Examples with DeepLearningParameters hex.deeplearning.DeepLearningModel.DeepLearningParameters used on opensource projects

Example 31 with DeepLearningParameters

use of hex.deeplearning.DeepLearningModel.DeepLearningParameters in project h2o-3 by h2oai.

the class DeepLearningTest method testAutoEncoder.

@Test
public void testAutoEncoder() {
    Frame tfr = null, vfr = null, fr2 = null;
    DeepLearningModel dl = null;
    Scope.enter();
    try {
        tfr = parse_test_file("smalldata/glm_test/cancar_logIn.csv");
        for (String s : new String[] { "Merit", "Class" }) {
            Scope.track(tfr.replace(tfr.find(s), tfr.vec(s).toCategoricalVec()));
        }
        DKV.put(tfr);
        DeepLearningParameters parms = new DeepLearningParameters();
        parms._train = tfr._key;
        parms._epochs = 100;
        parms._reproducible = true;
        parms._hidden = new int[] { 5, 5, 5 };
        parms._response_column = "Cost";
        parms._seed = 0xdecaf;
        parms._autoencoder = true;
        parms._input_dropout_ratio = 0.1;
        parms._activation = DeepLearningParameters.Activation.Tanh;
        // Build a first model; all remaining models should be equal
        dl = new DeepLearning(parms).trainModel().get();
        ModelMetricsAutoEncoder mm = (ModelMetricsAutoEncoder) dl._output._training_metrics;
        Assert.assertEquals(0.0712931422088762, mm._MSE, 1e-2);
        assertTrue(dl.testJavaScoring(tfr, fr2 = dl.score(tfr), 1e-5));
    } finally {
        if (tfr != null)
            tfr.remove();
        if (dl != null)
            dl.delete();
        if (fr2 != null)
            fr2.delete();
        Scope.exit();
    }
}

Example 32 with DeepLearningParameters

use of hex.deeplearning.DeepLearningModel.DeepLearningParameters in project h2o-3 by h2oai.

the class DeepLearningTest method testRowWeightsOne.

@Test
public void testRowWeightsOne() {
    Frame tfr = null, vfr = null, pred = null, fr2 = null;
    Scope.enter();
    try {
        tfr = parse_test_file("smalldata/junit/weights_all_ones.csv");
        DKV.put(tfr);
        DeepLearningParameters parms = new DeepLearningParameters();
        parms._train = tfr._key;
        parms._response_column = "response";
        parms._weights_column = "weight";
        parms._reproducible = true;
        parms._seed = 0xdecaf;
        parms._classification_stop = -1;
        parms._l1 = 0.1;
        parms._hidden = new int[] { 1 };
        parms._epochs = 1;
        // Build a first model; all remaining models should be equal
        DeepLearningModel dl = new DeepLearning(parms).trainModel().get();
        pred = dl.score(parms.train());
        hex.ModelMetricsBinomial mm = hex.ModelMetricsBinomial.getFromDKV(dl, parms.train());
        assertEquals(0.7592592592592592, mm.auc_obj()._auc, 1e-8);
        double mse = dl._output._training_metrics.mse();
        //Note: better results than non-shuffled
        assertEquals(0.3148133418670781, mse, 1e-8);
        //      assertTrue(dl.testJavaScoring(tfr, fr2=dl.score(tfr, 1e-5)); //PUBDEV-1900
        dl.delete();
    } finally {
        if (tfr != null)
            tfr.remove();
        if (vfr != null)
            vfr.remove();
        if (pred != null)
            pred.remove();
        if (fr2 != null)
            fr2.remove();
    }
    Scope.exit();
}

Example 33 with DeepLearningParameters

use of hex.deeplearning.DeepLearningModel.DeepLearningParameters in project h2o-3 by h2oai.

the class DeepLearningTest method testConvergenceMisclassification.

@Test
public void testConvergenceMisclassification() {
    Frame tfr = null;
    DeepLearningModel dl = null;
    DeepLearningModel dl2 = null;
    try {
        tfr = parse_test_file("./smalldata/iris/iris.csv");
        DeepLearningParameters parms = new DeepLearningParameters();
        parms._train = tfr._key;
        parms._epochs = 1000000;
        parms._response_column = "C5";
        parms._reproducible = true;
        parms._hidden = new int[] { 2, 2 };
        parms._seed = 0xdecaf;
        parms._variable_importances = true;
        parms._score_duty_cycle = 1.0;
        parms._score_interval = 0;
        //don't stop based on absolute classification error
        parms._classification_stop = -1;
        //don't stop based on absolute classification error
        parms._stopping_rounds = 2;
        //don't stop based on absolute classification error
        parms._stopping_metric = ScoreKeeper.StoppingMetric.misclassification;
        parms._stopping_tolerance = 0.0;
        dl = new DeepLearning(parms).trainModel().get();
        Assert.assertTrue(dl.epoch_counter < parms._epochs);
    } finally {
        if (tfr != null)
            tfr.delete();
        if (dl != null)
            dl.delete();
        if (dl2 != null)
            dl2.delete();
    }
}

Example 34 with DeepLearningParameters

use of hex.deeplearning.DeepLearningModel.DeepLearningParameters in project h2o-3 by h2oai.

the class DeepLearningTest method testConvergenceAUC.

@Test
public void testConvergenceAUC() {
    Frame tfr = null;
    DeepLearningModel dl = null;
    DeepLearningModel dl2 = null;
    try {
        tfr = parse_test_file("./smalldata/logreg/prostate.csv");
        for (String s : new String[] { "CAPSULE" }) {
            Vec resp = tfr.vec(s).toCategoricalVec();
            tfr.remove(s).remove();
            tfr.add(s, resp);
            DKV.put(tfr);
        }
        DeepLearningParameters parms = new DeepLearningParameters();
        parms._train = tfr._key;
        parms._epochs = 1000000;
        parms._response_column = "CAPSULE";
        parms._reproducible = true;
        parms._hidden = new int[] { 2, 2 };
        parms._seed = 0xdecaf;
        parms._variable_importances = true;
        parms._score_duty_cycle = 1.0;
        parms._score_interval = 0;
        //don't stop based on absolute classification error
        parms._classification_stop = -1;
        //don't stop based on absolute classification error
        parms._stopping_rounds = 2;
        //don't stop based on absolute classification error
        parms._stopping_metric = ScoreKeeper.StoppingMetric.AUC;
        parms._stopping_tolerance = 0.0;
        dl = new DeepLearning(parms).trainModel().get();
        Assert.assertTrue(dl.epoch_counter < parms._epochs);
    } finally {
        if (tfr != null)
            tfr.delete();
        if (dl != null)
            dl.delete();
        if (dl2 != null)
            dl2.delete();
    }
}

Example 35 with DeepLearningParameters

use of hex.deeplearning.DeepLearningModel.DeepLearningParameters in project h2o-3 by h2oai.

the class DeepLearningTask method makeNeurons.

// Helper
private static Neurons[] makeNeurons(final DeepLearningModelInfo minfo, boolean training) {
    DataInfo dinfo = minfo.data_info();
    final DeepLearningParameters params = minfo.get_params();
    final int[] h = params._hidden;
    // input + hidden + output
    Neurons[] neurons = new Neurons[h.length + 2];
    // input
    neurons[0] = new Neurons.Input(params, minfo.units[0], dinfo);
    // hidden
    for (int i = 0; i < h.length + (params._autoencoder ? 1 : 0); i++) {
        int n = params._autoencoder && i == h.length ? minfo.units[0] : h[i];
        switch(params._activation) {
            case Tanh:
                neurons[i + 1] = new Neurons.Tanh(n);
                break;
            case TanhWithDropout:
                neurons[i + 1] = params._autoencoder && i == h.length ? new Neurons.Tanh(n) : new Neurons.TanhDropout(n);
                break;
            case Rectifier:
                neurons[i + 1] = new Neurons.Rectifier(n);
                break;
            case RectifierWithDropout:
                neurons[i + 1] = params._autoencoder && i == h.length ? new Neurons.Rectifier(n) : new Neurons.RectifierDropout(n);
                break;
            case Maxout:
                neurons[i + 1] = new Neurons.Maxout(params, (short) 2, n);
                break;
            case MaxoutWithDropout:
                neurons[i + 1] = params._autoencoder && i == h.length ? new Neurons.Maxout(params, (short) 2, n) : new Neurons.MaxoutDropout(params, (short) 2, n);
                break;
            case ExpRectifier:
                neurons[i + 1] = new Neurons.ExpRectifier(n);
                break;
            case ExpRectifierWithDropout:
                neurons[i + 1] = params._autoencoder && i == h.length ? new Neurons.ExpRectifier(n) : new Neurons.ExpRectifierDropout(n);
                break;
        }
    }
    if (!params._autoencoder) {
        if (minfo._classification && minfo.get_params()._distribution != DistributionFamily.modified_huber)
            neurons[neurons.length - 1] = new Neurons.Softmax(minfo.units[minfo.units.length - 1]);
        else
            neurons[neurons.length - 1] = new Neurons.Linear();
    }
    //copy parameters from NN, and set previous/input layer links
    for (int i = 0; i < neurons.length; i++) {
        neurons[i].init(neurons, i, params, minfo, training);
        neurons[i]._input = neurons[0];
    }
    //    for (Neurons n : neurons) Log.info(n.toString());
    return neurons;
}