Implement 2D and 3D alpha_dropout #9073
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
tippisum
requested review from
apaszke,
colesbury,
ezyang,
gchanan,
soumith and
zdevito
as code owners
soumith
previously requested changes
Jul 1, 2018
Contributor
soumith
left a comment
soumith
left a comment
There was a problem hiding this comment.
please add tests in test_nn.py for the 2d and 3d variants.
Collaborator
Contributor
|
+1 for not going with |
Contributor
|
agree, let's not introduce |
Contributor
Author
|
Names are now corrected (existing droput*d names are untouched). Tests also seem OK. |
Contributor
facebook-github-bot
left a comment
facebook-github-bot
left a comment
There was a problem hiding this comment.
@ezyang has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.
ezyang
reviewed
Jul 14, 2018
torch/nn/_functions/dropout.py
Outdated
| b = ctx.noise | ||
| else: | ||
| ctx.noise.bernoulli_(1 - ctx.p) | ||
| a = ((3.09091329228798008 * ctx.p + 1) * (1 - ctx.p)) ** (-0.5) |
This comment was marked as off-topic.
This comment was marked as off-topic.
Sorry, something went wrong.
Contributor
|
math checks out |
Contributor
facebook-github-bot
left a comment
facebook-github-bot
left a comment
There was a problem hiding this comment.
@ezyang has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.
ezyang
approved these changes
Jul 17, 2018
jramseyer
pushed a commit
to jramseyer/pytorch
that referenced
this pull request
Jul 30, 2018
Summary: It implements per-channel alpha_dropout. It also creates corresponding function classes and unifies the process of dropout and alpha_dropout. Pull Request resolved: pytorch#9073 Differential Revision: D8727008 Pulled By: ezyang fbshipit-source-id: 9d509f9c5db4e98f7b698cdfc4443505a4d2b331
goodlux
pushed a commit
to goodlux/pytorch
that referenced
this pull request
Aug 15, 2018
Summary: It implements per-channel alpha_dropout. It also creates corresponding function classes and unifies the process of dropout and alpha_dropout. Pull Request resolved: pytorch#9073 Differential Revision: D8727008 Pulled By: ezyang fbshipit-source-id: 9d509f9c5db4e98f7b698cdfc4443505a4d2b331
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
6 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.
It implements per-channel alpha_dropout. It also creates corresponding function classes and unifies the process of dropout and alpha_dropout.