MultiLabelClassificationTask use sigmoid instead of softmax #791
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
isaaccorley
force-pushed
the
trainers/multilabel-classifier-sigmoid-fix
branch
from
a4d4dd3
to
bf6343c
Compare
isaaccorley
force-pushed
the
trainers/multilabel-classifier-sigmoid-fix
branch
from
bf6343c
to
71b1025
Compare
calebrob6
approved these changes
Sep 30, 2022
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Outdated suggestions cannot be applied.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.
MultiLabelClassificationTaskwas usingtorch.softmaxon the outputs prior to computing metrics, however we should usetorch.sigmoidinstead since each output logit is indepedent of others in the multilabel case.