Loss to be used with
In the training phase, computes individual losses with regard to two targets, weights them item-wise, and averages the linear combinations to yield the mean batch loss. For validation and testing, defers to the passed-in loss.
the underlying loss
nn_moduleto call. It must support the
reductionfield. During training the attribute will be changed to
'none'so we get the loss for individual observations. See for for example documentation for the
It should be used together with