`loss`¶

Gluon provides pre-defined loss functions in the mxnet.gluon.parameter module.

losses for training neural networks

`Loss`(weight, batch_axis, **kwargs)	Base class for loss.
`L2Loss`([weight, batch_axis])	Calculates the mean squared error between pred and label.
`L1Loss`([weight, batch_axis])	Calculates the mean absolute error between pred and label.
`SigmoidBinaryCrossEntropyLoss`([…])	The cross-entropy loss for binary classification.
`SoftmaxCrossEntropyLoss`([axis, …])	Computes the softmax cross entropy loss.
`KLDivLoss`([from_logits, axis, weight, …])	The Kullback-Leibler divergence loss.
`HuberLoss`([rho, weight, batch_axis])	Calculates smoothed L1 loss that is equal to L1 loss if absolute error exceeds rho but is equal to L2 loss otherwise.
`HingeLoss`([margin, weight, batch_axis])	Calculates the hinge loss function often used in SVMs:
`SquaredHingeLoss`([margin, weight, batch_axis])	Calculates the soft-margin loss function used in SVMs:
`LogisticLoss`([weight, batch_axis, label_format])	Calculates the logistic loss (for binary losses only):
`TripletLoss`([margin, weight, batch_axis])	Calculates triplet loss given three input tensors and a positive margin.
`CTCLoss`([layout, label_layout, weight])	Connectionist Temporal Classification Loss.

loss¶