Is symmetric_cross_entropy suitable for binary classification issue?

YisenWang / symmetric_cross_entropy_for_noisy_labels

Code for ICCV2019 "Symmetric Cross Entropy for Robust Learning with Noisy Labels"

https://arxiv.org/abs/1908.06112

171 stars 32 forks source link

Is symmetric_cross_entropy suitable for binary classification issue? #4

Closed useric closed 4 years ago

useric commented 4 years ago

Is symmetric_cross_entropy suitable for binary classification issue? If so, someone can give some hints to modify the symmetric_cross_entropy function?

YisenWang commented 4 years ago

symmetric_cross_entropy is definitely suitable for binary case where the one-hot label is [0,1] or [1,0].