Fix bug in grad.py when conv bias != None#12281
Closed
daquexian wants to merge 1 commit intopytorch:masterfrom
Closed
Fix bug in grad.py when conv bias != None#12281daquexian wants to merge 1 commit intopytorch:masterfrom
daquexian wants to merge 1 commit intopytorch:masterfrom
Conversation
ezyang
approved these changes
Oct 5, 2018
Contributor
|
Thank you, nice catch. This is technically BC-breaking but I doubt anyone will notice. |
Contributor
facebook-github-bot
left a comment
There was a problem hiding this comment.
ezyang is landing this pull request. If you are a Facebook employee, you can view this diff on Phabricator.
Contributor
Author
|
@ezyang Thanks! I agree that maybe no one will notice :D |
|
I noticed but wasn't sure enough about its being incorrect to say something. I appreciate the fix! Thank you! |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Obviously, the grads of conv weight and conv input are not relevant to the bias, but the original
convXd_inputandconvXd_weightmethods receive abiasparameter. What's more, while the doc saysbiasshould have the shape(out_channels,), one will get aRuntimeErrorif the bias != None and in_channels != out_channels, for the weight of transposed conv has the shape(in_channels, out_channels, kH, kW)while the weight of vanilla conv has the shape(out_channels, in_channels, kH, kW)