Join GitHub today
GitHub is home to over 40 million developers working together to host and review code, manage projects, and build software together.Sign up
FIX switch to binary_crossentropy if a binary problem #14869
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.