Package org.nd4j.linalg.lossfunctions.impl

Class LossBinaryXENT

java.lang.Object

org.nd4j.linalg.lossfunctions.impl.LossBinaryXENT

All Implemented Interfaces:

Serializable, ILossFunction

public class LossBinaryXENT
extends Object
implements ILossFunction

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field	Description
static double	DEFAULT_CLIPPING_EPSILON

Constructor Summary

Constructors

Constructor	Description
LossBinaryXENT()
LossBinaryXENT(double clipEps)	Binary cross entropy where each the output is (optionally) weighted/scaled by a fixed scalar value.
LossBinaryXENT(double clipEps, INDArray weights)	Binary cross entropy where each the output is (optionally) weighted/scaled by a fixed scalar value.
LossBinaryXENT(INDArray weights)	Binary cross entropy where each the output is (optionally) weighted/scaled by a fixed scalar value.

Method Summary

Modifier and Type	Method	Description
INDArray	computeGradient(INDArray labels, INDArray preOutput, IActivation activationFn, INDArray mask)	Compute the gradient of the loss function with respect to the inputs: dL/dOutput
Pair<Double,INDArray>	computeGradientAndScore(INDArray labels, INDArray preOutput, IActivation activationFn, INDArray mask, boolean average)	Compute both the score (loss function value) and gradient.
double	computeScore(INDArray labels, INDArray preOutput, IActivation activationFn, INDArray mask, boolean average)	Compute the score (loss function value) for the given inputs.
INDArray	computeScoreArray(INDArray labels, INDArray preOutput, IActivation activationFn, INDArray mask)	Compute the score (loss function value) for each example individually.
String	name()	The opName of this function
String	toString()

Methods inherited from class java.lang.Object

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

Field Detail

DEFAULT_CLIPPING_EPSILON

public static final double DEFAULT_CLIPPING_EPSILON

See Also:

Constant Field Values

Constructor Detail

LossBinaryXENT

public LossBinaryXENT()

LossBinaryXENT

public LossBinaryXENT(INDArray weights)

Binary cross entropy where each the output is (optionally) weighted/scaled by a fixed scalar value. Note that the weights array must be a row vector, of length equal to the labels/output dimension 1 size. A weight vector of 1s should give identical results to no weight vector.

Parameters:

weights - Weights array (row vector). May be null.

LossBinaryXENT

public LossBinaryXENT(double clipEps)

Binary cross entropy where each the output is (optionally) weighted/scaled by a fixed scalar value. Note that the weights array must be a row vector, of length equal to the labels/output dimension 1 size. A weight vector of 1s should give identical results to no weight vector.

Parameters:

clipEps - Epsilon value for clipping. Probabilities are clipped in range of [eps, 1-eps]. Default eps: 1e-5

LossBinaryXENT

public LossBinaryXENT(double clipEps,
                      INDArray weights)

Binary cross entropy where each the output is (optionally) weighted/scaled by a fixed scalar value. Note that the weights array must be a row vector, of length equal to the labels/output dimension 1 size. A weight vector of 1s should give identical results to no weight vector.

Parameters:

clipEps - Epsilon value for clipping. Probabilities are clipped in range of [eps, 1-eps]. Default eps: 1e-5

weights - Weights array (row vector). May be null.

Method Detail

computeScore

public double computeScore(INDArray labels,
                           INDArray preOutput,
                           IActivation activationFn,
                           INDArray mask,
                           boolean average)

Description copied from interface: ILossFunction

Compute the score (loss function value) for the given inputs.

Specified by:

computeScore in interface ILossFunction

Parameters:

labels - Label/expected preOutput

preOutput - Output of the model (neural network)

activationFn - Activation function that should be applied to preOutput

mask - Mask array; may be null

average - Whether the score should be averaged (divided by number of rows in labels/preOutput) or not @return Loss function value

computeScoreArray

public INDArray computeScoreArray(INDArray labels,
                                  INDArray preOutput,
                                  IActivation activationFn,
                                  INDArray mask)

Description copied from interface: ILossFunction

Compute the score (loss function value) for each example individually. For input [numExamples,nOut] returns scores as a column vector: [numExamples,1]

Specified by:

computeScoreArray in interface ILossFunction

Parameters:

labels - Labels/expected output

preOutput - Output of the model (neural network)

activationFn - Activation function that should be applied to preOutput

Returns:

Loss function value for each example; column vector

computeGradient

public INDArray computeGradient(INDArray labels,
                                INDArray preOutput,
                                IActivation activationFn,
                                INDArray mask)

Description copied from interface: ILossFunction

Compute the gradient of the loss function with respect to the inputs: dL/dOutput

Specified by:

computeGradient in interface ILossFunction

Parameters:

labels - Label/expected output

preOutput - Output of the model (neural network), before the activation function is applied

activationFn - Activation function that should be applied to preOutput

mask - Mask array; may be null

Returns:

Gradient dL/dPreOut

computeGradientAndScore

public Pair<Double,INDArray> computeGradientAndScore(INDArray labels,
                                                           INDArray preOutput,
                                                           IActivation activationFn,
                                                           INDArray mask,
                                                           boolean average)

Description copied from interface: ILossFunction

Compute both the score (loss function value) and gradient. This is equivalent to calling ILossFunction.computeScore(INDArray, INDArray, IActivation, INDArray, boolean) and ILossFunction.computeGradient(INDArray, INDArray, IActivation, INDArray) individually

Specified by:

computeGradientAndScore in interface ILossFunction

Parameters:

labels - Label/expected output

preOutput - Output of the model (neural network)

activationFn - Activation function that should be applied to preOutput

mask - Mask array; may be null

average - Whether the score should be averaged (divided by number of rows in labels/output) or not

Returns:

The score (loss function value) and gradient

name

public String name()

The opName of this function

Specified by:

name in interface ILossFunction

Returns:

toString

public String toString()

Overrides:

toString in class Object