This repository was archived by the owner on Aug 6, 2025. It is now read-only.
Add loss functions #199
Merged
Add loss functions #199
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
facebook-github-bot
added
the
CLA Signed
mmuckley
force-pushed
the
mmuckley/div2k_openimages
branch
from
10263c8 to
c9adf58
Compare
mmuckley
force-pushed
the
mmuckley/loss_fns
branch
from
3578b0d to
4c584a1
Compare
mmuckley
force-pushed
the
mmuckley/div2k_openimages
branch
from
c9adf58 to
ee2efc6
Compare
mmuckley
force-pushed
the
mmuckley/loss_fns
branch
from
4c584a1 to
ac9fa1a
Compare
lauragustafson
approved these changes
Jul 18, 2023
mmuckley
force-pushed
the
mmuckley/loss_fns
branch
from
ac9fa1a to
c860050
Compare
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Outdated suggestions cannot be applied.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.
This PR includes a suite of loss function refactors. Loss functions for training models are pulled out of the
metricssubmodule and into the newloss_fnsubmodule. This provides a more clear delineation of intended purpose. It also allows separate implementations, which is useful for LPIPS, where we need divide-by-0 protection for the loss, but not for the metric.Tests are included for all metrics. The normalized LPIPS loss is tested implicitly with the MSE-LPIPS loss.
Losses include: