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

Example 36 with MnistDataSetIterator

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

the class LocalResponseTest method testMultiCNNLayer.

@Test
public void testMultiCNNLayer() throws Exception {
    MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder().optimizationAlgo(OptimizationAlgorithm.LINE_GRADIENT_DESCENT).iterations(1).seed(123).list().layer(0, new ConvolutionLayer.Builder().nIn(1).nOut(6).weightInit(WeightInit.XAVIER).activation(Activation.RELU).build()).layer(1, new LocalResponseNormalization.Builder().build()).layer(2, new DenseLayer.Builder().nOut(2).build()).layer(3, new OutputLayer.Builder(LossFunctions.LossFunction.MCXENT).weightInit(WeightInit.XAVIER).activation(Activation.SOFTMAX).nIn(2).nOut(10).build()).backprop(true).pretrain(false).setInputType(InputType.convolutionalFlat(28, 28, 1)).build();
    MultiLayerNetwork network = new MultiLayerNetwork(conf);
    network.init();
    DataSetIterator iter = new MnistDataSetIterator(2, 2);
    DataSet next = iter.next();
    network.fit(next);
}

Example 37 with MnistDataSetIterator

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

the class MultiLayerTest method testOutput.

@Test
public void testOutput() throws Exception {
    Nd4j.getRandom().setSeed(12345);
    MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder().regularization(false).learningRate(1.0).weightInit(WeightInit.XAVIER).seed(12345L).list().layer(0, new DenseLayer.Builder().nIn(784).nOut(50).activation(Activation.RELU).build()).layer(1, new OutputLayer.Builder(LossFunctions.LossFunction.MCXENT).activation(Activation.SOFTMAX).nIn(50).nOut(10).build()).pretrain(false).backprop(true).setInputType(InputType.convolutional(28, 28, 1)).build();
    MultiLayerNetwork net = new MultiLayerNetwork(conf);
    net.init();
    DataSetIterator fullData = new MnistDataSetIterator(1, 2);
    net.fit(fullData);
    fullData.reset();
    DataSet expectedSet = fullData.next(2);
    INDArray expectedOut = net.output(expectedSet.getFeatureMatrix(), false);
    fullData.reset();
    INDArray actualOut = net.output(fullData);
    assertEquals(expectedOut, actualOut);
}

Example 38 with MnistDataSetIterator

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

the class RBMTests method testBackprop.

@Test
public void testBackprop() throws Exception {
    int numSamples = 10;
    int batchSize = 10;
    DataSetIterator mnistIter = new MnistDataSetIterator(batchSize, numSamples, true);
    DataSet input = mnistIter.next();
    INDArray features = input.getFeatures();
    mnistIter.reset();
    MultiLayerNetwork rbm = getRBMMLNNet(true, true, features, 50, 10, WeightInit.UNIFORM);
    rbm.fit(mnistIter);
    MultiLayerNetwork rbm2 = getRBMMLNNet(true, true, features, 50, 10, WeightInit.UNIFORM);
    rbm2.fit(mnistIter);
    DataSet test = mnistIter.next();
    Evaluation eval = new Evaluation();
    INDArray output = rbm.output(test.getFeatureMatrix());
    eval.eval(test.getLabels(), output);
    double f1Score = eval.f1();
    Evaluation eval2 = new Evaluation();
    INDArray output2 = rbm2.output(test.getFeatureMatrix());
    eval2.eval(test.getLabels(), output2);
    double f1Score2 = eval2.f1();
    assertEquals(f1Score, f1Score2, 1e-4);
}

Example 39 with MnistDataSetIterator

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

the class TestDecayPolicies method testUpdatingInConf.

@Test
public void testUpdatingInConf() throws Exception {
    OptimizationAlgorithm[] optimizationAlgorithms = new OptimizationAlgorithm[] { OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT, OptimizationAlgorithm.LINE_GRADIENT_DESCENT, OptimizationAlgorithm.CONJUGATE_GRADIENT, OptimizationAlgorithm.LBFGS };
    for (OptimizationAlgorithm oa : optimizationAlgorithms) {
        Map<Integer, Double> momentumSchedule = new HashMap<>();
        double m = 0.001;
        for (int i = 0; i <= 100; i++) {
            momentumSchedule.put(i, Math.min(m, 0.9999));
            m += 0.001;
        }
        Map<Integer, Double> learningRateSchedule = new HashMap<>();
        double lr = 0.1;
        for (int i = 0; i <= 100; i++) {
            learningRateSchedule.put(i, lr);
            lr *= 0.96;
        }
        MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder().optimizationAlgo(oa).iterations(1).learningRateDecayPolicy(LearningRatePolicy.Schedule).learningRateSchedule(learningRateSchedule).updater(org.deeplearning4j.nn.conf.Updater.NESTEROVS).weightInit(WeightInit.XAVIER).momentum(0.9).momentumAfter(momentumSchedule).regularization(true).l2(0.0001).list().layer(0, new DenseLayer.Builder().nIn(784).nOut(10).build()).layer(1, new OutputLayer.Builder().nIn(10).nOut(10).build()).pretrain(false).backprop(true).build();
        MultiLayerNetwork net = new MultiLayerNetwork(conf);
        net.init();
        int last_layer_index = 1;
        DataSetIterator trainIter = new MnistDataSetIterator(64, true, 12345);
        int count = 0;
        while (trainIter.hasNext()) {
            net.fit(trainIter.next());
            // always print the same number (0.1 and 0.9)
            double lrLastLayer = (net.getLayer(last_layer_index)).conf().getLearningRateByParam("W");
            double mLastLayer = (net.getLayer(last_layer_index)).conf().getLayer().getMomentum();
            assertEquals(learningRateSchedule.get(count), lrLastLayer, 1e-6);
            assertEquals(momentumSchedule.get(count), mLastLayer, 1e-6);
            if (count++ >= 100)
                break;
        }
    }
}

Example 40 with MnistDataSetIterator

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

the class TestSparkMultiLayerParameterAveraging method testFitViaStringPathsSize1.

@Test
public void testFitViaStringPathsSize1() throws Exception {
    Path tempDir = Files.createTempDirectory("DL4J-testFitViaStringPathsSize1");
    File tempDirF = tempDir.toFile();
    tempDirF.deleteOnExit();
    int dataSetObjSize = 1;
    int batchSizePerExecutor = 25;
    int numSplits = 10;
    int averagingFrequency = 3;
    int totalExamples = numExecutors() * batchSizePerExecutor * numSplits * averagingFrequency;
    DataSetIterator iter = new MnistDataSetIterator(dataSetObjSize, totalExamples, false);
    int i = 0;
    while (iter.hasNext()) {
        File nextFile = new File(tempDirF, i + ".bin");
        DataSet ds = iter.next();
        ds.save(nextFile);
        i++;
    }
    System.out.println("Saved to: " + tempDirF.getAbsolutePath());
    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();
    SparkDl4jMultiLayer sparkNet = new SparkDl4jMultiLayer(sc, conf, new ParameterAveragingTrainingMaster.Builder(numExecutors(), dataSetObjSize).workerPrefetchNumBatches(5).batchSizePerWorker(batchSizePerExecutor).averagingFrequency(averagingFrequency).repartionData(Repartition.Always).build());
    sparkNet.setCollectTrainingStats(true);
    //List files:
    Configuration config = new Configuration();
    FileSystem hdfs = FileSystem.get(tempDir.toUri(), config);
    RemoteIterator<LocatedFileStatus> fileIter = hdfs.listFiles(new org.apache.hadoop.fs.Path(tempDir.toString()), false);
    List<String> paths = new ArrayList<>();
    while (fileIter.hasNext()) {
        String path = fileIter.next().getPath().toString();
        paths.add(path);
    }
    INDArray paramsBefore = sparkNet.getNetwork().params().dup();
    JavaRDD<String> pathRdd = sc.parallelize(paths);
    sparkNet.fitPaths(pathRdd);
    INDArray paramsAfter = sparkNet.getNetwork().params().dup();
    assertNotEquals(paramsBefore, paramsAfter);
    Thread.sleep(2000);
    SparkTrainingStats stats = sparkNet.getSparkTrainingStats();
    //Expect
    System.out.println(stats.statsAsString());
    assertEquals(numSplits, stats.getValue("ParameterAveragingMasterRepartitionTimesMs").size());
    List<EventStats> list = stats.getValue("ParameterAveragingWorkerFitTimesMs");
    assertEquals(numSplits * numExecutors() * averagingFrequency, list.size());
    for (EventStats es : list) {
        ExampleCountEventStats e = (ExampleCountEventStats) es;
        assertTrue(batchSizePerExecutor * averagingFrequency - 10 >= e.getTotalExampleCount());
    }
    sparkNet.getTrainingMaster().deleteTempFiles(sc);
}