This repository has been archived by the owner on Nov 17, 2023. It is now read-only.
fix normalize mean error bug #15539
Merged
fix normalize mean error bug #15539
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
ChaiBapchya
suggested changes
Jul 15, 2019
|
@mxnet-label-bot add [Operator, pr-awaiting-response] |
marcoabreu
added
Operator
pr-awaiting-response
@ChaiBapchya We are upgrading MXNet from 1.3 to 1.5 in our deployment env these days and notice some accuracy drop of our models. This bug seems to exist for at least a few months. Maybe we should add more tests to avoid similar bugs in the future. |
|
Hi @nicklhy , could you please add an unittest in Thank you! |
|
@nicklhy Great work! Thank you so much! |
wkcn
added
pr-awaiting-merge
anirudhacharya
pushed a commit
to anirudhacharya/mxnet
that referenced
this pull request
Aug 20, 2019
* fix normalize mean error bug * add scalar mean/std tests for image_normalize
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
The normalize operator may produce wrong result when setting the mean arg with a single float val.