Examples with SplitTestAndTrain org.nd4j.linalg.dataset.SplitTestAndTrain used on opensource projects

Example 6 with SplitTestAndTrain

use of org.nd4j.linalg.dataset.SplitTestAndTrain 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 7 with SplitTestAndTrain

use of org.nd4j.linalg.dataset.SplitTestAndTrain in project deeplearning4j by deeplearning4j.

the class MultiLayerTest method testBatchNorm.

@Test
public void testBatchNorm() {
    Nd4j.getRandom().setSeed(123);
    MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder().optimizationAlgo(OptimizationAlgorithm.LINE_GRADIENT_DESCENT).iterations(5).seed(123).list().layer(0, new DenseLayer.Builder().nIn(4).nOut(3).weightInit(WeightInit.XAVIER).activation(Activation.TANH).build()).layer(1, new DenseLayer.Builder().nIn(3).nOut(2).weightInit(WeightInit.XAVIER).activation(Activation.TANH).build()).layer(2, new BatchNormalization.Builder().nOut(2).build()).layer(3, new org.deeplearning4j.nn.conf.layers.OutputLayer.Builder(LossFunctions.LossFunction.MCXENT).weightInit(WeightInit.XAVIER).activation(Activation.SOFTMAX).nIn(2).nOut(3).build()).backprop(true).pretrain(false).build();
    MultiLayerNetwork network = new MultiLayerNetwork(conf);
    network.init();
    network.setListeners(new ScoreIterationListener(1));
    DataSetIterator iter = new IrisDataSetIterator(150, 150);
    DataSet next = iter.next();
    next.normalizeZeroMeanZeroUnitVariance();
    SplitTestAndTrain trainTest = next.splitTestAndTrain(110);
    network.setLabels(trainTest.getTrain().getLabels());
    network.init();
    network.fit(trainTest.getTrain());
}

Example 8 with SplitTestAndTrain

use of org.nd4j.linalg.dataset.SplitTestAndTrain in project deeplearning4j by deeplearning4j.

the class ManualTests method testCNNActivationsVisualization.

/**
     * This test is for manual execution only, since it's here just to get working CNN and visualize it's layers
     *
     * @throws Exception
     */
@Test
public void testCNNActivationsVisualization() throws Exception {
    final int numRows = 40;
    final int numColumns = 40;
    int nChannels = 3;
    int outputNum = LFWLoader.NUM_LABELS;
    int numSamples = LFWLoader.NUM_IMAGES;
    boolean useSubset = false;
    // numSamples/10;
    int batchSize = 200;
    int iterations = 5;
    int splitTrainNum = (int) (batchSize * .8);
    int seed = 123;
    int listenerFreq = iterations / 5;
    DataSet lfwNext;
    SplitTestAndTrain trainTest;
    DataSet trainInput;
    List<INDArray> testInput = new ArrayList<>();
    List<INDArray> testLabels = new ArrayList<>();
    log.info("Load data....");
    DataSetIterator lfw = new LFWDataSetIterator(batchSize, numSamples, new int[] { numRows, numColumns, nChannels }, outputNum, useSubset, true, 1.0, new Random(seed));
    log.info("Build model....");
    MultiLayerConfiguration.Builder builder = new NeuralNetConfiguration.Builder().seed(seed).iterations(iterations).activation(Activation.RELU).weightInit(WeightInit.XAVIER).gradientNormalization(GradientNormalization.RenormalizeL2PerLayer).optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT).learningRate(0.01).momentum(0.9).regularization(true).updater(Updater.ADAGRAD).useDropConnect(true).list().layer(0, new ConvolutionLayer.Builder(4, 4).name("cnn1").nIn(nChannels).stride(1, 1).nOut(20).build()).layer(1, new SubsamplingLayer.Builder(SubsamplingLayer.PoolingType.MAX, new int[] { 2, 2 }).name("pool1").build()).layer(2, new ConvolutionLayer.Builder(3, 3).name("cnn2").stride(1, 1).nOut(40).build()).layer(3, new SubsamplingLayer.Builder(SubsamplingLayer.PoolingType.MAX, new int[] { 2, 2 }).name("pool2").build()).layer(4, new ConvolutionLayer.Builder(3, 3).name("cnn3").stride(1, 1).nOut(60).build()).layer(5, new SubsamplingLayer.Builder(SubsamplingLayer.PoolingType.MAX, new int[] { 2, 2 }).name("pool3").build()).layer(6, new ConvolutionLayer.Builder(2, 2).name("cnn3").stride(1, 1).nOut(80).build()).layer(7, new DenseLayer.Builder().name("ffn1").nOut(160).dropOut(0.5).build()).layer(8, new OutputLayer.Builder(LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD).nOut(outputNum).activation(Activation.SOFTMAX).build()).backprop(true).pretrain(false);
    new ConvolutionLayerSetup(builder, numRows, numColumns, nChannels);
    MultiLayerNetwork model = new MultiLayerNetwork(builder.build());
    model.init();
    log.info("Train model....");
    model.setListeners(Arrays.asList(new ScoreIterationListener(listenerFreq), new ConvolutionalIterationListener(listenerFreq)));
    while (lfw.hasNext()) {
        lfwNext = lfw.next();
        lfwNext.scale();
        // train set that is the result
        trainTest = lfwNext.splitTestAndTrain(splitTrainNum, new Random(seed));
        // get feature matrix and labels for training
        trainInput = trainTest.getTrain();
        testInput.add(trainTest.getTest().getFeatureMatrix());
        testLabels.add(trainTest.getTest().getLabels());
        model.fit(trainInput);
    }
    log.info("Evaluate model....");
    Evaluation eval = new Evaluation(lfw.getLabels());
    for (int i = 0; i < testInput.size(); i++) {
        INDArray output = model.output(testInput.get(i));
        eval.eval(testLabels.get(i), output);
    }
    INDArray output = model.output(testInput.get(0));
    eval.eval(testLabels.get(0), output);
    log.info(eval.stats());
    log.info("****************Example finished********************");
}

Example 9 with SplitTestAndTrain

use of org.nd4j.linalg.dataset.SplitTestAndTrain in project deeplearning4j by deeplearning4j.

the class FlowIterationListenerTest method setUp.

@Before
public void setUp() throws Exception {
    if (graph == null) {
        int VOCAB_SIZE = 1000;
        ComputationGraphConfiguration configuration = new NeuralNetConfiguration.Builder().regularization(true).l2(0.0001).weightInit(WeightInit.XAVIER).learningRate(0.01).updater(Updater.RMSPROP).optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT).iterations(1).graphBuilder().addInputs("inEn", "inFr").setInputTypes(InputType.recurrent(VOCAB_SIZE + 1), InputType.recurrent(VOCAB_SIZE + 1)).addLayer("embeddingEn", new EmbeddingLayer.Builder().nIn(VOCAB_SIZE + 1).nOut(128).activation(Activation.IDENTITY).build(), "inEn").addLayer("encoder", new GravesLSTM.Builder().nIn(128).nOut(256).activation(Activation.SOFTSIGN).build(), "embeddingEn").addVertex("lastTimeStep", new LastTimeStepVertex("inEn"), "encoder").addVertex("duplicateTimeStep", new DuplicateToTimeSeriesVertex("inFr"), "lastTimeStep").addLayer("embeddingFr", new EmbeddingLayer.Builder().nIn(VOCAB_SIZE + 1).nOut(128).activation(Activation.IDENTITY).build(), "inFr").addVertex("embeddingFrSeq", new PreprocessorVertex(new FeedForwardToRnnPreProcessor()), "embeddingFr").addLayer("decoder", new GravesLSTM.Builder().nIn(128 + 256).nOut(256).activation(Activation.SOFTSIGN).build(), "embeddingFrSeq", "duplicateTimeStep").addLayer("output", new RnnOutputLayer.Builder().nIn(256).nOut(VOCAB_SIZE + 1).activation(Activation.SOFTMAX).build(), "decoder").setOutputs("output").pretrain(false).backprop(true).build();
        graph = new ComputationGraph(configuration);
        graph.init();
        INDArray input = Nd4j.zeros(10, VOCAB_SIZE, 20);
        graph.setInputs(input, input);
    }
    if (network == null) {
        final int numRows = 40;
        final int numColumns = 40;
        int nChannels = 3;
        int outputNum = LFWLoader.NUM_LABELS;
        int numSamples = LFWLoader.NUM_IMAGES;
        boolean useSubset = false;
        // numSamples/10;
        int batchSize = 200;
        int iterations = 5;
        int splitTrainNum = (int) (batchSize * .8);
        int seed = 123;
        int listenerFreq = iterations / 5;
        DataSet lfwNext;
        SplitTestAndTrain trainTest;
        DataSet trainInput;
        List<INDArray> testInput = new ArrayList<>();
        List<INDArray> testLabels = new ArrayList<>();
        MultiLayerConfiguration.Builder builder = new NeuralNetConfiguration.Builder().seed(seed).iterations(iterations).activation(Activation.RELU).weightInit(WeightInit.XAVIER).gradientNormalization(GradientNormalization.RenormalizeL2PerLayer).optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT).learningRate(0.01).momentum(0.9).regularization(true).updater(Updater.ADAGRAD).useDropConnect(true).list().layer(0, new ConvolutionLayer.Builder(4, 4).name("cnn1").nIn(nChannels).stride(1, 1).nOut(20).build()).layer(1, new SubsamplingLayer.Builder(SubsamplingLayer.PoolingType.MAX, new int[] { 2, 2 }).name("pool1").build()).layer(2, new ConvolutionLayer.Builder(3, 3).name("cnn2").stride(1, 1).nOut(40).build()).layer(3, new SubsamplingLayer.Builder(SubsamplingLayer.PoolingType.MAX, new int[] { 2, 2 }).name("pool2").build()).layer(4, new ConvolutionLayer.Builder(3, 3).name("cnn3").stride(1, 1).nOut(60).build()).layer(5, new SubsamplingLayer.Builder(SubsamplingLayer.PoolingType.MAX, new int[] { 2, 2 }).name("pool3").build()).layer(6, new ConvolutionLayer.Builder(2, 2).name("cnn4").stride(1, 1).nOut(80).build()).layer(7, new DenseLayer.Builder().name("ffn1").nOut(160).dropOut(0.5).build()).layer(8, new OutputLayer.Builder(LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD).nOut(outputNum).activation(Activation.SOFTMAX).build()).backprop(true).pretrain(false);
        new ConvolutionLayerSetup(builder, numRows, numColumns, nChannels);
        network = new MultiLayerNetwork(builder.build());
        network.init();
        INDArray input = Nd4j.zeros(10, nChannels, numRows, numColumns);
        network.setInput(input);
    }
}