Fix the padding issue of quantized average pool operator #28260
Closed
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
|
I think it is ready to go. Can you stamp it? @supriyar @raghuramank100 |
Contributor
facebook-github-bot
left a comment
facebook-github-bot
left a comment
There was a problem hiding this comment.
@lly-zero-one has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.
supriyar
reviewed
Oct 21, 2019
supriyar
approved these changes
Oct 21, 2019
Contributor
supriyar
left a comment
supriyar
left a comment
There was a problem hiding this comment.
Please address comment. Otherwise looks good!
Contributor
facebook-github-bot
left a comment
facebook-github-bot
left a comment
There was a problem hiding this comment.
@lly-zero-one is landing this pull request. If you are a Facebook employee, you can view this diff on Phabricator.
zdevito
pushed a commit
to zdevito/ATen
that referenced
this pull request
Oct 21, 2019
Summary: This is actually a bug in both testing and the average pool implementation. In testing, we used the quantized value as float input and failed to padding the value with zero_point. In op implementation, the size for averaging is not correct for padding case when count_include_pad is true. Pull Request resolved: pytorch/pytorch#28260 Differential Revision: D18039960 Pulled By: lly-zero-one fbshipit-source-id: 7b5d34498b60f5d574a276a22798c9f576944734
Contributor
|
@lly-zero-one merged this pull request in 4d9c017. |
thiagocrepaldi
pushed a commit
to thiagocrepaldi/pytorch
that referenced
this pull request
Feb 4, 2020
Summary: This is actually a bug in both testing and the average pool implementation. In testing, we used the quantized value as float input and failed to padding the value with zero_point. In op implementation, the size for averaging is not correct for padding case when count_include_pad is true. Pull Request resolved: pytorch#28260 Differential Revision: D18039960 Pulled By: lly-zero-one fbshipit-source-id: 7b5d34498b60f5d574a276a22798c9f576944734
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 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.
This is actually a bug in both testing and the average pool implementation.
In testing, we used the quantized value as float input and failed to padding the value with zero_point.
In op implementation, the size for averaging is not correct for padding case when count_include_pad is true.