This repository has been archived by the owner on Jul 7, 2023. It is now read-only.
Loss twice multiplied with loss_coef #1627
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
In the case of topk gating, the loss is falsely multiplied twice by the loss coefficient.
lukaszkaiser
approved these changes
Jul 18, 2019
tensorflow-copybara
pushed a commit
that referenced
this pull request
Jul 18, 2019
PiperOrigin-RevId: 258823663
# for free
to subscribe to this conversation on GitHub.
Already have an account?
#.
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Outdated suggestions cannot be applied.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.
In the case of topk gating, the loss is falsely multiplied twice by the loss coefficient.