Examples with NormalizerMinMaxScaler org.nd4j.linalg.dataset.api.preprocessor.NormalizerMinMaxScaler used on opensource projects

Example 6 with NormalizerMinMaxScaler

use of org.nd4j.linalg.dataset.api.preprocessor.NormalizerMinMaxScaler in project deeplearning4j by deeplearning4j.

the class GradientCheckTests method testGradientMLP2LayerIrisL1L2Simple.

@Test
public void testGradientMLP2LayerIrisL1L2Simple() {
    //As above (testGradientMLP2LayerIrisSimple()) but with L2, L1, and both L2/L1 applied
    //Need to run gradient through updater, so that L2 can be applied
    String[] activFns = { "sigmoid", "tanh" };
    //If true: run some backprop steps first
    boolean[] characteristic = { false, true };
    LossFunction[] lossFunctions = { LossFunction.MCXENT, LossFunction.MSE };
    //i.e., lossFunctions[i] used with outputActivations[i] here
    String[] outputActivations = { "softmax", "tanh" };
    DataNormalization scaler = new NormalizerMinMaxScaler();
    DataSetIterator iter = new IrisDataSetIterator(150, 150);
    scaler.fit(iter);
    iter.setPreProcessor(scaler);
    DataSet ds = iter.next();
    INDArray input = ds.getFeatureMatrix();
    INDArray labels = ds.getLabels();
    //use l2vals[i] with l1vals[i]
    double[] l2vals = { 0.4, 0.0, 0.4, 0.4 };
    double[] l1vals = { 0.0, 0.0, 0.5, 0.0 };
    double[] biasL2 = { 0.0, 0.0, 0.0, 0.2 };
    double[] biasL1 = { 0.0, 0.0, 0.6, 0.0 };
    for (String afn : activFns) {
        for (boolean doLearningFirst : characteristic) {
            for (int i = 0; i < lossFunctions.length; i++) {
                for (int k = 0; k < l2vals.length; k++) {
                    LossFunction lf = lossFunctions[i];
                    String outputActivation = outputActivations[i];
                    double l2 = l2vals[k];
                    double l1 = l1vals[k];
                    MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder().regularization(true).l2(l2).l1(l1).l2Bias(biasL2[k]).l1Bias(biasL1[k]).optimizationAlgo(OptimizationAlgorithm.CONJUGATE_GRADIENT).seed(12345L).list().layer(0, new DenseLayer.Builder().nIn(4).nOut(3).weightInit(WeightInit.DISTRIBUTION).dist(new NormalDistribution(0, 1)).updater(Updater.NONE).activation(afn).build()).layer(1, new OutputLayer.Builder(lf).nIn(3).nOut(3).weightInit(WeightInit.DISTRIBUTION).dist(new NormalDistribution(0, 1)).updater(Updater.NONE).activation(outputActivation).build()).pretrain(false).backprop(true).build();
                    MultiLayerNetwork mln = new MultiLayerNetwork(conf);
                    mln.init();
                    if (doLearningFirst) {
                        //Run a number of iterations of learning
                        mln.setInput(ds.getFeatures());
                        mln.setLabels(ds.getLabels());
                        mln.computeGradientAndScore();
                        double scoreBefore = mln.score();
                        for (int j = 0; j < 10; j++) mln.fit(ds);
                        mln.computeGradientAndScore();
                        double scoreAfter = mln.score();
                        //Can't test in 'characteristic mode of operation' if not learning
                        String msg = "testGradMLP2LayerIrisSimple() - score did not (sufficiently) decrease during learning - activationFn=" + afn + ", lossFn=" + lf + ", outputActivation=" + outputActivation + ", doLearningFirst=" + doLearningFirst + ", l2=" + l2 + ", l1=" + l1 + " (before=" + scoreBefore + ", scoreAfter=" + scoreAfter + ")";
                        assertTrue(msg, scoreAfter < 0.8 * scoreBefore);
                    }
                    if (PRINT_RESULTS) {
                        System.out.println("testGradientMLP2LayerIrisSimpleRandom() - activationFn=" + afn + ", lossFn=" + lf + ", outputActivation=" + outputActivation + ", doLearningFirst=" + doLearningFirst + ", l2=" + l2 + ", l1=" + l1);
                        for (int j = 0; j < mln.getnLayers(); j++) System.out.println("Layer " + j + " # params: " + mln.getLayer(j).numParams());
                    }
                    boolean gradOK = GradientCheckUtil.checkGradients(mln, DEFAULT_EPS, DEFAULT_MAX_REL_ERROR, DEFAULT_MIN_ABS_ERROR, PRINT_RESULTS, RETURN_ON_FIRST_FAILURE, input, labels);
                    String msg = "testGradMLP2LayerIrisSimple() - activationFn=" + afn + ", lossFn=" + lf + ", outputActivation=" + outputActivation + ", doLearningFirst=" + doLearningFirst + ", l2=" + l2 + ", l1=" + l1;
                    assertTrue(msg, gradOK);
                }
            }
        }
    }
}

Example 7 with NormalizerMinMaxScaler

use of org.nd4j.linalg.dataset.api.preprocessor.NormalizerMinMaxScaler in project deeplearning4j by deeplearning4j.

the class ModelSerializerTest method testWriteMlnModelInputStream.

@Test
public void testWriteMlnModelInputStream() throws Exception {
    int nIn = 5;
    int nOut = 6;
    MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder().seed(12345).regularization(true).l1(0.01).l2(0.01).learningRate(0.1).activation(Activation.TANH).weightInit(WeightInit.XAVIER).list().layer(0, new DenseLayer.Builder().nIn(nIn).nOut(20).build()).layer(1, new DenseLayer.Builder().nIn(20).nOut(30).build()).layer(2, new OutputLayer.Builder().lossFunction(LossFunctions.LossFunction.MSE).nIn(30).nOut(nOut).build()).build();
    MultiLayerNetwork net = new MultiLayerNetwork(conf);
    net.init();
    File tempFile = File.createTempFile("tsfs", "fdfsdf");
    tempFile.deleteOnExit();
    FileOutputStream fos = new FileOutputStream(tempFile);
    ModelSerializer.writeModel(net, fos, true);
    // checking adding of DataNormalization to the model file
    NormalizerMinMaxScaler scaler = new NormalizerMinMaxScaler();
    DataSetIterator iter = new IrisDataSetIterator(150, 150);
    scaler.fit(iter);
    ModelSerializer.addNormalizerToModel(tempFile, scaler);
    NormalizerMinMaxScaler restoredScaler = ModelSerializer.restoreNormalizerFromFile(tempFile);
    assertNotEquals(null, scaler.getMax());
    assertEquals(scaler.getMax(), restoredScaler.getMax());
    assertEquals(scaler.getMin(), restoredScaler.getMin());
    FileInputStream fis = new FileInputStream(tempFile);
    MultiLayerNetwork network = ModelSerializer.restoreMultiLayerNetwork(fis);
    assertEquals(network.getLayerWiseConfigurations().toJson(), net.getLayerWiseConfigurations().toJson());
    assertEquals(net.params(), network.params());
    assertEquals(net.getUpdater(), network.getUpdater());
}