Fix in documentation of convolutional modules#30079
Closed
davda54 wants to merge 3 commits intopytorch:masterfrom
davda54:master
Closed
Fix in documentation of convolutional modules#30079davda54 wants to merge 3 commits intopytorch:masterfrom davda54:master
davda54 wants to merge 3 commits intopytorch:masterfrom
davda54:master
Conversation
Initialization of transposed convolutions is dependent on `out_channels` not `in_channels`.
The initialization is actually influenced by the number of groups, too.
ezyang
approved these changes
Feb 3, 2020
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
BowenBao
pushed a commit
to BowenBao/pytorch
that referenced
this pull request
Feb 12, 2020
Summary: I noticed the description of the initialization of convolutional modules is inconsistent with the actual implementation. There are two such cases: 1) `k` in the initialization of ConvTranspose modules is not dependent on the input channels but on the output channels (`kaiming_uniform_` uses the size of the second dimension of `weight` which is transposed in the first two dimensions). 2) Both the normal convolutions and the transposed ones use `k` divided by `groups`. Pull Request resolved: pytorch#30079 Differential Revision: D19698511 Pulled By: ezyang fbshipit-source-id: 1ba938fbbd97663eaf29fd1245872179d2761fff
ttumiel
pushed a commit
to ttumiel/pytorch
that referenced
this pull request
Mar 4, 2020
Summary: I noticed the description of the initialization of convolutional modules is inconsistent with the actual implementation. There are two such cases: 1) `k` in the initialization of ConvTranspose modules is not dependent on the input channels but on the output channels (`kaiming_uniform_` uses the size of the second dimension of `weight` which is transposed in the first two dimensions). 2) Both the normal convolutions and the transposed ones use `k` divided by `groups`. Pull Request resolved: pytorch#30079 Differential Revision: D19698511 Pulled By: ezyang fbshipit-source-id: 1ba938fbbd97663eaf29fd1245872179d2761fff
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
5 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.
I noticed the description of the initialization of convolutional modules is inconsistent with the actual implementation. There are two such cases:
kin the initialization of ConvTranspose modules is not dependent on the input channels but on the output channels (kaiming_uniform_uses the size of the second dimension ofweightwhich is transposed in the first two dimensions).Both the normal convolutions and the transposed ones use
kdivided bygroups.