[Accuracy diff No.115] support softmax=False and weight != None && soft_label==True for cross_entropy #410
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
|
Thanks for your contribution! |
zrr1999
changed the title
cangtianhuang
requested changes
Jul 23, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.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.
weight 需要满足和为一。
softmax=False 时需要按照文档要求对输入手动进行softmax操作。
因为 torch tensor 自带了 softmax，所以只paddle的输入进行 softmax操作。
PyTorch 的对应 API 不支持使用 soft_label时添加weight，需要手动实现对齐 Paddle。