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

Support for last layer self-attention visualisation on ViT #2220

Closed
wants to merge 2 commits into from
Closed

Support for last layer self-attention visualisation on ViT #2220

wants to merge 2 commits into from

Conversation

K-bNd
Copy link

@K-bNd K-bNd commented Jul 1, 2024

Added access to the last attention layer output for ViT, similar to DINO and DINOv2.

facebookresearch/dinov2#306

@K-bNd K-bNd mentioned this pull request Jul 1, 2024
Open
@rwightman
Copy link
Collaborator

@K-bNd I don't plan to plumb that path through for visualization, risks of too many issues, complexities etc, for viz the recommended approach is via FX or hooks #1232

@rwightman rwightman closed this Jul 2, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@K-bNd @rwightman