Support Global_Pool_2D ops in .tflite model #25613
Merged
+53
−0
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
May 21, 2024
dkurt
reviewed
May 21, 2024
Contributor
Author
|
Thank you for your comment. However, I'm not sure which case you're concerned about. Could you please provide your expected model architecture for me to verify the correctness. |
Member
|
@CNOCycle, never mind. I misunderstood the fact that Flatten goes after Pooling, not before. I added minor changes to the code to make it look more unified with other layers. LGTM after tests pass. |
dkurt
approved these changes
May 31, 2024
dkurt
approved these changes
May 31, 2024
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Outdated suggestions cannot be applied.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
Merge with extra: opencv/opencv_extra#1180
This PR adds support for
GlobalAveragePooling2DandGlobalMaxPool2Don the TFlite backend. When the keep_dimsoption is enabled, the output is a 2D tensor, necessitating the inclusion of an additional flatten layer. Additionally, the names of these layers have been updated to match the output tensor names generated bygenerate.pyfrom the opencv_extra repository.Patch to opencv_extra has the same branch name.