ENH Adds label_smoothing to cross entropy loss #63122
Closed
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
thomasjpfan
added
module: nn
🔗 Helpful links
💊 CI failures summary and remediationsAs of commit 1a41ce5 (more details on the Dr. CI page): 💚 💚 Looks good so far! There are no failures yet. 💚 💚 This comment was automatically generated by Dr. CI (expand for details).Follow this link to opt-out of these comments for your Pull Requests.Please report bugs/suggestions to the (internal) Dr. CI Users group. |
thomasjpfan
changed the title
thomasjpfan
commented
Aug 12, 2021
jbschlosser
reviewed
Aug 13, 2021
There was a problem hiding this comment.
Thanks for tackling this! Added some comments below. To summarize:
- I think we want the end result to handle both
ignore_indexand class prob targets - Can the implementation be simplified by doing label smoothing as additional math outside of the call to
at::nll_loss_ndand doing a linear combination?
thomasjpfan
requested review from
BowenBao,
neginraoof and
shubhambhokare1
as code owners
This was referenced Aug 17, 2021
|
@jbschlosser has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
datumbox
reviewed
Aug 26, 2021
|
@datumbox has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
jbschlosser
reviewed
Aug 27, 2021
|
@datumbox has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
|
@jbschlosser has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
Codecov Report
@@ Coverage Diff @@
## master #63122 +/- ##
=======================================
Coverage 66.73% 66.74%
=======================================
Files 698 698
Lines 90892 90922 +30
=======================================
+ Hits 60661 60690 +29
- Misses 30231 30232 +1 |
|
@jbschlosser merged this pull request in d3bcba5. |
jbschlosser
added a commit
to jbschlosser/nestedtensor
that referenced
this pull request
Sep 2, 2021
Summary: Adds awareness of the new `label_smoothing` functionality in `cross_entropy` added in pytorch/pytorch#63122 to nestedtensor's implementation. Fixes broken test: `test.test_nested_tensor_functional.TestFunctional`. Differential Revision: D30730728 fbshipit-source-id: 34d907b76a1d2058cc7bc7d12c271cc3088a351b
facebook-github-bot
pushed a commit
to pytorch/nestedtensor
that referenced
this pull request
Sep 2, 2021
Summary: Pull Request resolved: #452 Adds awareness of the new `label_smoothing` functionality in `cross_entropy` added in pytorch/pytorch#63122 to nestedtensor's implementation. Fixes broken test: `test.test_nested_tensor_functional.TestFunctional`. Reviewed By: cpuhrsch Differential Revision: D30730728 fbshipit-source-id: 04f146d6de7f764f165059e4b5654d7f39142e38
16 tasks
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Fixes #7455
Partially resolves pytorch/vision#4281
cc @albanD @mruberry @jbschlosser