Module loss

Structs

BCEWithLogitsLoss

This loss combines a Sigmoid layer and the BCELoss in one single class. This version is more numerically stable than using a plain Sigmoid followed by a BCELoss as, by combining the operations into one layer, we take advantage of the log-sum-exp trick for numerical stability.

CrossEntropyLoss

CrossEntropyLoss

MSELoss

MSELoss The left-most dimension is the N.

Enums

Reduction