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
FIX switch to binary_crossentropy if a binary problem #14869
Conversation
Thanks for the PR. If the user specifies categorical_crossentropy on a binary classif problem, I think we should either:
I'm in favor of just raising an error (because we have the 'auto' option that just works). But I'm OK with option 2 as well. The current proposal is re-implementing the 'auto' logic but with a warning so I don't think we want that. |
@ogrisel maybe you could have a look? |
ping @ogrisel or @glemaitre should be an easy one :) |
I pushed the fix and will merge when it is green |
Fixes #14858.
Raise a warning and switch to
binary_crossentropy
if it's a binary classification problem andcategorical_crossentropy
is given.