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

Example 71 with DataSetIterator

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

the class TestSparkMultiLayerParameterAveraging method testIterationCounts.

@Test
public void testIterationCounts() throws Exception {
    int dataSetObjSize = 5;
    int batchSizePerExecutor = 25;
    List<DataSet> list = new ArrayList<>();
    int minibatchesPerWorkerPerEpoch = 10;
    DataSetIterator iter = new MnistDataSetIterator(dataSetObjSize, batchSizePerExecutor * numExecutors() * minibatchesPerWorkerPerEpoch, false);
    while (iter.hasNext()) {
        list.add(iter.next());
    }
    MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder().updater(Updater.RMSPROP).optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT).iterations(1).list().layer(0, new org.deeplearning4j.nn.conf.layers.DenseLayer.Builder().nIn(28 * 28).nOut(50).activation(Activation.TANH).build()).layer(1, new org.deeplearning4j.nn.conf.layers.OutputLayer.Builder(LossFunctions.LossFunction.MCXENT).nIn(50).nOut(10).activation(Activation.SOFTMAX).build()).pretrain(false).backprop(true).build();
    for (int avgFreq : new int[] { 1, 5, 10 }) {
        System.out.println("--- Avg freq " + avgFreq + " ---");
        SparkDl4jMultiLayer sparkNet = new SparkDl4jMultiLayer(sc, conf.clone(), new ParameterAveragingTrainingMaster.Builder(numExecutors(), dataSetObjSize).batchSizePerWorker(batchSizePerExecutor).averagingFrequency(avgFreq).repartionData(Repartition.Always).build());
        sparkNet.setListeners(new ScoreIterationListener(1));
        JavaRDD<DataSet> rdd = sc.parallelize(list);
        assertEquals(0, sparkNet.getNetwork().getLayerWiseConfigurations().getIterationCount());
        sparkNet.fit(rdd);
        assertEquals(minibatchesPerWorkerPerEpoch, sparkNet.getNetwork().getLayerWiseConfigurations().getIterationCount());
        sparkNet.fit(rdd);
        assertEquals(2 * minibatchesPerWorkerPerEpoch, sparkNet.getNetwork().getLayerWiseConfigurations().getIterationCount());
        sparkNet.getTrainingMaster().deleteTempFiles(sc);
    }
}

Example 72 with DataSetIterator

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

the class TestSparkMultiLayerParameterAveraging method testSeedRepeatability.

@Test
public void testSeedRepeatability() throws Exception {
    MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder().seed(12345).updater(Updater.RMSPROP).optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT).iterations(1).weightInit(WeightInit.XAVIER).list().layer(0, new org.deeplearning4j.nn.conf.layers.DenseLayer.Builder().nIn(4).nOut(4).activation(Activation.TANH).build()).layer(1, new org.deeplearning4j.nn.conf.layers.OutputLayer.Builder(LossFunctions.LossFunction.MCXENT).nIn(4).nOut(3).activation(Activation.SOFTMAX).build()).pretrain(false).backprop(true).build();
    Nd4j.getRandom().setSeed(12345);
    MultiLayerNetwork n1 = new MultiLayerNetwork(conf);
    n1.init();
    Nd4j.getRandom().setSeed(12345);
    MultiLayerNetwork n2 = new MultiLayerNetwork(conf);
    n2.init();
    Nd4j.getRandom().setSeed(12345);
    MultiLayerNetwork n3 = new MultiLayerNetwork(conf);
    n3.init();
    SparkDl4jMultiLayer sparkNet1 = new SparkDl4jMultiLayer(sc, n1, new ParameterAveragingTrainingMaster.Builder(1).workerPrefetchNumBatches(5).batchSizePerWorker(5).averagingFrequency(1).repartionData(Repartition.Always).rngSeed(12345).build());
    //Training master IDs are only unique if they are created at least 1 ms apart...
    Thread.sleep(100);
    SparkDl4jMultiLayer sparkNet2 = new SparkDl4jMultiLayer(sc, n2, new ParameterAveragingTrainingMaster.Builder(1).workerPrefetchNumBatches(5).batchSizePerWorker(5).averagingFrequency(1).repartionData(Repartition.Always).rngSeed(12345).build());
    Thread.sleep(100);
    SparkDl4jMultiLayer sparkNet3 = new SparkDl4jMultiLayer(sc, n3, new ParameterAveragingTrainingMaster.Builder(1).workerPrefetchNumBatches(5).batchSizePerWorker(5).averagingFrequency(1).repartionData(Repartition.Always).rngSeed(98765).build());
    List<DataSet> data = new ArrayList<>();
    DataSetIterator iter = new IrisDataSetIterator(1, 150);
    while (iter.hasNext()) data.add(iter.next());
    JavaRDD<DataSet> rdd = sc.parallelize(data);
    sparkNet1.fit(rdd);
    sparkNet2.fit(rdd);
    sparkNet3.fit(rdd);
    INDArray p1 = sparkNet1.getNetwork().params();
    INDArray p2 = sparkNet2.getNetwork().params();
    INDArray p3 = sparkNet3.getNetwork().params();
    sparkNet1.getTrainingMaster().deleteTempFiles(sc);
    sparkNet2.getTrainingMaster().deleteTempFiles(sc);
    sparkNet3.getTrainingMaster().deleteTempFiles(sc);
    assertEquals(p1, p2);
    assertNotEquals(p1, p3);
}

Example 73 with DataSetIterator

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

the class TestRenders method testHistogramComputationGraph.

@Test
public void testHistogramComputationGraph() throws Exception {
    ComputationGraphConfiguration conf = new NeuralNetConfiguration.Builder().optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT).graphBuilder().addInputs("input").addLayer("cnn1", new ConvolutionLayer.Builder(2, 2).stride(2, 2).nIn(1).nOut(3).build(), "input").addLayer("cnn2", new ConvolutionLayer.Builder(4, 4).stride(2, 2).padding(1, 1).nIn(1).nOut(3).build(), "input").addLayer("max1", new SubsamplingLayer.Builder(SubsamplingLayer.PoolingType.MAX).kernelSize(2, 2).build(), "cnn1", "cnn2").addLayer("output", new OutputLayer.Builder().nIn(7 * 7 * 6).nOut(10).build(), "max1").setOutputs("output").inputPreProcessor("cnn1", new FeedForwardToCnnPreProcessor(28, 28, 1)).inputPreProcessor("cnn2", new FeedForwardToCnnPreProcessor(28, 28, 1)).inputPreProcessor("output", new CnnToFeedForwardPreProcessor(7, 7, 6)).pretrain(false).backprop(true).build();
    ComputationGraph graph = new ComputationGraph(conf);
    graph.init();
    graph.setListeners(new HistogramIterationListener(1), new ScoreIterationListener(1));
    DataSetIterator mnist = new MnistDataSetIterator(32, 640, false, true, false, 12345);
    graph.fit(mnist);
}

Example 74 with DataSetIterator

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

the class TestFlowListener method testUI.

@Test
public void testUI() throws Exception {
    // Number of input channels
    int nChannels = 1;
    // The number of possible outcomes
    int outputNum = 10;
    // Test batch size
    int batchSize = 64;
    DataSetIterator mnistTrain = new MnistDataSetIterator(batchSize, true, 12345);
    MultiLayerConfiguration conf = // Training iterations as above
    new NeuralNetConfiguration.Builder().seed(12345).iterations(1).regularization(true).l2(0.0005).learningRate(0.01).weightInit(WeightInit.XAVIER).optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT).updater(Updater.NESTEROVS).momentum(0.9).list().layer(0, new ConvolutionLayer.Builder(5, 5).nIn(nChannels).stride(1, 1).nOut(20).activation(Activation.IDENTITY).build()).layer(1, new SubsamplingLayer.Builder(SubsamplingLayer.PoolingType.MAX).kernelSize(2, 2).stride(2, 2).build()).layer(2, new ConvolutionLayer.Builder(5, 5).stride(1, 1).nOut(50).activation(Activation.IDENTITY).build()).layer(3, new SubsamplingLayer.Builder(SubsamplingLayer.PoolingType.MAX).kernelSize(2, 2).stride(2, 2).build()).layer(4, new DenseLayer.Builder().activation(Activation.RELU).nOut(500).build()).layer(5, new OutputLayer.Builder(LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD).nOut(outputNum).activation(Activation.SOFTMAX).build()).setInputType(//See note below
    InputType.convolutionalFlat(28, 28, 1)).backprop(true).pretrain(false).build();
    MultiLayerNetwork net = new MultiLayerNetwork(conf);
    net.init();
    net.setListeners(new FlowIterationListener(1), new ScoreIterationListener(1));
    for (int i = 0; i < 50; i++) {
        net.fit(mnistTrain.next());
        Thread.sleep(1000);
    }
    Thread.sleep(100000);
}

Example 75 with DataSetIterator

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

the class ManualTests method testHistograms.

@Test
public void testHistograms() throws Exception {
    final int numRows = 28;
    final int numColumns = 28;
    int outputNum = 10;
    int numSamples = 60000;
    int batchSize = 100;
    int iterations = 10;
    int seed = 123;
    int listenerFreq = batchSize / 5;
    log.info("Load data....");
    DataSetIterator iter = new MnistDataSetIterator(batchSize, numSamples, true);
    log.info("Build model....");
    MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder().seed(seed).gradientNormalization(GradientNormalization.ClipElementWiseAbsoluteValue).gradientNormalizationThreshold(1.0).iterations(iterations).momentum(0.5).momentumAfter(Collections.singletonMap(3, 0.9)).optimizationAlgo(OptimizationAlgorithm.CONJUGATE_GRADIENT).list().layer(0, new RBM.Builder().nIn(numRows * numColumns).nOut(500).weightInit(WeightInit.XAVIER).lossFunction(LossFunctions.LossFunction.KL_DIVERGENCE).visibleUnit(RBM.VisibleUnit.BINARY).hiddenUnit(RBM.HiddenUnit.BINARY).build()).layer(1, new RBM.Builder().nIn(500).nOut(250).weightInit(WeightInit.XAVIER).lossFunction(LossFunctions.LossFunction.KL_DIVERGENCE).visibleUnit(RBM.VisibleUnit.BINARY).hiddenUnit(RBM.HiddenUnit.BINARY).build()).layer(2, new RBM.Builder().nIn(250).nOut(200).weightInit(WeightInit.XAVIER).lossFunction(LossFunctions.LossFunction.KL_DIVERGENCE).visibleUnit(RBM.VisibleUnit.BINARY).hiddenUnit(RBM.HiddenUnit.BINARY).build()).layer(3, new OutputLayer.Builder(LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD).activation(Activation.SOFTMAX).nIn(200).nOut(outputNum).build()).pretrain(true).backprop(false).build();
    //        UiServer server = UiServer.getInstance();
    //        UiConnectionInfo connectionInfo = server.getConnectionInfo();
    //        connectionInfo.setSessionId("my session here");
    MultiLayerNetwork model = new MultiLayerNetwork(conf);
    model.init();
    model.setListeners(Arrays.asList(new ScoreIterationListener(listenerFreq), new HistogramIterationListener(listenerFreq), new FlowIterationListener(listenerFreq)));
    log.info("Train model....");
    // achieves end to end pre-training
    model.fit(iter);
    log.info("Evaluate model....");
    Evaluation eval = new Evaluation(outputNum);
    DataSetIterator testIter = new MnistDataSetIterator(100, 10000);
    while (testIter.hasNext()) {
        DataSet testMnist = testIter.next();
        INDArray predict2 = model.output(testMnist.getFeatureMatrix());
        eval.eval(testMnist.getLabels(), predict2);
    }
    log.info(eval.stats());
    log.info("****************Example finished********************");
    fail("Not implemented");
}