disable mixed precision in bn fusion & clone #93
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
|
@EikanWang Please help merge it. As we found it will decrease the rn50 top1 accuracy by 0.08%. |
Contributor
|
If we disable the BN, does it impact the perf? Because there are two reorder here. |
Contributor
Author
|
@EikanWang What do you mean by Two reorders |
Contributor
Author
|
@EikanWang I've also removed auto mixed precision in |
pinzhenx
changed the title
zhuhaozhe
pushed a commit
to zhuhaozhe/intel-extension-for-pytorch
that referenced
this pull request
Jun 24, 2020
* disable mixed precision in bn fusion * disable mixed precision in dil_clone
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Outdated suggestions cannot be applied.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.
Disable mix precision in model fusion, since mixed precision in fusion cannot bring any benefits for inference, but will lead to a little bit loss of accuracy, noticed by @jiayisunx