ai.djl.training.loss

Class L2Loss

java.lang.Object

ai.djl.training.metrics.TrainingMetric

ai.djl.training.loss.Loss

ai.djl.training.loss.L2Loss

All Implemented Interfaces:

java.lang.Cloneable

public class L2Loss
extends Loss

Calculates L2Loss between label and prediction, a.k.a. MSE(Mean Square Error).

L2 loss is defined by \(L = \frac{1}{2} \sum_i \vert {label}_i - {prediction}_i \vert^2\)

Constructor Summary

Constructors

Constructor and Description
L2Loss() Calculate L2Loss between the label and prediction, a.k.a.
L2Loss(float weight, int batchAxis) Calculates L2Loss between the label and prediction, a.k.a.

Method Summary

Modifier and Type	Method and Description
NDArray	getLoss(NDList label, NDList prediction) Calculates loss between the label and prediction.

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

duplicate, excludeBatchAxis, getValue, hingeLoss, hingeLoss, l1Loss, l1Loss, l2Loss, l2Loss, reset, sigmoidBinaryCrossEntropyLoss, sigmoidBinaryCrossEntropyLoss, softmaxCrossEntropyLoss, softmaxCrossEntropyLoss, update

Methods inherited from class ai.djl.training.metrics.TrainingMetric

checkLabelShapes, checkLabelShapes, getName

Methods inherited from class java.lang.Object

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

Constructor Detail

L2Loss

public L2Loss(float weight,
              int batchAxis)

Calculates L2Loss between the label and prediction, a.k.a. MSE(Mean Square Error).

Parameters:

weight - the weight to apply on loss value, default 1/2

batchAxis - the axis that represents mini-batch, default 0

L2Loss

public L2Loss()

Calculate L2Loss between the label and prediction, a.k.a. MSE(Mean Square Error).

Method Detail

getLoss

public NDArray getLoss(NDList label,
                       NDList prediction)

Calculates loss between the label and prediction.

Specified by:

getLoss in class Loss

Parameters:

label - the true label

prediction - the predicted label

Returns:

the loss value