Examples with DefaultRandom org.nd4j.linalg.api.rng.DefaultRandom used on opensource projects

Example 1 with DefaultRandom

use of org.nd4j.linalg.api.rng.DefaultRandom in project deeplearning4j by deeplearning4j.

the class TestOptimizers method testSphereFnOptHelper.

public void testSphereFnOptHelper(OptimizationAlgorithm oa, int numLineSearchIter, int nDimensions) {
    if (PRINT_OPT_RESULTS)
        System.out.println("---------\n Alg= " + oa + ", nIter= " + numLineSearchIter + ", nDimensions= " + nDimensions);
    NeuralNetConfiguration conf = new NeuralNetConfiguration.Builder().maxNumLineSearchIterations(numLineSearchIter).iterations(100).learningRate(1e-2).layer(new RBM.Builder().nIn(1).nOut(1).updater(Updater.SGD).build()).build();
    //Normally done by ParamInitializers, but obviously that isn't done here
    conf.addVariable("W");
    Random rng = new DefaultRandom(12345L);
    org.nd4j.linalg.api.rng.distribution.Distribution dist = new org.nd4j.linalg.api.rng.distribution.impl.UniformDistribution(rng, -10, 10);
    Model m = new SphereFunctionModel(nDimensions, dist, conf);
    m.computeGradientAndScore();
    double scoreBefore = m.score();
    assertTrue(!Double.isNaN(scoreBefore) && !Double.isInfinite(scoreBefore));
    if (PRINT_OPT_RESULTS) {
        System.out.println("Before:");
        System.out.println(scoreBefore);
        System.out.println(m.params());
    }
    ConvexOptimizer opt = getOptimizer(oa, conf, m);
    opt.setupSearchState(m.gradientAndScore());
    opt.optimize();
    m.computeGradientAndScore();
    double scoreAfter = m.score();
    assertTrue(!Double.isNaN(scoreAfter) && !Double.isInfinite(scoreAfter));
    if (PRINT_OPT_RESULTS) {
        System.out.println("After:");
        System.out.println(scoreAfter);
        System.out.println(m.params());
    }
    //Expected behaviour after optimization:
    //(a) score is better (lower) after optimization.
    //(b) Parameters are closer to minimum after optimization (TODO)
    assertTrue("Score did not improve after optimization (b= " + scoreBefore + " ,a= " + scoreAfter + ")", scoreAfter < scoreBefore);
}

Example 2 with DefaultRandom

use of org.nd4j.linalg.api.rng.DefaultRandom in project deeplearning4j by deeplearning4j.

the class TestOptimizers method testSphereFnMultipleStepsHelper.

private static void testSphereFnMultipleStepsHelper(OptimizationAlgorithm oa, int nOptIter, int maxNumLineSearchIter) {
    double[] scores = new double[nOptIter + 1];
    for (int i = 0; i <= nOptIter; i++) {
        Random rng = new DefaultRandom(12345L);
        org.nd4j.linalg.api.rng.distribution.Distribution dist = new org.nd4j.linalg.api.rng.distribution.impl.UniformDistribution(rng, -10, 10);
        NeuralNetConfiguration conf = new NeuralNetConfiguration.Builder().maxNumLineSearchIterations(maxNumLineSearchIter).iterations(i).learningRate(0.1).layer(new DenseLayer.Builder().nIn(1).nOut(1).updater(Updater.SGD).build()).build();
        //Normally done by ParamInitializers, but obviously that isn't done here
        conf.addVariable("W");
        Model m = new SphereFunctionModel(100, dist, conf);
        if (i == 0) {
            m.computeGradientAndScore();
            //Before optimization
            scores[0] = m.score();
        } else {
            ConvexOptimizer opt = getOptimizer(oa, conf, m);
            opt.optimize();
            m.computeGradientAndScore();
            scores[i] = m.score();
            assertTrue(!Double.isNaN(scores[i]) && !Double.isInfinite(scores[i]));
        }
    }
    if (PRINT_OPT_RESULTS) {
        System.out.println("Multiple optimization iterations (" + nOptIter + " opt. iter.) score vs iteration, maxNumLineSearchIter=" + maxNumLineSearchIter + ": " + oa);
        System.out.println(Arrays.toString(scores));
    }
    for (int i = 1; i < scores.length; i++) {
        assertTrue(scores[i] <= scores[i - 1]);
    }
    //Very easy function, expect score ~= 0 with any reasonable number of steps/numLineSearchIter
    assertTrue(scores[scores.length - 1] < 1.0);
}