Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Catch cases in MultiLabelLoss where label array is all 0/1 #6880

Closed
treo opened this issue Dec 17, 2018 · 1 comment

Comments

@treo
Copy link

commented Dec 17, 2018

The loss function requires that the label array defines two sets: The in set (1) and the out set (0). If it is all 0 or all 1, then it runs into NaNs.

@treo treo added the Bug label Dec 17, 2018

@treo treo self-assigned this Dec 17, 2018

treo added a commit that referenced this issue Dec 18, 2018
AlexDBlack added a commit that referenced this issue Dec 18, 2018
printomi added a commit to printomi/deeplearning4j that referenced this issue Jan 7, 2019
@lock

This comment has been minimized.

Copy link

commented Jan 17, 2019

This thread has been automatically locked since there has not been any recent activity after it was closed. Please open a new issue for related bugs.

@lock lock bot locked and limited conversation to collaborators Jan 17, 2019

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Projects
None yet
1 participant
You can’t perform that action at this time.