Needing clarity for equivalent of Categoricalcrossentropy as CrossEntropyLoss

[mMagmer]

it seems that only crossentorpy in version 1.10 can get Probabilities for each class as target.

Soft Cross Entropy Loss (TF has it does Pytorch have it)

As of the current stable version, pytorch 1.10.0, “soft” cross-entropy labels are now supported. See: CrossEntropyLoss – 1.1010. Best. K. Frank