ai.djl.training.loss

Class HingeLoss

java.lang.Object

ai.djl.training.metrics.TrainingMetric

ai.djl.training.loss.Loss

ai.djl.training.loss.HingeLoss

All Implemented Interfaces:

java.lang.Cloneable

public class HingeLoss
extends Loss

HingeLoss is a type of Loss.

Hinge loss is defined by: \(L = \sum_i max(0, margin - pred_i \cdot label_i)\)

Constructor Summary

Constructors

Constructor and Description
HingeLoss() Calculates Hinge loss.
HingeLoss(int margin, float weight, int batchAxis) Calculates Hinge loss.

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

HingeLoss

public HingeLoss(int margin,
                 float weight,
                 int batchAxis)

Calculates Hinge loss.

Parameters:

margin - the margin in hinge loss. Defaults to 1.0

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

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

HingeLoss

public HingeLoss()

Calculates Hinge loss.

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