Fix the bug of incorrect gradient when loss_weight set to zero#3868
Closed
Cysu wants to merge 4 commits intoBVLC:masterfrom
Closed
Fix the bug of incorrect gradient when loss_weight set to zero#3868Cysu wants to merge 4 commits intoBVLC:masterfrom
Cysu wants to merge 4 commits intoBVLC:masterfrom
Conversation
Member
|
thanks! |
|
Hope this bug could be solved soon |
|
Does any other loss functions meets the same bug when the loss_weight is setted to be zero? |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 aims at fixing the bug raised in #2895.
A flag (diff_written_) is added to the Blob class to indicate whether its diff has been used. When BP, clear the bottom diffs (if necessary) of the layers that do not propagate down. The computation and memory overhead are negligible.