Package ai.djl.training.loss

Class IndexLoss

java.lang.Object

ai.djl.training.evaluator.Evaluator

ai.djl.training.loss.Loss

ai.djl.training.loss.IndexLoss

public class IndexLoss
extends Loss

A wrapper for a Loss that evaluates on only a particular NDArray in the predictions and/or labels NDLists.

Field Summary

Fields inherited from class ai.djl.training.evaluator.Evaluator

totalInstances

Constructor Summary

Constructors

Constructor	Description
IndexLoss(Loss loss, int index)	Constructs an IndexLoss with the same index for both predictions and labels.
IndexLoss(Loss loss, java.lang.Integer predictionsIndex, java.lang.Integer labelsIndex)	Constructs an IndexLoss.

Method Summary

Modifier and Type	Method	Description
NDArray	evaluate(NDList labels, NDList predictions)	Calculates the evaluation between the labels and the predictions.

Methods inherited from class ai.djl.training.loss.Loss

addAccumulator, elasticNetWeightedDecay, elasticNetWeightedDecay, elasticNetWeightedDecay, elasticNetWeightedDecay, getAccumulator, hingeLoss, hingeLoss, hingeLoss, l1Loss, l1Loss, l1Loss, l1WeightedDecay, l1WeightedDecay, l1WeightedDecay, l2Loss, l2Loss, l2Loss, l2WeightedDecay, l2WeightedDecay, l2WeightedDecay, maskedSoftmaxCrossEntropyLoss, maskedSoftmaxCrossEntropyLoss, maskedSoftmaxCrossEntropyLoss, resetAccumulator, sigmoidBinaryCrossEntropyLoss, sigmoidBinaryCrossEntropyLoss, sigmoidBinaryCrossEntropyLoss, softmaxCrossEntropyLoss, softmaxCrossEntropyLoss, softmaxCrossEntropyLoss, updateAccumulator

Methods inherited from class ai.djl.training.evaluator.Evaluator

checkLabelShapes, checkLabelShapes, getName

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

IndexLoss

public IndexLoss(Loss loss,
                 int index)

Constructs an IndexLoss with the same index for both predictions and labels.

Parameters:

loss - the base evaluator

index - the index for both predictions and labels

IndexLoss

public IndexLoss(Loss loss,
                 java.lang.Integer predictionsIndex,
                 java.lang.Integer labelsIndex)

Constructs an IndexLoss.

Parameters:

loss - the base evaluator

predictionsIndex - the predictions index

labelsIndex - the labels index

Method Detail

evaluate

public NDArray evaluate(NDList labels,
                        NDList predictions)

Calculates the evaluation between the labels and the predictions.

Specified by:

evaluate in class Evaluator

Parameters:

labels - the correct values

predictions - the predicted values

Returns:

the evaluation result