Search in sources :

Example 1 with ReconstructionDistribution

use of org.deeplearning4j.nn.conf.layers.variational.ReconstructionDistribution in project deeplearning4j by deeplearning4j.

the class TestReconstructionDistributions method testBernoulliLogProb.

@Test
public void testBernoulliLogProb() {
    Nd4j.getRandom().setSeed(12345);
    int inputSize = 4;
    int[] mbs = new int[] { 1, 2, 5 };
    Random r = new Random(12345);
    for (boolean average : new boolean[] { true, false }) {
        for (int minibatch : mbs) {
            INDArray x = Nd4j.zeros(minibatch, inputSize);
            for (int i = 0; i < minibatch; i++) {
                for (int j = 0; j < inputSize; j++) {
                    x.putScalar(i, j, r.nextInt(2));
                }
            }
            //i.e., pre-sigmoid prob
            INDArray distributionParams = Nd4j.rand(minibatch, inputSize).muli(2).subi(1);
            INDArray prob = Transforms.sigmoid(distributionParams, true);
            ReconstructionDistribution dist = new BernoulliReconstructionDistribution("sigmoid");
            double negLogProb = dist.negLogProbability(x, distributionParams, average);
            INDArray exampleNegLogProb = dist.exampleNegLogProbability(x, distributionParams);
            assertArrayEquals(new int[] { minibatch, 1 }, exampleNegLogProb.shape());
            //Calculate the same thing, but using Apache Commons math
            double logProbSum = 0.0;
            for (int i = 0; i < minibatch; i++) {
                double exampleSum = 0.0;
                for (int j = 0; j < inputSize; j++) {
                    double p = prob.getDouble(i, j);
                    //Bernoulli is a special case of binomial
                    BinomialDistribution binomial = new BinomialDistribution(1, p);
                    double xVal = x.getDouble(i, j);
                    double thisLogProb = binomial.logProbability((int) xVal);
                    logProbSum += thisLogProb;
                    exampleSum += thisLogProb;
                }
                assertEquals(-exampleNegLogProb.getDouble(i), exampleSum, 1e-6);
            }
            double expNegLogProb;
            if (average) {
                expNegLogProb = -logProbSum / minibatch;
            } else {
                expNegLogProb = -logProbSum;
            }
            //                System.out.println(x);
            //                System.out.println(expNegLogProb + "\t" + logProb + "\t" + (logProb / expNegLogProb));
            assertEquals(expNegLogProb, negLogProb, 1e-6);
            //Also: check random sampling...
            int count = minibatch * inputSize;
            INDArray arr = Nd4j.linspace(-3, 3, count).reshape(minibatch, inputSize);
            INDArray sampleMean = dist.generateAtMean(arr);
            INDArray sampleRandom = dist.generateRandom(arr);
            for (int i = 0; i < minibatch; i++) {
                for (int j = 0; j < inputSize; j++) {
                    double d1 = sampleMean.getDouble(i, j);
                    double d2 = sampleRandom.getDouble(i, j);
                    //Mean value - probability... could do 0 or 1 (based on most likely) but that isn't very useful...
                    assertTrue(d1 >= 0.0 || d1 <= 1.0);
                    assertTrue(d2 == 0.0 || d2 == 1.0);
                }
            }
        }
    }
}
Also used : Random(java.util.Random) INDArray(org.nd4j.linalg.api.ndarray.INDArray) BernoulliReconstructionDistribution(org.deeplearning4j.nn.conf.layers.variational.BernoulliReconstructionDistribution) BinomialDistribution(org.apache.commons.math3.distribution.BinomialDistribution) GaussianReconstructionDistribution(org.deeplearning4j.nn.conf.layers.variational.GaussianReconstructionDistribution) ReconstructionDistribution(org.deeplearning4j.nn.conf.layers.variational.ReconstructionDistribution) ExponentialReconstructionDistribution(org.deeplearning4j.nn.conf.layers.variational.ExponentialReconstructionDistribution) BernoulliReconstructionDistribution(org.deeplearning4j.nn.conf.layers.variational.BernoulliReconstructionDistribution) Test(org.junit.Test)

Example 2 with ReconstructionDistribution

use of org.deeplearning4j.nn.conf.layers.variational.ReconstructionDistribution in project deeplearning4j by deeplearning4j.

the class TestReconstructionDistributions method testGaussianLogProb.

@Test
public void testGaussianLogProb() {
    Nd4j.getRandom().setSeed(12345);
    int inputSize = 4;
    int[] mbs = new int[] { 1, 2, 5 };
    for (boolean average : new boolean[] { true, false }) {
        for (int minibatch : mbs) {
            INDArray x = Nd4j.rand(minibatch, inputSize);
            INDArray mean = Nd4j.randn(minibatch, inputSize);
            INDArray logStdevSquared = Nd4j.rand(minibatch, inputSize).subi(0.5);
            INDArray distributionParams = Nd4j.createUninitialized(new int[] { minibatch, 2 * inputSize });
            distributionParams.get(NDArrayIndex.all(), NDArrayIndex.interval(0, inputSize)).assign(mean);
            distributionParams.get(NDArrayIndex.all(), NDArrayIndex.interval(inputSize, 2 * inputSize)).assign(logStdevSquared);
            ReconstructionDistribution dist = new GaussianReconstructionDistribution("identity");
            double negLogProb = dist.negLogProbability(x, distributionParams, average);
            INDArray exampleNegLogProb = dist.exampleNegLogProbability(x, distributionParams);
            assertArrayEquals(new int[] { minibatch, 1 }, exampleNegLogProb.shape());
            //Calculate the same thing, but using Apache Commons math
            double logProbSum = 0.0;
            for (int i = 0; i < minibatch; i++) {
                double exampleSum = 0.0;
                for (int j = 0; j < inputSize; j++) {
                    double mu = mean.getDouble(i, j);
                    double logSigma2 = logStdevSquared.getDouble(i, j);
                    double sigma = Math.sqrt(Math.exp(logSigma2));
                    NormalDistribution nd = new NormalDistribution(mu, sigma);
                    double xVal = x.getDouble(i, j);
                    double thisLogProb = nd.logDensity(xVal);
                    logProbSum += thisLogProb;
                    exampleSum += thisLogProb;
                }
                assertEquals(-exampleNegLogProb.getDouble(i), exampleSum, 1e-6);
            }
            double expNegLogProb;
            if (average) {
                expNegLogProb = -logProbSum / minibatch;
            } else {
                expNegLogProb = -logProbSum;
            }
            //                System.out.println(expLogProb + "\t" + logProb + "\t" + (logProb / expLogProb));
            assertEquals(expNegLogProb, negLogProb, 1e-6);
            //Also: check random sampling...
            int count = minibatch * inputSize;
            INDArray arr = Nd4j.linspace(-3, 3, count).reshape(minibatch, inputSize);
            INDArray sampleMean = dist.generateAtMean(arr);
            INDArray sampleRandom = dist.generateRandom(arr);
        }
    }
}
Also used : GaussianReconstructionDistribution(org.deeplearning4j.nn.conf.layers.variational.GaussianReconstructionDistribution) INDArray(org.nd4j.linalg.api.ndarray.INDArray) NormalDistribution(org.apache.commons.math3.distribution.NormalDistribution) GaussianReconstructionDistribution(org.deeplearning4j.nn.conf.layers.variational.GaussianReconstructionDistribution) ReconstructionDistribution(org.deeplearning4j.nn.conf.layers.variational.ReconstructionDistribution) ExponentialReconstructionDistribution(org.deeplearning4j.nn.conf.layers.variational.ExponentialReconstructionDistribution) BernoulliReconstructionDistribution(org.deeplearning4j.nn.conf.layers.variational.BernoulliReconstructionDistribution) Test(org.junit.Test)

Example 3 with ReconstructionDistribution

use of org.deeplearning4j.nn.conf.layers.variational.ReconstructionDistribution in project deeplearning4j by deeplearning4j.

the class TestReconstructionDistributions method gradientCheckReconstructionDistributions.

@Test
public void gradientCheckReconstructionDistributions() {
    double eps = 1e-6;
    double maxRelError = 1e-6;
    double minAbsoluteError = 1e-9;
    Nd4j.getRandom().setSeed(12345);
    int inputSize = 4;
    int[] mbs = new int[] { 1, 3 };
    Random r = new Random(12345);
    ReconstructionDistribution[] distributions = new ReconstructionDistribution[] { new GaussianReconstructionDistribution("identity"), new GaussianReconstructionDistribution("tanh"), new BernoulliReconstructionDistribution("sigmoid"), new ExponentialReconstructionDistribution("identity"), new ExponentialReconstructionDistribution("tanh") };
    List<String> passes = new ArrayList<>();
    List<String> failures = new ArrayList<>();
    for (ReconstructionDistribution rd : distributions) {
        for (int minibatch : mbs) {
            INDArray x;
            INDArray distributionParams;
            if (rd instanceof GaussianReconstructionDistribution) {
                distributionParams = Nd4j.rand(minibatch, inputSize * 2).muli(2).subi(1);
                x = Nd4j.rand(minibatch, inputSize);
            } else if (rd instanceof BernoulliReconstructionDistribution) {
                distributionParams = Nd4j.rand(minibatch, inputSize).muli(2).subi(1);
                x = Nd4j.zeros(minibatch, inputSize);
                for (int i = 0; i < minibatch; i++) {
                    for (int j = 0; j < inputSize; j++) {
                        x.putScalar(i, j, r.nextInt(2));
                    }
                }
            } else if (rd instanceof ExponentialReconstructionDistribution) {
                distributionParams = Nd4j.rand(minibatch, inputSize).muli(2).subi(1);
                x = Nd4j.rand(minibatch, inputSize);
            } else {
                throw new RuntimeException();
            }
            INDArray gradient = rd.gradient(x, distributionParams);
            String testName = "minibatch = " + minibatch + ", size = " + inputSize + ", Distribution = " + rd;
            System.out.println("\n\n***** Starting test: " + testName + "*****");
            int totalFailureCount = 0;
            for (int i = 0; i < distributionParams.size(1); i++) {
                for (int j = 0; j < distributionParams.size(0); j++) {
                    double initial = distributionParams.getDouble(j, i);
                    distributionParams.putScalar(j, i, initial + eps);
                    double scorePlus = rd.negLogProbability(x, distributionParams, false);
                    distributionParams.putScalar(j, i, initial - eps);
                    double scoreMinus = rd.negLogProbability(x, distributionParams, false);
                    distributionParams.putScalar(j, i, initial);
                    double numericalGrad = (scorePlus - scoreMinus) / (2.0 * eps);
                    double backpropGrad = gradient.getDouble(j, i);
                    double relError = Math.abs(numericalGrad - backpropGrad) / (Math.abs(numericalGrad) + Math.abs(backpropGrad));
                    double absError = Math.abs(backpropGrad - numericalGrad);
                    if (relError > maxRelError || Double.isNaN(relError)) {
                        if (absError < minAbsoluteError) {
                            log.info("Input (" + j + "," + i + ") passed: grad= " + backpropGrad + ", numericalGrad= " + numericalGrad + ", relError= " + relError + "; absolute error = " + absError + " < minAbsoluteError = " + minAbsoluteError);
                        } else {
                            log.info("Input (" + j + "," + i + ") FAILED: grad= " + backpropGrad + ", numericalGrad= " + numericalGrad + ", relError= " + relError + ", scorePlus=" + scorePlus + ", scoreMinus= " + scoreMinus);
                            totalFailureCount++;
                        }
                    } else {
                        log.info("Input (" + j + "," + i + ") passed: grad= " + backpropGrad + ", numericalGrad= " + numericalGrad + ", relError= " + relError);
                    }
                }
            }
            if (totalFailureCount > 0) {
                failures.add(testName);
            } else {
                passes.add(testName);
            }
        }
    }
    System.out.println("\n\n\n +++++ Test Passes +++++");
    for (String s : passes) {
        System.out.println(s);
    }
    System.out.println("\n\n\n +++++ Test Faliures +++++");
    for (String s : failures) {
        System.out.println(s);
    }
    assertEquals(0, failures.size());
}
Also used : ExponentialReconstructionDistribution(org.deeplearning4j.nn.conf.layers.variational.ExponentialReconstructionDistribution) ArrayList(java.util.ArrayList) GaussianReconstructionDistribution(org.deeplearning4j.nn.conf.layers.variational.GaussianReconstructionDistribution) ReconstructionDistribution(org.deeplearning4j.nn.conf.layers.variational.ReconstructionDistribution) ExponentialReconstructionDistribution(org.deeplearning4j.nn.conf.layers.variational.ExponentialReconstructionDistribution) BernoulliReconstructionDistribution(org.deeplearning4j.nn.conf.layers.variational.BernoulliReconstructionDistribution) GaussianReconstructionDistribution(org.deeplearning4j.nn.conf.layers.variational.GaussianReconstructionDistribution) Random(java.util.Random) INDArray(org.nd4j.linalg.api.ndarray.INDArray) BernoulliReconstructionDistribution(org.deeplearning4j.nn.conf.layers.variational.BernoulliReconstructionDistribution) Test(org.junit.Test)

Example 4 with ReconstructionDistribution

use of org.deeplearning4j.nn.conf.layers.variational.ReconstructionDistribution in project deeplearning4j by deeplearning4j.

the class TestReconstructionDistributions method testExponentialLogProb.

@Test
public void testExponentialLogProb() {
    Nd4j.getRandom().setSeed(12345);
    int inputSize = 4;
    int[] mbs = new int[] { 1, 2, 5 };
    Random r = new Random(12345);
    for (boolean average : new boolean[] { true, false }) {
        for (int minibatch : mbs) {
            INDArray x = Nd4j.zeros(minibatch, inputSize);
            for (int i = 0; i < minibatch; i++) {
                for (int j = 0; j < inputSize; j++) {
                    x.putScalar(i, j, r.nextInt(2));
                }
            }
            //i.e., pre-afn gamma
            INDArray distributionParams = Nd4j.rand(minibatch, inputSize).muli(2).subi(1);
            INDArray gammas = Transforms.tanh(distributionParams, true);
            ReconstructionDistribution dist = new ExponentialReconstructionDistribution("tanh");
            double negLogProb = dist.negLogProbability(x, distributionParams, average);
            INDArray exampleNegLogProb = dist.exampleNegLogProbability(x, distributionParams);
            assertArrayEquals(new int[] { minibatch, 1 }, exampleNegLogProb.shape());
            //Calculate the same thing, but using Apache Commons math
            double logProbSum = 0.0;
            for (int i = 0; i < minibatch; i++) {
                double exampleSum = 0.0;
                for (int j = 0; j < inputSize; j++) {
                    double gamma = gammas.getDouble(i, j);
                    double lambda = Math.exp(gamma);
                    double mean = 1.0 / lambda;
                    //Commons math uses mean = 1/lambda
                    ExponentialDistribution exp = new ExponentialDistribution(mean);
                    double xVal = x.getDouble(i, j);
                    double thisLogProb = exp.logDensity(xVal);
                    logProbSum += thisLogProb;
                    exampleSum += thisLogProb;
                }
                assertEquals(-exampleNegLogProb.getDouble(i), exampleSum, 1e-6);
            }
            double expNegLogProb;
            if (average) {
                expNegLogProb = -logProbSum / minibatch;
            } else {
                expNegLogProb = -logProbSum;
            }
            //                System.out.println(x);
            //                System.out.println(expNegLogProb + "\t" + logProb + "\t" + (logProb / expNegLogProb));
            assertEquals(expNegLogProb, negLogProb, 1e-6);
            //Also: check random sampling...
            int count = minibatch * inputSize;
            INDArray arr = Nd4j.linspace(-3, 3, count).reshape(minibatch, inputSize);
            INDArray sampleMean = dist.generateAtMean(arr);
            INDArray sampleRandom = dist.generateRandom(arr);
            for (int i = 0; i < minibatch; i++) {
                for (int j = 0; j < inputSize; j++) {
                    double d1 = sampleMean.getDouble(i, j);
                    double d2 = sampleRandom.getDouble(i, j);
                    assertTrue(d1 >= 0.0);
                    assertTrue(d2 >= 0.0);
                }
            }
        }
    }
}
Also used : Random(java.util.Random) INDArray(org.nd4j.linalg.api.ndarray.INDArray) ExponentialReconstructionDistribution(org.deeplearning4j.nn.conf.layers.variational.ExponentialReconstructionDistribution) ExponentialDistribution(org.apache.commons.math3.distribution.ExponentialDistribution) GaussianReconstructionDistribution(org.deeplearning4j.nn.conf.layers.variational.GaussianReconstructionDistribution) ReconstructionDistribution(org.deeplearning4j.nn.conf.layers.variational.ReconstructionDistribution) ExponentialReconstructionDistribution(org.deeplearning4j.nn.conf.layers.variational.ExponentialReconstructionDistribution) BernoulliReconstructionDistribution(org.deeplearning4j.nn.conf.layers.variational.BernoulliReconstructionDistribution) Test(org.junit.Test)

Aggregations

BernoulliReconstructionDistribution (org.deeplearning4j.nn.conf.layers.variational.BernoulliReconstructionDistribution)4 ExponentialReconstructionDistribution (org.deeplearning4j.nn.conf.layers.variational.ExponentialReconstructionDistribution)4 GaussianReconstructionDistribution (org.deeplearning4j.nn.conf.layers.variational.GaussianReconstructionDistribution)4 ReconstructionDistribution (org.deeplearning4j.nn.conf.layers.variational.ReconstructionDistribution)4 Test (org.junit.Test)4 INDArray (org.nd4j.linalg.api.ndarray.INDArray)4 Random (java.util.Random)3 ArrayList (java.util.ArrayList)1 BinomialDistribution (org.apache.commons.math3.distribution.BinomialDistribution)1 ExponentialDistribution (org.apache.commons.math3.distribution.ExponentialDistribution)1 NormalDistribution (org.apache.commons.math3.distribution.NormalDistribution)1