-
Notifications
You must be signed in to change notification settings - Fork 2.1k
Add: A minimal implementation of ShiftViT #811
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
Conversation
fchollet
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks for the PR! 👍
Please format the code using black.
|
Thank you for the review @fchollet We have made the necessary changes! |
fchollet
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks for the updates! I pushed some copyedits.
|
@fchollet I have made changes as requested! |
|
Thanks for the thorough review @fchollet We have added the generated files after some minor edits (removing spaces and adding a period to the description). Note: The code was more than 300 lines, so we modified the |
fchollet
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Awesome -- thank you for the great contribution! 👍
As much as possible, this should be avoided, but it's not a blocker. |
This is a minimal implementation of ShiftViT. In this paper the authors have proposed to replace the attention module of a ViT with a NO PARAMETER shifting operation. In this example we have tried aligning the implementation as closely as we could with the official implementation in PyTorch. We hope this will benefit the keras community.
Colab Notebook
CC: @ritwikraha