[relay][qnn]: Fix qnn.avg_pool2d layout inference #17339
Merged
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
Contributor
Author
|
@masahi @kparzysz-quic @quic-sanirudh PTAL, thanks |
Contributor
|
Thanks @f2013519 for the fix ! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.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.
Issue:
Currently the qnn.avg_pool2d operator does not take the layout specified with the Convert Layout pass.
Cause:
The layout of the zero point and scale tensors are specified as "undefined". This causes the Convert Layout pass to bail and maintain the original layout.
Fix:
The fix updates the layouts for the scale and zero point tensors to be "channel" layout, similar to how it is done for qnn.conv2d.
Testing:
Added unit test