Support for Unflatten operation requred by Attention layer
#25851
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
dkurt
reviewed
Jul 2, 2024
| if (range.start < 0) | ||
| { | ||
| range.start += n; | ||
| if (!(range.start == n)){ |
Member
There was a problem hiding this comment.
If range.start == n doe it mean uninitialized value?
Contributor
Author
There was a problem hiding this comment.
no, it means that start index is equal to the last dimention of the input, in which case we do not want it to be (n-1)
Contributor
|
@Abdurrahheem Should it be back-ported to 4.x too? |
Contributor
|
Replaced by #25861 |
Merged
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Pull Request Readiness Checklist
All test data and models for PR are located #1188
This PR fixes issue reised when importing batched vanilla
Attentionlayer fromPyTorchvia ONNX. Currently batched version ofAttentionlayer in PyTorch has unflatten operation inside.unflattenoperation causes issue inreshapelayer (see the Reshape_2 in the graph below) due to incorrect output ofslicelayer. This PR particularly fixessliceandconcatlayers to handleunflattenoperation.See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
Patch to opencv_extra has the same branch name.