[MRG] Fix mdd loss #277
Merged
[MRG] Fix mdd loss #277
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
|
It seems nice, but why adding the new arguments domain_criterion_t and domain_criterion_s? I feel it adds too much complexity. Maybe we can say that the original MDD paper only focus on multi classification, and we do the same here. We can almost remove the domain_criterion argument and hardset it to be crossentropy for source and custom crossentropy for target. We can let to future PRs the generalization of MDD to other losses? |
|
I agree, I change this |
|
Ok, I just have one comment, but the rest is ok for me. |
tomMoral
reviewed
Nov 18, 2024
| """Compute the modified CrossEntropyLoss""" | ||
| prob = F.softmax(input, dim=-1) | ||
| prob = prob[..., target] | ||
| log_one_minus_prob = torch.log(1 - prob) |
There was a problem hiding this comment.
Maybe use this one: https://pytorch.org/docs/stable/generated/torch.log1p.html
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Outdated suggestions cannot be applied.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.
Use equations (26)-(29) from https://arxiv.org/pdf/1904.05801