Call LossLayer::LayerSetUp in SmoothL1LossLayer.
#8
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
This gives the layer a loss_weight of 1 if no loss_weight is explicitly specified (previously it was defaulting to 0).
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Outdated suggestions cannot be applied.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.
If
SmoothL1LossLayerdoesn't have aloss_weightexplicitly set, then it currently defaults to 0:In particular, note the first line, in which the loss is 0 even though the output is nonzero.
This PR is a 1-line change that calls the parent
LayerSetUpmethod, which does the work of setting the defaultloss_weightto 1.(On a somewhat related note, in the py-faster-rcnn repository it seems to be the case that
loss_weightis always explicitly set, so this bug was never an issue there.)