• Home
• org.nd4j
• nd4j-api
• 0.6.0
• source code
• LossPoisson.java

×

Project download

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.LossPoisson Maven / Gradle / Ivy

package org.nd4j.linalg.lossfunctions.impl;

import lombok.EqualsAndHashCode;
import org.apache.commons.math3.util.Pair;
import org.nd4j.linalg.api.ndarray.INDArray;
import org.nd4j.linalg.factory.Nd4j;
import org.nd4j.linalg.lossfunctions.ILossFunction;
import org.nd4j.linalg.ops.transforms.Transforms;

/**
 * Created by susaneraly on 9/9/16.
 */
@EqualsAndHashCode
public class LossPoisson implements ILossFunction {

    public INDArray scoreArray(INDArray labels, INDArray preOutput, String activationFn, INDArray mask) {
        /*
         mean of (yhat - y * log(yhat))
         */
        INDArray postOutput = Nd4j.getExecutioner().execAndReturn(Nd4j.getOpFactory().createTransform(activationFn, preOutput.dup()));

        INDArray scoreArr = Transforms.log(postOutput);
        scoreArr.muli(labels);
        scoreArr = postOutput.sub(scoreArr);

        if (mask != null) scoreArr.muliColumnVector(mask);
        return scoreArr;
    }

    @Override
    public double computeScore(INDArray labels, INDArray preOutput, String 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, String activationFn, INDArray mask) {
        INDArray scoreArr = scoreArray(labels, preOutput, activationFn, mask);
        return scoreArr.sum(1);
    }

    @Override
    public INDArray computeGradient(INDArray labels, INDArray preOutput, String activationFn, INDArray mask) {
        INDArray postOutDer = Nd4j.getExecutioner().execAndReturn(Nd4j.getOpFactory().createTransform(activationFn, preOutput.dup()).derivative());
        /*
        gradient of loss function wrt yhat = (1 - y/yhat)
        */
        INDArray yDivyhat = Nd4j.getExecutioner().execAndReturn(Nd4j.getOpFactory().createTransform(activationFn, preOutput.dup()));
        yDivyhat = labels.div(yDivyhat);

        INDArray gradients = yDivyhat.muli(-1);
        gradients.addi(1);
        gradients.muli(postOutDer);

        if (mask != null) {
            gradients.muliColumnVector(mask);
        }

        return gradients;
    }

    @Override
    public org.apache.commons.math3.util.Pair computeGradientAndScore(INDArray labels, INDArray preOutput, String activationFn, INDArray mask, boolean average) {
        //TODO: probably a more efficient way to do this...
        //Yes - will implement in round two. Just want to get done now.

        return new Pair<>(
                computeScore(labels, preOutput, activationFn, mask, average),
                computeGradient(labels, preOutput, activationFn, mask));
    }

    @Override
    public String toString() {
        return "LossPoisson()";
    }
}