Package ai.djl.training.loss
package ai.djl.training.loss
-
ClassesClassDescription
ElasticWeightDecaycalculates L1+L2 penalty of a set of parameters.HingeLossis a type ofLoss.L1Losscalculates L1 loss between label and prediction.L1WeightDecaycalculates L1 penalty of a set of parameters.Calculates L2Loss between label and prediction, a.k.a.L2WeightDecaycalculates L2 penalty of a set of parameters.Loss functions (or Cost functions) are used to evaluate the model predictions against true labels for optimization.MaskedSoftmaxCrossEntropyLossis an implementation ofLossthat only considers a specific number of values for the loss computations, and masks the rest according to the given sequence.QuantileL1Losscalculates the Weighted Quantile Loss between labels and predictions.SigmoidBinaryCrossEntropyLossis a type ofLoss.SingleShotDetectionLossis an implementation ofLoss.SoftmaxCrossEntropyLossis a type ofLossthat calculates the softmax cross entropy loss.Calculates the loss for tabNet in Classification tasks.Calculates the loss of tabNet for regression tasks.YOLOv3Lossis an implementation ofLoss.The Builder to construct aYOLOv3Lossobject.