All Downloads are FREE. Search and download functionalities are using the official Maven repository.
Please wait. This can take some minutes ...
Many resources are needed to download a project. Please understand that we have to compensate our server costs. Thank you in advance.
Project price only 1 $
You can buy this project and download/modify it how often you want.
org.nd4j.linalg.lossfunctions.impl.LossBinaryXENT Maven / Gradle / Ivy
package org.nd4j.linalg.lossfunctions.impl;
import lombok.EqualsAndHashCode;
import lombok.Getter;
import org.apache.commons.math3.util.Pair;
import org.nd4j.linalg.activations.IActivation;
import org.nd4j.linalg.activations.impl.ActivationSoftmax;
import org.nd4j.linalg.api.ndarray.INDArray;
import org.nd4j.linalg.api.ops.impl.transforms.LogSoftMax;
import org.nd4j.linalg.api.ops.impl.transforms.TimesOneMinus;
import org.nd4j.linalg.factory.Nd4j;
import org.nd4j.linalg.lossfunctions.ILossFunction;
import org.nd4j.linalg.lossfunctions.LossUtil;
import org.nd4j.linalg.lossfunctions.serde.RowVectorDeserializer;
import org.nd4j.linalg.lossfunctions.serde.RowVectorSerializer;
import org.nd4j.linalg.ops.transforms.Transforms;
import org.nd4j.shade.jackson.annotation.JsonInclude;
import org.nd4j.shade.jackson.databind.annotation.JsonDeserialize;
import org.nd4j.shade.jackson.databind.annotation.JsonSerialize;
/**
* Binary cross entropy loss function
*
* https://en.wikipedia.org/wiki/Cross_entropy#Cross-entropy_error_function_and_logistic_regression
* Labels are assumed to take values 0 or 1
*
* @author Susan Eraly
*/
@EqualsAndHashCode
@JsonInclude(JsonInclude.Include.NON_NULL)
@Getter
public class LossBinaryXENT implements ILossFunction {
@JsonSerialize(using = RowVectorSerializer.class)
@JsonDeserialize(using = RowVectorDeserializer.class)
private final INDArray weights;
public LossBinaryXENT() {
this(null);
}
/**
* 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.
*
* @param weights Weights array (row vector). May be null.
*/
public LossBinaryXENT(INDArray weights) {
if (weights != null && !weights.isRowVector()) {
throw new IllegalArgumentException("Weights array must be a row vector");
}
this.weights = weights;
}
private INDArray scoreArray(INDArray labels,
INDArray preOutput,
IActivation activationFn,
INDArray mask) {
if (labels.size(1) != preOutput.size(1)) {
throw new IllegalArgumentException("Labels array numColumns (size(1) = " + labels.size(1)
+ ") does not match output layer" + " number of outputs (nOut = " + preOutput.size(1)
+ ") ");
}
INDArray scoreArr;
if (activationFn instanceof ActivationSoftmax) {
//Use LogSoftMax op to avoid numerical issues when calculating score
INDArray logsoftmax = Nd4j.getExecutioner().execAndReturn(new LogSoftMax(preOutput.dup()));
scoreArr = logsoftmax.muli(labels);
} else {
//INDArray output = Nd4j.getExecutioner().execAndReturn(Nd4j.getOpFactory().createTransform(activationFn, preOutput.dup()));
INDArray output = activationFn.getActivation(preOutput.dup(), true);
scoreArr = Transforms.log(output, true).muli(labels);
INDArray secondTerm = output.rsubi(1);
Transforms.log(secondTerm, false);
secondTerm.muli(labels.rsub(1));
scoreArr.addi(secondTerm);
}
//Weighted loss function
if (weights != null) {
if (weights.length() != preOutput.size(1)) {
throw new IllegalStateException("Weights vector (length " + weights.length()
+ ") does not match output.size(1)=" + preOutput.size(1));
}
scoreArr.muliRowVector(weights);
}
if (mask != null) {
LossUtil.applyMask(scoreArr, mask);
}
return scoreArr;
}
@Override
public double computeScore(INDArray labels,
INDArray preOutput,
IActivation activationFn,
INDArray mask,
boolean average) {
INDArray scoreArr = scoreArray(labels, preOutput, activationFn, mask);
double score = -scoreArr.sumNumber().doubleValue();
if (average) {
score /= scoreArr.size(0);
}
return score;
}
@Override
public INDArray computeScoreArray(INDArray labels,
INDArray preOutput,
IActivation activationFn,
INDArray mask) {
INDArray scoreArr = scoreArray(
labels,
preOutput,
activationFn,
mask);
return scoreArr.sum(1).muli(-1);
}
@Override
public INDArray computeGradient(INDArray labels,
INDArray preOutput,
IActivation activationFn,
INDArray mask) {
if (labels.size(1) != preOutput.size(1)) {
throw new IllegalArgumentException("Labels array numColumns (size(1) = " + labels.size(1)
+ ") does not match output layer" + " number of outputs (nOut = " + preOutput.size(1)
+ ") ");
}
INDArray output = activationFn.getActivation(preOutput.dup(), true);
INDArray numerator = output.sub(labels);
INDArray denominator = Nd4j.getExecutioner().execAndReturn(new TimesOneMinus(output)); // output * (1-output)
INDArray dLda = numerator.divi(denominator);
if(mask != null && LossUtil.isPerOutputMasking(dLda, mask)) {
//For *most* activation functions: we don't actually need to mask dL/da in addition to masking dL/dz later
//but: some, like softmax, require both (due to dL/dz_i being a function of dL/da_j, for i != j)
//We could add a special case for softmax (activationFn instanceof ActivationSoftmax) but that would be
// error prone - but buy us a tiny bit of performance
LossUtil.applyMask(dLda, mask);
}
INDArray grad = activationFn.backprop(preOutput, dLda).getFirst(); //TODO activation functions with weights
//Weighted loss function
if (weights != null) {
if (weights.length() != output.size(1)) {
throw new IllegalStateException("Weights vector (length " + weights.length()
+ ") does not match output.size(1)=" + output.size(1));
}
grad.muliRowVector(weights);
}
if (mask != null) {
LossUtil.applyMask(grad, mask);
}
return grad;
}
@Override
public Pair computeGradientAndScore(INDArray labels, INDArray preOutput, IActivation activationFn,
INDArray mask, boolean average) {
//TODO: probably a more efficient way to do this...
return new Pair<>(
computeScore(
labels,
preOutput,
activationFn,
mask,
average),
computeGradient(labels,
preOutput,
activationFn,
mask));
}
/**
* The name of this function
*
* @return
*/
@Override
public String name() {
return toString();
}
@Override
public String toString() {
if (weights == null)
return "LossBinaryXENT()";
return "LossBinaryXENT(weights=" + weights + ")";
}
}