Fix to issue #25537 #27546
Merged
Fix to issue #25537 #27546
Conversation
This file contains 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
test=develop
|
Thanks for your contribution! |
|
✅ This PR's description meets the template requirements! |
Closed
test=develop
|
@arogowie-intel , @arlesniak Please review |
|
@wojtuss , @wozna , @arlesniak , @arogowie-intel Please review @luotao1 PR-CI-Windows is in mending mode since yesterday. I tried to close/reopen PR but no impact visible. Could you please advice how to proceed? |
luotao1
approved these changes
Oct 1, 2020
|
@luotao1 Thanks very much for explanation |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
PR types
Bug fixes
PR changes
Others
Describe
fix #25537.
Fix a misuse of Tensor::layout for purpose of oneDNN NHWC arrangment implementation and It does adjust transpose oneDNN kernel for NHWC arrangmeent. Tranpose kernel has to be modified as this is oneDNN kernel , but it does produce non-oneDNN tensor , so output shape for NHWC model has to be matched.