Implemented CORN loss for ordinal classification #3375
Merged
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
arnavgarg1
reviewed
May 1, 2023
arnavgarg1
reviewed
May 1, 2023
Comment on lines
12
to
25
| def coral_loss(logits, levels, importance_weights=None, reduction="mean"): | ||
| """Computes the CORAL loss described in. | ||
|
|
||
| Cao, Mirjalili, and Raschka (2020) | ||
| *Rank Consistent Ordinal Regression for Neural Networks | ||
| with Application to Age Estimation* | ||
| Pattern Recognition Letters, https://doi.org/10.1016/j.patrec.2020.11.008 | ||
|
|
||
| Parameters | ||
| ---------- | ||
| logits : torch.tensor, shape(num_examples, num_classes-1) | ||
| Outputs of the CORAL layer. | ||
|
|
||
| levels : torch.tensor, shape(num_examples, num_classes-1) |
There was a problem hiding this comment.
Is it also worth adding a CoralLoss Config?
There was a problem hiding this comment.
Maybe, removed for now as not sure where it would make sense to use it.
arnavgarg1
approved these changes
May 2, 2023
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Outdated suggestions cannot be applied.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.
See: https://github.com/Raschka-research-group/coral-pytorch
When using the CORN loss, the vocab needs to be explicitly provided to ensure that the ordering of the categories is properly honored:
We chose to replicate the code here with attribution rather than add an additional dependency due to the self-contained nature of the implementation to just a couple torch-only functions.