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.

Sign up for GitHub

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

Jump to bottom

Good work! How to get patch embedding of image？ #54

Open
cyysc1998 opened this issue Jul 23, 2024 · 1 comment
Open

Good work! How to get patch embedding of image？ #54

cyysc1998 opened this issue Jul 23, 2024 · 1 comment

Comments

@cyysc1998
Copy link

Excellent work! I want to know how to get image patch embedding, like output_hidden_states=True in CLIPVisionModelWithProjection. Thank you!
@SunzeY
Copy link
Owner

SunzeY commented Jul 24, 2024

We current haven't push the model to huggingface. so you need to modify model code of original openai CLIP, the demo of attn_map visualization may help you to also return image patch embedding.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@cyysc1998 @SunzeY