Package ai.djl.training.loss
package ai.djl.training.loss
-
ClassesClassDescription
ElasticWeightDecay
calculates L1+L2 penalty of a set of parameters.HingeLoss
is a type ofLoss
.L1Loss
calculates L1 loss between label and prediction.L1WeightDecay
calculates L1 penalty of a set of parameters.Calculates L2Loss between label and prediction, a.k.a.L2WeightDecay
calculates L2 penalty of a set of parameters.Loss functions (or Cost functions) are used to evaluate the model predictions against true labels for optimization.MaskedSoftmaxCrossEntropyLoss
is an implementation ofLoss
that only considers a specific number of values for the loss computations, and masks the rest according to the given sequence.QuantileL1Loss
calculates the Weighted Quantile Loss between labels and predictions.SigmoidBinaryCrossEntropyLoss
is a type ofLoss
.SingleShotDetectionLoss
is an implementation ofLoss
.SoftmaxCrossEntropyLoss
is a type ofLoss
that calculates the softmax cross entropy loss.Calculates the loss for tabNet in Classification tasks.Calculates the loss of tabNet for regression tasks.YOLOv3Loss
is an implementation ofLoss
.The Builder to construct aYOLOv3Loss
object.