This repository has been archived by the owner on Nov 3, 2022. It is now read-only.
Jaccard Loss Updated #533
Open
Jaccard Loss Updated #533
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
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
#526
- What I did
Fixed the issue referenced, which concerns implementation of Jaccard Loss function.
- How I did it
I changed the axis argument of summation terms from only channels to all except channels, which is the correct way according to what I have studied. Consequently, this returns a per-channel loss vector for each sample.
- How you can verify it
The functionality and correctness demands (other than theoretical reasoning) verification by training via this loss function. I have used this as well as dice loss (also arranged in a similar configuration) for multiple training sessions which yield good performance.
This pull request fixes Issue #526 opened by me