type of suggestions are appreciated :)

@amyeroberts
Copy link
Collaborator

Hi @bhuvanmdev, thanks for working on this!

I must apologies for the making the issue clear when I first created it. Models which are linked through # Copied from statements should be modified together i.e. CLIP should changed and then realted models like altclip included in this change.

As there's other PRs open to add this feature to CLIP, those will take precedence over this PR. Apologies for the time that you've already spent adding it to this model.

@bhuvanmdev
Copy link
Contributor Author

I did get to understand the architecture behind CLIP like models a bit better :), so it was'nt a waste of time.
Then in that case, should I just close this PR?

@amyeroberts
Copy link
Collaborator

Then in that case, should I just close this PR?

Yes, let's close this PR. Thanks again for working on this and contributing to improving the library

@bhuvanmdev bhuvanmdev closed this May 8, 2024
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

Successfully merging this pull request may close these issues.

Community contribution: enable dynamic resolution input for more vision models.
2 participants