ai.djl.training.loss

Class HingeLoss

java.lang.Object

ai.djl.training.evaluator.Evaluator

ai.djl.training.loss.Loss

ai.djl.training.loss.HingeLoss

public class HingeLoss
extends Loss

HingeLoss is a type of Loss.

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

Field Summary

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

totalInstances

Constructor Summary

Constructors

Constructor and Description
HingeLoss() Calculates Hinge loss.
HingeLoss(java.lang.String name) Calculates Hinge loss.
HingeLoss(java.lang.String name, int margin, float weight) Calculates Hinge loss.

Method Summary

Modifier and Type	Method and 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, getAccumulator, hingeLoss, hingeLoss, hingeLoss, l1Loss, l1Loss, l1Loss, l2Loss, l2Loss, l2Loss, 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

HingeLoss

public HingeLoss()

Calculates Hinge loss.

HingeLoss

public HingeLoss(java.lang.String name)

Calculates Hinge loss.

Parameters:

name - the name of the loss

HingeLoss

public HingeLoss(java.lang.String name,
                 int margin,
                 float weight)

Calculates Hinge loss.

Parameters:

name - the name of the loss

margin - the margin in hinge loss. Defaults to 1.0

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