-
Notifications
You must be signed in to change notification settings - Fork 117
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
Converted to Keras Core: A Vision Transformer without Attention #497
Conversation
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). View this failed invocation of the CLA check for more information. For the most up to date status, view the checks section at the bottom of the pull request. |
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! Can you provide the git diff from the original example?
@@ -0,0 +1,880 @@ | |||
|
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.
Remove blank line
In this example, we minimally implement the paper with close alignement to the author's | ||
[official implementation](https://github.com/microsoft/SPACH/blob/main/models/shiftvit.py). | ||
|
||
|
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.
You can remove empty text lines at the end of text blocks
Here it is. |
Thanks! The number of epochs should be reverted to its original value. |
Done. |
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.
LGTM, thank you!
…s-team#497) * Port ShiftViT to keras core * remove empty spaces * Reverted epochs
Remove tensorflow_addons dependency
Fix imports
Update shape computation in
DropPath
toshape = (tf.shape(x)[0],) + (1,) * (len(x.shape) - 1)
Update loss computation metrics update in subclassed model
Linked Issue: keras-team/keras#18468