Examples with DataSetIterator org.nd4j.linalg.dataset.api.iterator.DataSetIterator used on opensource projects

Example 96 with DataSetIterator

use of org.nd4j.linalg.dataset.api.iterator.DataSetIterator in project deeplearning4j by deeplearning4j.

the class DropoutLayerTest method testDropoutLayerWithDenseMnist.

@Test
public void testDropoutLayerWithDenseMnist() throws Exception {
    DataSetIterator iter = new MnistDataSetIterator(2, 2);
    DataSet next = iter.next();
    // Run without separate activation layer
    MultiLayerConfiguration confIntegrated = new NeuralNetConfiguration.Builder().optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT).iterations(1).seed(123).list().layer(0, new DenseLayer.Builder().nIn(28 * 28 * 1).nOut(10).activation(Activation.RELU).weightInit(WeightInit.XAVIER).build()).layer(1, new OutputLayer.Builder(LossFunctions.LossFunction.MCXENT).weightInit(WeightInit.XAVIER).activation(Activation.SOFTMAX).dropOut(0.25).nIn(10).nOut(10).build()).backprop(true).pretrain(false).build();
    MultiLayerNetwork netIntegrated = new MultiLayerNetwork(confIntegrated);
    netIntegrated.init();
    netIntegrated.fit(next);
    // Run with separate activation layer
    MultiLayerConfiguration confSeparate = new NeuralNetConfiguration.Builder().optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT).iterations(1).seed(123).list().layer(0, new DenseLayer.Builder().nIn(28 * 28 * 1).nOut(10).activation(Activation.RELU).weightInit(WeightInit.XAVIER).build()).layer(1, new DropoutLayer.Builder(0.25).build()).layer(2, new OutputLayer.Builder(LossFunctions.LossFunction.MCXENT).weightInit(WeightInit.XAVIER).activation(Activation.SOFTMAX).nIn(10).nOut(10).build()).backprop(true).pretrain(false).build();
    MultiLayerNetwork netSeparate = new MultiLayerNetwork(confSeparate);
    netSeparate.init();
    netSeparate.fit(next);
    // check parameters
    assertEquals(netIntegrated.getLayer(0).getParam("W"), netSeparate.getLayer(0).getParam("W"));
    assertEquals(netIntegrated.getLayer(0).getParam("b"), netSeparate.getLayer(0).getParam("b"));
    assertEquals(netIntegrated.getLayer(1).getParam("W"), netSeparate.getLayer(2).getParam("W"));
    assertEquals(netIntegrated.getLayer(1).getParam("b"), netSeparate.getLayer(2).getParam("b"));
    // check activations
    netIntegrated.setInput(next.getFeatureMatrix());
    netSeparate.setInput(next.getFeatureMatrix());
    Nd4j.getRandom().setSeed(12345);
    List<INDArray> actTrainIntegrated = netIntegrated.feedForward(true);
    Nd4j.getRandom().setSeed(12345);
    List<INDArray> actTrainSeparate = netSeparate.feedForward(true);
    assertEquals(actTrainIntegrated.get(1), actTrainSeparate.get(1));
    assertEquals(actTrainIntegrated.get(2), actTrainSeparate.get(3));
    Nd4j.getRandom().setSeed(12345);
    List<INDArray> actTestIntegrated = netIntegrated.feedForward(false);
    Nd4j.getRandom().setSeed(12345);
    List<INDArray> actTestSeparate = netSeparate.feedForward(false);
    assertEquals(actTestIntegrated.get(1), actTrainSeparate.get(1));
    assertEquals(actTestIntegrated.get(2), actTestSeparate.get(3));
}

Example 97 with DataSetIterator

use of org.nd4j.linalg.dataset.api.iterator.DataSetIterator in project deeplearning4j by deeplearning4j.

the class OutputLayerTest method testIris2.

@Test
public void testIris2() {
    NeuralNetConfiguration conf = new NeuralNetConfiguration.Builder().optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT).iterations(10).learningRate(1e-1).layer(new org.deeplearning4j.nn.conf.layers.OutputLayer.Builder().nIn(4).nOut(3).weightInit(WeightInit.XAVIER).activation(Activation.SOFTMAX).lossFunction(LossFunctions.LossFunction.MCXENT).build()).build();
    int numParams = conf.getLayer().initializer().numParams(conf);
    INDArray params = Nd4j.create(1, numParams);
    OutputLayer l = (OutputLayer) conf.getLayer().instantiate(conf, Collections.<IterationListener>singletonList(new ScoreIterationListener(1)), 0, params, true);
    l.setBackpropGradientsViewArray(Nd4j.create(1, params.length()));
    DataSetIterator iter = new IrisDataSetIterator(150, 150);
    DataSet next = iter.next();
    next.shuffle();
    SplitTestAndTrain trainTest = next.splitTestAndTrain(110);
    trainTest.getTrain().normalizeZeroMeanZeroUnitVariance();
    l.fit(trainTest.getTrain());
    DataSet test = trainTest.getTest();
    test.normalizeZeroMeanZeroUnitVariance();
    Evaluation eval = new Evaluation();
    INDArray output = l.output(test.getFeatureMatrix());
    eval.eval(test.getLabels(), output);
    log.info("Score " + eval.stats());
}

Example 98 with DataSetIterator

use of org.nd4j.linalg.dataset.api.iterator.DataSetIterator in project deeplearning4j by deeplearning4j.

the class OutputLayerTest method testIris.

@Test
public void testIris() {
    NeuralNetConfiguration conf = new NeuralNetConfiguration.Builder().optimizationAlgo(OptimizationAlgorithm.LINE_GRADIENT_DESCENT).iterations(5).learningRate(1e-1).layer(new org.deeplearning4j.nn.conf.layers.OutputLayer.Builder().nIn(4).nOut(3).weightInit(WeightInit.XAVIER).activation(Activation.SOFTMAX).lossFunction(LossFunctions.LossFunction.MCXENT).build()).build();
    int numParams = conf.getLayer().initializer().numParams(conf);
    INDArray params = Nd4j.create(1, numParams);
    OutputLayer l = (OutputLayer) conf.getLayer().instantiate(conf, Collections.<IterationListener>singletonList(new ScoreIterationListener(1)), 0, params, true);
    l.setBackpropGradientsViewArray(Nd4j.create(1, params.length()));
    DataSetIterator iter = new IrisDataSetIterator(150, 150);
    DataSet next = iter.next();
    next.shuffle();
    SplitTestAndTrain trainTest = next.splitTestAndTrain(110);
    trainTest.getTrain().normalizeZeroMeanZeroUnitVariance();
    l.fit(trainTest.getTrain());
    DataSet test = trainTest.getTest();
    test.normalizeZeroMeanZeroUnitVariance();
    Evaluation eval = new Evaluation();
    INDArray output = l.output(test.getFeatureMatrix());
    eval.eval(test.getLabels(), output);
    log.info("Score " + eval.stats());
}

Example 99 with DataSetIterator

use of org.nd4j.linalg.dataset.api.iterator.DataSetIterator in project deeplearning4j by deeplearning4j.

the class ActivationLayerTest method testCNNActivationLayer.

@Test
public void testCNNActivationLayer() throws Exception {
    DataSetIterator iter = new MnistDataSetIterator(2, 2);
    DataSet next = iter.next();
    // Run without separate activation layer
    MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder().optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT).iterations(1).seed(123).list().layer(0, new ConvolutionLayer.Builder(4, 4).stride(2, 2).nIn(1).nOut(20).activation(Activation.RELU).weightInit(WeightInit.XAVIER).build()).layer(1, new org.deeplearning4j.nn.conf.layers.OutputLayer.Builder(LossFunctions.LossFunction.MCXENT).weightInit(WeightInit.XAVIER).activation(Activation.SOFTMAX).nOut(10).build()).backprop(true).pretrain(false).setInputType(InputType.convolutionalFlat(28, 28, 1)).build();
    MultiLayerNetwork network = new MultiLayerNetwork(conf);
    network.init();
    network.fit(next);
    // Run with separate activation layer
    MultiLayerConfiguration conf2 = new NeuralNetConfiguration.Builder().optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT).iterations(1).seed(123).list().layer(0, new ConvolutionLayer.Builder(4, 4).stride(2, 2).nIn(1).nOut(20).activation(Activation.IDENTITY).weightInit(WeightInit.XAVIER).build()).layer(1, new org.deeplearning4j.nn.conf.layers.ActivationLayer.Builder().activation(Activation.RELU).build()).layer(2, new OutputLayer.Builder(LossFunctions.LossFunction.MCXENT).weightInit(WeightInit.XAVIER).activation(Activation.SOFTMAX).nOut(10).build()).backprop(true).pretrain(false).setInputType(InputType.convolutionalFlat(28, 28, 1)).build();
    MultiLayerNetwork network2 = new MultiLayerNetwork(conf2);
    network2.init();
    network2.fit(next);
    // check parameters
    assertEquals(network.getLayer(0).getParam("W"), network2.getLayer(0).getParam("W"));
    assertEquals(network.getLayer(1).getParam("W"), network2.getLayer(2).getParam("W"));
    assertEquals(network.getLayer(0).getParam("b"), network2.getLayer(0).getParam("b"));
    // check activations
    network.init();
    network.setInput(next.getFeatureMatrix());
    List<INDArray> activations = network.feedForward(true);
    network2.init();
    network2.setInput(next.getFeatureMatrix());
    List<INDArray> activations2 = network2.feedForward(true);
    assertEquals(activations.get(1).reshape(activations2.get(2).shape()), activations2.get(2));
    assertEquals(activations.get(2), activations2.get(3));
}

Example 100 with DataSetIterator

use of org.nd4j.linalg.dataset.api.iterator.DataSetIterator in project deeplearning4j by deeplearning4j.

the class TestComputationGraphNetwork method testGradientUpdate.

@Test
public void testGradientUpdate() {
    DataSetIterator iter = new IrisDataSetIterator(1, 1);
    Gradient expectedGradient = new DefaultGradient();
    expectedGradient.setGradientFor("first_W", Nd4j.ones(4, 5));
    expectedGradient.setGradientFor("first_b", Nd4j.ones(1, 5));
    expectedGradient.setGradientFor("output_W", Nd4j.ones(5, 3));
    expectedGradient.setGradientFor("output_b", Nd4j.ones(1, 3));
    ComputationGraphConfiguration conf = new NeuralNetConfiguration.Builder().optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT).graphBuilder().addInputs("input").addLayer("first", new DenseLayer.Builder().nIn(4).nOut(5).build(), "input").addLayer("output", new OutputLayer.Builder().nIn(5).nOut(3).build(), "first").setOutputs("output").pretrain(false).backprop(true).build();
    ComputationGraph net = new ComputationGraph(conf);
    net.init();
    net.fit(iter.next());
    Gradient actualGradient = net.gradient;
    assertNotEquals(expectedGradient.getGradientFor("first_W"), actualGradient.getGradientFor("first_W"));
    net.update(expectedGradient);
    actualGradient = net.gradient;
    assertEquals(expectedGradient.getGradientFor("first_W"), actualGradient.getGradientFor("first_W"));
    // Update params with set
    net.setParam("first_W", Nd4j.ones(4, 5));
    net.setParam("first_b", Nd4j.ones(1, 5));
    net.setParam("output_W", Nd4j.ones(5, 3));
    net.setParam("output_b", Nd4j.ones(1, 3));
    INDArray actualParams = net.params();
    // Confirm params
    assertEquals(Nd4j.ones(1, 43), actualParams);
    net.update(expectedGradient);
    actualParams = net.params();
    assertEquals(Nd4j.ones(1, 43).addi(1), actualParams);
}