Package ai.djl.training.loss

Class L1Loss

java.lang.Object

ai.djl.training.evaluator.Evaluator

ai.djl.training.loss.Loss

ai.djl.training.loss.L1Loss

public class L1Loss
extends Loss

L1Loss calculates L1 loss between label and prediction.

L1 loss is defined by \(L = \sum_i \vert {label}_i - {prediction}_i \vert\).

Field Summary

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

totalInstances

Constructor Summary

Constructors

Constructor	Description
L1Loss()	Calculates L1 Loss between the label and prediction, a.k.a.
L1Loss(java.lang.String name)	Calculates L1 Loss between the label and prediction, a.k.a.
L1Loss(java.lang.String name, float weight)	Calculates L1 Loss between the label and prediction, a.k.a.

Method Summary

Modifier and Type	Method	Description
NDArray	evaluate(NDList label, NDList prediction)	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

L1Loss

public L1Loss()

Calculates L1 Loss between the label and prediction, a.k.a. MAE(Mean Absolute Error).

L1Loss

public L1Loss(java.lang.String name)

Calculates L1 Loss between the label and prediction, a.k.a. MAE(Mean Absolute Error).

Parameters:

name - the name of the loss

L1Loss

public L1Loss(java.lang.String name,
              float weight)

Calculates L1 Loss between the label and prediction, a.k.a. MAE(Mean Absolute Error).

Parameters:

name - the name of the loss

weight - the weight to apply on loss value, default 1

Method Detail

evaluate

public NDArray evaluate(NDList label,
                        NDList prediction)

Calculates the evaluation between the labels and the predictions.

Specified by:

evaluate in class Evaluator

Parameters:

label - the correct values

prediction - the predicted values

Returns:

the evaluation result