Examples with MnistDataSetIterator org.deeplearning4j.datasets.iterator.impl.MnistDataSetIterator used on opensource projects

Example 1 with MnistDataSetIterator

use of org.deeplearning4j.datasets.iterator.impl.MnistDataSetIterator in project deeplearning4j by deeplearning4j.

the class DataSetIteratorTest method testMnist.

@Test
public void testMnist() throws Exception {
    ClassPathResource cpr = new ClassPathResource("mnist_first_200.txt");
    CSVRecordReader rr = new CSVRecordReader(0, ",");
    rr.initialize(new FileSplit(cpr.getTempFileFromArchive()));
    RecordReaderDataSetIterator dsi = new RecordReaderDataSetIterator(rr, 10, 0, 10);
    MnistDataSetIterator iter = new MnistDataSetIterator(10, 200, false, true, false, 0);
    while (dsi.hasNext()) {
        DataSet dsExp = dsi.next();
        DataSet dsAct = iter.next();
        INDArray fExp = dsExp.getFeatureMatrix();
        fExp.divi(255);
        INDArray lExp = dsExp.getLabels();
        INDArray fAct = dsAct.getFeatureMatrix();
        INDArray lAct = dsAct.getLabels();
        assertEquals(fExp, fAct);
        assertEquals(lExp, lAct);
    }
    assertFalse(iter.hasNext());
}

Example 2 with MnistDataSetIterator

use of org.deeplearning4j.datasets.iterator.impl.MnistDataSetIterator in project deeplearning4j by deeplearning4j.

the class ParallelWrapperTest method testParallelWrapperRun.

@Test
public void testParallelWrapperRun() throws Exception {
    int nChannels = 1;
    int outputNum = 10;
    // for GPU you usually want to have higher batchSize
    int batchSize = 128;
    int nEpochs = 10;
    int iterations = 1;
    int seed = 123;
    log.info("Load data....");
    DataSetIterator mnistTrain = new MnistDataSetIterator(batchSize, true, 12345);
    DataSetIterator mnistTest = new MnistDataSetIterator(batchSize, false, 12345);
    log.info("Build model....");
    MultiLayerConfiguration.Builder builder = new NeuralNetConfiguration.Builder().seed(seed).iterations(iterations).regularization(true).l2(0.0005).learningRate(//.biasLearningRate(0.02)
    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()).backprop(true).pretrain(false);
    // The builder needs the dimensions of the image along with the number of channels. these are 28x28 images in one channel
    new ConvolutionLayerSetup(builder, 28, 28, 1);
    MultiLayerConfiguration conf = builder.build();
    MultiLayerNetwork model = new MultiLayerNetwork(conf);
    model.init();
    // ParallelWrapper will take care of load balancing between GPUs.
    ParallelWrapper wrapper = new ParallelWrapper.Builder(model).prefetchBuffer(24).workers(2).averagingFrequency(3).reportScoreAfterAveraging(true).useLegacyAveraging(true).build();
    log.info("Train model....");
    model.setListeners(new ScoreIterationListener(100));
    long timeX = System.currentTimeMillis();
    for (int i = 0; i < nEpochs; i++) {
        long time1 = System.currentTimeMillis();
        // Please note: we're feeding ParallelWrapper with iterator, not model directly
        //            wrapper.fit(mnistMultiEpochIterator);
        wrapper.fit(mnistTrain);
        long time2 = System.currentTimeMillis();
        log.info("*** Completed epoch {}, time: {} ***", i, (time2 - time1));
    }
    long timeY = System.currentTimeMillis();
    log.info("*** Training complete, time: {} ***", (timeY - timeX));
    log.info("Evaluate model....");
    Evaluation eval = new Evaluation(outputNum);
    while (mnistTest.hasNext()) {
        DataSet ds = mnistTest.next();
        INDArray output = model.output(ds.getFeatureMatrix(), false);
        eval.eval(ds.getLabels(), output);
    }
    log.info(eval.stats());
    mnistTest.reset();
    log.info("****************Example finished********************");
    wrapper.shutdown();
}

Example 3 with MnistDataSetIterator

use of org.deeplearning4j.datasets.iterator.impl.MnistDataSetIterator in project deeplearning4j by deeplearning4j.

the class ParallelWrapperMainTest method runParallelWrapperMain.

@Test
public void runParallelWrapperMain() throws Exception {
    int nChannels = 1;
    int outputNum = 10;
    // for GPU you usually want to have higher batchSize
    int batchSize = 128;
    int nEpochs = 10;
    int iterations = 1;
    int seed = 123;
    int uiPort = new Random().nextInt(1000) + 9000;
    System.setProperty("org.deeplearning4j.ui.port", String.valueOf(uiPort));
    log.info("Load data....");
    DataSetIterator mnistTrain = new MnistDataSetIterator(batchSize, true, 12345);
    DataSetIterator mnistTest = new MnistDataSetIterator(batchSize, false, 12345);
    log.info("Build model....");
    MultiLayerConfiguration.Builder builder = new NeuralNetConfiguration.Builder().seed(seed).iterations(iterations).regularization(true).l2(0.0005).learningRate(//.biasLearningRate(0.02)
    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()).backprop(true).pretrain(false);
    // The builder needs the dimensions of the image along with the number of channels. these are 28x28 images in one channel
    new ConvolutionLayerSetup(builder, 28, 28, 1);
    MultiLayerConfiguration conf = builder.build();
    MultiLayerNetwork model = new MultiLayerNetwork(conf);
    model.init();
    File tempModel = new File("tmpmodel.zip");
    tempModel.deleteOnExit();
    ModelSerializer.writeModel(model, tempModel, false);
    File tmp = new File("tmpmodel.bin");
    tmp.deleteOnExit();
    ParallelWrapperMain parallelWrapperMain = new ParallelWrapperMain();
    parallelWrapperMain.runMain(new String[] { "--modelPath", tempModel.getAbsolutePath(), "--dataSetIteratorFactoryClazz", MnistDataSetIteratorProviderFactory.class.getName(), "--modelOutputPath", tmp.getAbsolutePath(), "--uiUrl", "localhost:" + uiPort });
    Thread.sleep(30000);
}

Example 4 with MnistDataSetIterator

use of org.deeplearning4j.datasets.iterator.impl.MnistDataSetIterator in project deeplearning4j by deeplearning4j.

the class ParameterServerParallelWrapperTest method testWrapper.

@Test
public void testWrapper() throws Exception {
    int nChannels = 1;
    int outputNum = 10;
    // for GPU you usually want to have higher batchSize
    int batchSize = 128;
    int nEpochs = 10;
    int iterations = 1;
    int seed = 123;
    log.info("Load data....");
    DataSetIterator mnistTrain = new MnistDataSetIterator(batchSize, 1000);
    DataSetIterator mnistTest = new MnistDataSetIterator(batchSize, false, 12345);
    log.info("Build model....");
    MultiLayerConfiguration.Builder builder = new NeuralNetConfiguration.Builder().seed(seed).iterations(iterations).regularization(true).l2(0.0005).learningRate(//.biasLearningRate(0.02)
    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(InputType.convolutionalFlat(28, 28, 1)).backprop(true).pretrain(false);
    MultiLayerConfiguration conf = builder.build();
    MultiLayerNetwork model = new MultiLayerNetwork(conf);
    model.init();
    ParameterServerParallelWrapper parameterServerParallelWrapper = ParameterServerParallelWrapper.builder().model(model).multiLayerNetwork(model).numEpochs(10).numWorkers(Runtime.getRuntime().availableProcessors()).statusServerPort(33000).preFetchSize(3).build();
    parameterServerParallelWrapper.fit(mnistTrain);
    parameterServerParallelWrapper.close();
    Thread.sleep(30000);
}

Example 5 with MnistDataSetIterator

use of org.deeplearning4j.datasets.iterator.impl.MnistDataSetIterator in project deeplearning4j by deeplearning4j.

the class MultiNeuralNetConfLayerBuilderTest method testRbmSetup.

@Test
public void testRbmSetup() throws Exception {
    MultiLayerConfiguration multiLayerConfiguration = new NeuralNetConfiguration.Builder().optimizationAlgo(OptimizationAlgorithm.CONJUGATE_GRADIENT).seed(123).iterations(5).maxNumLineSearchIterations(// Magical Optimisation Stuff
    10).regularization(true).list().layer(0, new RBM.Builder(RBM.HiddenUnit.RECTIFIED, RBM.VisibleUnit.GAUSSIAN).nIn(784).nOut(1000).weightInit(WeightInit.XAVIER).activation(Activation.RELU).build()).layer(1, new RBM.Builder(RBM.HiddenUnit.RECTIFIED, RBM.VisibleUnit.GAUSSIAN).nIn(1000).nOut(500).weightInit(WeightInit.XAVIER).activation(Activation.RELU).build()).layer(2, new RBM.Builder(RBM.HiddenUnit.RECTIFIED, RBM.VisibleUnit.GAUSSIAN).nIn(500).nOut(250).weightInit(WeightInit.XAVIER).activation(Activation.RELU).build()).layer(3, new OutputLayer.Builder(LossFunctions.LossFunction.MCXENT).weightInit(WeightInit.XAVIER).activation(Activation.SOFTMAX).nIn(250).nOut(10).build()).pretrain(false).backprop(true).build();
    MultiLayerNetwork network = new MultiLayerNetwork(multiLayerConfiguration);
    network.init();
    DataSet d = new MnistDataSetIterator(2, 2).next();
    org.deeplearning4j.nn.api.Layer firstRbm = network.getLayer(0);
    org.deeplearning4j.nn.api.Layer secondRbm = network.getLayer(1);
    org.deeplearning4j.nn.api.Layer thirdRbm = network.getLayer(2);
    org.deeplearning4j.nn.api.Layer fourthRbm = network.getLayer(3);
    INDArray[] weightMatrices = new INDArray[] { firstRbm.getParam(DefaultParamInitializer.WEIGHT_KEY), secondRbm.getParam(DefaultParamInitializer.WEIGHT_KEY), thirdRbm.getParam(DefaultParamInitializer.WEIGHT_KEY), fourthRbm.getParam(DefaultParamInitializer.WEIGHT_KEY) };
    INDArray[] hiddenBiases = new INDArray[] { firstRbm.getParam(DefaultParamInitializer.BIAS_KEY), secondRbm.getParam(DefaultParamInitializer.BIAS_KEY), thirdRbm.getParam(DefaultParamInitializer.BIAS_KEY), fourthRbm.getParam(DefaultParamInitializer.BIAS_KEY) };
    int[][] shapeAssertions = new int[][] { { 784, 1000 }, { 1000, 500 }, { 500, 250 }, { 250, 10 } };
    int[][] biasAssertions = new int[][] { { 1, 1000 }, { 1, 500 }, { 1, 250 }, { 1, 10 } };
    for (int i = 0; i < shapeAssertions.length; i++) {
        assertArrayEquals(shapeAssertions[i], weightMatrices[i].shape());
        assertArrayEquals(biasAssertions[i], hiddenBiases[i].shape());
    }
    network.fit(d);
}