Package ai.djl.training.loss

Class SigmoidBinaryCrossEntropyLoss

java.lang.Object

ai.djl.training.evaluator.Evaluator

ai.djl.training.loss.Loss

ai.djl.training.loss.SigmoidBinaryCrossEntropyLoss

public class SigmoidBinaryCrossEntropyLoss
extends Loss

SigmoidBinaryCrossEntropyLoss is a type of Loss.

Sigmoid binary cross-entropy loss is defined by: \(L = -\sum_i {label_i * log(prob_i) * posWeight + (1 - label_i) * log(1 - prob_i)}\) where \(prob = \frac{1}{1 + e^{-pred}}\)

Field Summary

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

totalInstances

Constructor Summary

Constructors

Constructor	Description
SigmoidBinaryCrossEntropyLoss()	Performs Sigmoid cross-entropy loss for binary classification.
SigmoidBinaryCrossEntropyLoss(String name)	Performs Sigmoid cross-entropy loss for binary classification.
SigmoidBinaryCrossEntropyLoss(String name, float weight, boolean fromSigmoid)	Performs Sigmoid cross-entropy loss for binary classification.

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, quantileL1Loss, quantileL1Loss, resetAccumulator, sigmoidBinaryCrossEntropyLoss, sigmoidBinaryCrossEntropyLoss, sigmoidBinaryCrossEntropyLoss, softmaxCrossEntropyLoss, softmaxCrossEntropyLoss, softmaxCrossEntropyLoss, updateAccumulator, updateAccumulators

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 Details

SigmoidBinaryCrossEntropyLoss

public SigmoidBinaryCrossEntropyLoss()

Performs Sigmoid cross-entropy loss for binary classification.

SigmoidBinaryCrossEntropyLoss

public SigmoidBinaryCrossEntropyLoss(String name)

Performs Sigmoid cross-entropy loss for binary classification.

Parameters:

name - the name of the loss

SigmoidBinaryCrossEntropyLoss

public SigmoidBinaryCrossEntropyLoss(String name,
 float weight,
 boolean fromSigmoid)

Performs Sigmoid cross-entropy loss for binary classification.

Parameters:

name - the name of the loss

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

fromSigmoid - whether the input is from the output of sigmoid, default false

Method Details

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