make loss cond. on label while using Stirling approximation #56992
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
|
你的PR提交成功，感谢你对开源项目的贡献! |
|
@LyndonKong Could you help review this PR? |
|
LGTM |
luotao1
approved these changes
Sep 6, 2023
|
Thank you @luotao1 and @LyndonKong for sticking me with this one even though I made a lot of mistakes . Your support and guidance was invaluable ! |
BeingGod
pushed a commit
to BeingGod/Paddle
that referenced
this pull request
Sep 9, 2023
akshatvishu
added a commit
to akshatvishu/ivy
that referenced
this pull request
Sep 13, 2023
…le issue Refined the `poisson_nll_loss` composition function to address discrepancies with the native PaddlePaddle method. This refinement ensures accuracy and is to be replaced once PaddlePaddle promotes the changes from the develop branch to a stable release. Related to PR in PaddlePaddle: PaddlePaddle/Paddle#56992
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Outdated suggestions cannot be applied.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.
PR types
Others
PR changes
Others
Description
This commit updates the condition for adding the Stirling approximation term in Poisson NLL Loss to align with how PyTorch and TensorFlow handle it. The condition is changed from 'label <= 1' to 'label > 1' for adding the Stirling term, making the behavior consistent across frameworks.