Package ai.djl.training.loss

Contains classes for measuring the Loss of a model.

See: Description

Class Summary

Class	Description
CompositeLoss	CompositeLoss is an implementation of the Loss abstract class that can combine different Loss functions by adding the individual losses together.
HingeLoss	HingeLoss is a type of Loss.
L1Loss	L1Loss calculates L1 loss between label and prediction.
L2Loss	Calculates L2Loss between label and prediction, a.k.a.
Loss	Loss functions or Cost Functions to evaluate model predictions against true labels.
SigmoidBinaryCrossEntropyLoss	SigmoidBinaryCrossEntropyLoss is a type of Loss.
SingleShotDetectionLoss	SingleShotDetectionLoss is an implementation of Loss.
SoftmaxCrossEntropyLoss	SoftmaxCrossEntropyLoss is a type of Loss that calculates the softmax cross entropy loss.

Package ai.djl.training.loss Description

Contains classes for measuring the Loss of a model.

It contains a main interface Loss and various losses that extend it.