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

Example 11 with IrisDataSetIterator

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

the class GradientCheckTestsComputationGraph method testBasicIrisWithElementWiseNode.

@Test
public void testBasicIrisWithElementWiseNode() {
    ElementWiseVertex.Op[] ops = new ElementWiseVertex.Op[] { ElementWiseVertex.Op.Add, ElementWiseVertex.Op.Subtract };
    for (ElementWiseVertex.Op op : ops) {
        Nd4j.getRandom().setSeed(12345);
        ComputationGraphConfiguration conf = new NeuralNetConfiguration.Builder().seed(12345).optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT).weightInit(WeightInit.DISTRIBUTION).dist(new NormalDistribution(0, 1)).updater(Updater.NONE).learningRate(1.0).graphBuilder().addInputs("input").addLayer("l1", new DenseLayer.Builder().nIn(4).nOut(5).activation(Activation.TANH).build(), "input").addLayer("l2", new DenseLayer.Builder().nIn(4).nOut(5).activation(Activation.SIGMOID).build(), "input").addVertex("elementwise", new ElementWiseVertex(op), "l1", "l2").addLayer("outputLayer", new OutputLayer.Builder().lossFunction(LossFunctions.LossFunction.MCXENT).activation(Activation.SOFTMAX).nIn(5).nOut(3).build(), "elementwise").setOutputs("outputLayer").pretrain(false).backprop(true).build();
        ComputationGraph graph = new ComputationGraph(conf);
        graph.init();
        int numParams = (4 * 5 + 5) + (4 * 5 + 5) + (5 * 3 + 3);
        assertEquals(numParams, graph.numParams());
        Nd4j.getRandom().setSeed(12345);
        int nParams = graph.numParams();
        INDArray newParams = Nd4j.rand(1, nParams);
        graph.setParams(newParams);
        DataSet ds = new IrisDataSetIterator(150, 150).next();
        INDArray min = ds.getFeatureMatrix().min(0);
        INDArray max = ds.getFeatureMatrix().max(0);
        ds.getFeatureMatrix().subiRowVector(min).diviRowVector(max.sub(min));
        INDArray input = ds.getFeatureMatrix();
        INDArray labels = ds.getLabels();
        if (PRINT_RESULTS) {
            System.out.println("testBasicIrisWithElementWiseVertex(op=" + op + ")");
            for (int j = 0; j < graph.getNumLayers(); j++) System.out.println("Layer " + j + " # params: " + graph.getLayer(j).numParams());
        }
        boolean gradOK = GradientCheckUtil.checkGradients(graph, DEFAULT_EPS, DEFAULT_MAX_REL_ERROR, DEFAULT_MIN_ABS_ERROR, PRINT_RESULTS, RETURN_ON_FIRST_FAILURE, new INDArray[] { input }, new INDArray[] { labels });
        String msg = "testBasicIrisWithElementWiseVertex(op=" + op + ")";
        assertTrue(msg, gradOK);
    }
}

Example 12 with IrisDataSetIterator

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

the class TestParallelEarlyStopping method testBadTuning.

@Test
public void testBadTuning() {
    //Test poor tuning (high LR): should terminate on MaxScoreIterationTerminationCondition
    Nd4j.getRandom().setSeed(12345);
    MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder().seed(12345).optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT).iterations(1).updater(Updater.SGD).learningRate(//Intentionally huge LR
    1.0).weightInit(WeightInit.XAVIER).list().layer(0, new OutputLayer.Builder().nIn(4).nOut(3).activation(Activation.SOFTMAX).lossFunction(LossFunctions.LossFunction.MCXENT).build()).pretrain(false).backprop(true).build();
    MultiLayerNetwork net = new MultiLayerNetwork(conf);
    net.setListeners(new ScoreIterationListener(1));
    DataSetIterator irisIter = new IrisDataSetIterator(10, 150);
    EarlyStoppingModelSaver<MultiLayerNetwork> saver = new InMemoryModelSaver<>();
    EarlyStoppingConfiguration<MultiLayerNetwork> esConf = new EarlyStoppingConfiguration.Builder<MultiLayerNetwork>().epochTerminationConditions(new MaxEpochsTerminationCondition(5000)).iterationTerminationConditions(new MaxTimeIterationTerminationCondition(1, TimeUnit.MINUTES), //Initial score is ~2.5
    new MaxScoreIterationTerminationCondition(10)).scoreCalculator(new DataSetLossCalculator(irisIter, true)).modelSaver(saver).build();
    IEarlyStoppingTrainer<MultiLayerNetwork> trainer = new EarlyStoppingParallelTrainer<>(esConf, net, irisIter, null, 2, 2, 1);
    EarlyStoppingResult result = trainer.fit();
    assertTrue(result.getTotalEpochs() < 5);
    assertEquals(EarlyStoppingResult.TerminationReason.IterationTerminationCondition, result.getTerminationReason());
    String expDetails = new MaxScoreIterationTerminationCondition(10).toString();
    assertEquals(expDetails, result.getTerminationDetails());
    assertTrue(result.getBestModelEpoch() <= 0);
    assertNotNull(result.getBestModel());
}

Example 13 with IrisDataSetIterator

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

the class TestParallelEarlyStopping method testEarlyStoppingEveryNEpoch.

// parallel training results vary wildly with expected result
// need to determine if this test is feasible, and how it should
// be properly designed
//    @Test
//    public void testEarlyStoppingIris(){
//        MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder()
//                .optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT).iterations(1)
//                .updater(Updater.SGD)
//                .weightInit(WeightInit.XAVIER)
//                .list()
//                .layer(0,new OutputLayer.Builder().nIn(4).nOut(3).lossFunction(LossFunctions.LossFunction.MCXENT).build())
//                .pretrain(false).backprop(true)
//                .build();
//        MultiLayerNetwork net = new MultiLayerNetwork(conf);
//        net.setListeners(new ScoreIterationListener(1));
//
//        DataSetIterator irisIter = new IrisDataSetIterator(50,600);
//        EarlyStoppingModelSaver<MultiLayerNetwork> saver = new InMemoryModelSaver<>();
//        EarlyStoppingConfiguration<MultiLayerNetwork> esConf = new EarlyStoppingConfiguration.Builder<MultiLayerNetwork>()
//            .epochTerminationConditions(new MaxEpochsTerminationCondition(5))
//            .evaluateEveryNEpochs(1)
//            .iterationTerminationConditions(new MaxTimeIterationTerminationCondition(1, TimeUnit.MINUTES))
//            .scoreCalculator(new DataSetLossCalculator(irisIter,true))
//            .modelSaver(saver)
//            .build();
//
//        IEarlyStoppingTrainer<MultiLayerNetwork> trainer = new EarlyStoppingParallelTrainer<>(esConf,net,irisIter,null,2,2,1);
//
//        EarlyStoppingResult<MultiLayerNetwork> result = trainer.fit();
//        System.out.println(result);
//
//        assertEquals(5, result.getTotalEpochs());
//        assertEquals(EarlyStoppingResult.TerminationReason.EpochTerminationCondition,result.getTerminationReason());
//        Map<Integer,Double> scoreVsIter = result.getScoreVsEpoch();
//        assertEquals(5,scoreVsIter.size());
//        String expDetails = esConf.getEpochTerminationConditions().get(0).toString();
//        assertEquals(expDetails, result.getTerminationDetails());
//
//        MultiLayerNetwork out = result.getBestModel();
//        assertNotNull(out);
//
//        //Check that best score actually matches (returned model vs. manually calculated score)
//        MultiLayerNetwork bestNetwork = result.getBestModel();
//        irisIter.reset();
//        double score = bestNetwork.score(irisIter.next());
//        assertEquals(result.getBestModelScore(), score, 1e-4);
//    }
@Test
public void testEarlyStoppingEveryNEpoch() {
    MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder().optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT).iterations(1).updater(Updater.SGD).weightInit(WeightInit.XAVIER).list().layer(0, new OutputLayer.Builder().nIn(4).nOut(3).lossFunction(LossFunctions.LossFunction.MCXENT).build()).pretrain(false).backprop(true).build();
    MultiLayerNetwork net = new MultiLayerNetwork(conf);
    net.setListeners(new ScoreIterationListener(1));
    DataSetIterator irisIter = new IrisDataSetIterator(50, 600);
    EarlyStoppingModelSaver<MultiLayerNetwork> saver = new InMemoryModelSaver<>();
    EarlyStoppingConfiguration<MultiLayerNetwork> esConf = new EarlyStoppingConfiguration.Builder<MultiLayerNetwork>().epochTerminationConditions(new MaxEpochsTerminationCondition(5)).scoreCalculator(new DataSetLossCalculator(irisIter, true)).evaluateEveryNEpochs(2).modelSaver(saver).build();
    IEarlyStoppingTrainer<MultiLayerNetwork> trainer = new EarlyStoppingParallelTrainer<>(esConf, net, irisIter, null, 2, 6, 1);
    EarlyStoppingResult<MultiLayerNetwork> result = trainer.fit();
    System.out.println(result);
    assertEquals(5, result.getTotalEpochs());
    assertEquals(EarlyStoppingResult.TerminationReason.EpochTerminationCondition, result.getTerminationReason());
}

Example 14 with IrisDataSetIterator

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

the class CNNGradientCheckTest method testGradientCNNL1L2MLN.

@Test
public void testGradientCNNL1L2MLN() {
    //Parameterized test, testing combinations of:
    // (a) activation function
    // (b) Whether to test at random initialization, or after some learning (i.e., 'characteristic mode of operation')
    // (c) Loss function (with specified output activations)
    String[] activFns = { "sigmoid", "tanh" };
    //If true: run some backprop steps first
    boolean[] characteristic = { false, true };
    LossFunctions.LossFunction[] lossFunctions = { LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD, LossFunctions.LossFunction.MSE };
    //i.e., lossFunctions[i] used with outputActivations[i] here
    String[] outputActivations = { "softmax", "tanh" };
    DataSet ds = new IrisDataSetIterator(150, 150).next();
    ds.normalizeZeroMeanZeroUnitVariance();
    INDArray input = ds.getFeatureMatrix();
    INDArray labels = ds.getLabels();
    //use l2vals[i] with l1vals[i]
    double[] l2vals = { 0.4, 0.0, 0.4, 0.4 };
    double[] l1vals = { 0.0, 0.0, 0.5, 0.0 };
    double[] biasL2 = { 0.0, 0.0, 0.0, 0.2 };
    double[] biasL1 = { 0.0, 0.0, 0.6, 0.0 };
    for (String afn : activFns) {
        for (boolean doLearningFirst : characteristic) {
            for (int i = 0; i < lossFunctions.length; i++) {
                for (int k = 0; k < l2vals.length; k++) {
                    LossFunctions.LossFunction lf = lossFunctions[i];
                    String outputActivation = outputActivations[i];
                    double l2 = l2vals[k];
                    double l1 = l1vals[k];
                    MultiLayerConfiguration.Builder builder = new NeuralNetConfiguration.Builder().regularization(true).l2(l2).l1(l1).l2Bias(biasL2[k]).l1Bias(biasL1[k]).optimizationAlgo(OptimizationAlgorithm.CONJUGATE_GRADIENT).seed(12345L).list().layer(0, new ConvolutionLayer.Builder(new int[] { 1, 1 }).nIn(1).nOut(6).weightInit(WeightInit.XAVIER).activation(afn).updater(Updater.NONE).build()).layer(1, new OutputLayer.Builder(lf).activation(outputActivation).nOut(3).weightInit(WeightInit.XAVIER).updater(Updater.NONE).build()).pretrain(false).backprop(true).setInputType(InputType.convolutionalFlat(1, 4, 1));
                    MultiLayerConfiguration conf = builder.build();
                    MultiLayerNetwork mln = new MultiLayerNetwork(conf);
                    mln.init();
                    String testName = new Object() {
                    }.getClass().getEnclosingMethod().getName();
                    if (doLearningFirst) {
                        //Run a number of iterations of learning
                        mln.setInput(ds.getFeatures());
                        mln.setLabels(ds.getLabels());
                        mln.computeGradientAndScore();
                        double scoreBefore = mln.score();
                        for (int j = 0; j < 10; j++) mln.fit(ds);
                        mln.computeGradientAndScore();
                        double scoreAfter = mln.score();
                        //Can't test in 'characteristic mode of operation' if not learning
                        String msg = testName + "- score did not (sufficiently) decrease during learning - activationFn=" + afn + ", lossFn=" + lf + ", outputActivation=" + outputActivation + ", doLearningFirst=" + doLearningFirst + " (before=" + scoreBefore + ", scoreAfter=" + scoreAfter + ")";
                        assertTrue(msg, scoreAfter < 0.8 * scoreBefore);
                    }
                    if (PRINT_RESULTS) {
                        System.out.println(testName + "- activationFn=" + afn + ", lossFn=" + lf + ", outputActivation=" + outputActivation + ", doLearningFirst=" + doLearningFirst);
                        for (int j = 0; j < mln.getnLayers(); j++) System.out.println("Layer " + j + " # params: " + mln.getLayer(j).numParams());
                    }
                    boolean gradOK = GradientCheckUtil.checkGradients(mln, DEFAULT_EPS, DEFAULT_MAX_REL_ERROR, DEFAULT_MIN_ABS_ERROR, PRINT_RESULTS, RETURN_ON_FIRST_FAILURE, input, labels);
                    assertTrue(gradOK);
                }
            }
        }
    }
}

Example 15 with IrisDataSetIterator

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

the class CNNGradientCheckTest method testGradientCNNMLN.

@Test
public void testGradientCNNMLN() {
    //Parameterized test, testing combinations of:
    // (a) activation function
    // (b) Whether to test at random initialization, or after some learning (i.e., 'characteristic mode of operation')
    // (c) Loss function (with specified output activations)
    String[] activFns = { "sigmoid", "tanh" };
    //If true: run some backprop steps first
    boolean[] characteristic = { false, true };
    LossFunctions.LossFunction[] lossFunctions = { LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD, LossFunctions.LossFunction.MSE };
    //i.e., lossFunctions[i] used with outputActivations[i] here
    String[] outputActivations = { "softmax", "tanh" };
    DataSet ds = new IrisDataSetIterator(150, 150).next();
    ds.normalizeZeroMeanZeroUnitVariance();
    INDArray input = ds.getFeatureMatrix();
    INDArray labels = ds.getLabels();
    for (String afn : activFns) {
        for (boolean doLearningFirst : characteristic) {
            for (int i = 0; i < lossFunctions.length; i++) {
                LossFunctions.LossFunction lf = lossFunctions[i];
                String outputActivation = outputActivations[i];
                MultiLayerConfiguration.Builder builder = new NeuralNetConfiguration.Builder().regularization(false).optimizationAlgo(OptimizationAlgorithm.CONJUGATE_GRADIENT).updater(Updater.NONE).weightInit(WeightInit.XAVIER).seed(12345L).list().layer(0, new ConvolutionLayer.Builder(1, 1).nOut(6).activation(afn).build()).layer(1, new OutputLayer.Builder(lf).activation(outputActivation).nOut(3).build()).setInputType(InputType.convolutionalFlat(1, 4, 1)).pretrain(false).backprop(true);
                MultiLayerConfiguration conf = builder.build();
                MultiLayerNetwork mln = new MultiLayerNetwork(conf);
                mln.init();
                String name = new Object() {
                }.getClass().getEnclosingMethod().getName();
                if (doLearningFirst) {
                    //Run a number of iterations of learning
                    mln.setInput(ds.getFeatures());
                    mln.setLabels(ds.getLabels());
                    mln.computeGradientAndScore();
                    double scoreBefore = mln.score();
                    for (int j = 0; j < 10; j++) mln.fit(ds);
                    mln.computeGradientAndScore();
                    double scoreAfter = mln.score();
                    //Can't test in 'characteristic mode of operation' if not learning
                    String msg = name + " - score did not (sufficiently) decrease during learning - activationFn=" + afn + ", lossFn=" + lf + ", outputActivation=" + outputActivation + ", doLearningFirst= " + doLearningFirst + " (before=" + scoreBefore + ", scoreAfter=" + scoreAfter + ")";
                    assertTrue(msg, scoreAfter < 0.8 * scoreBefore);
                }
                if (PRINT_RESULTS) {
                    System.out.println(name + " - activationFn=" + afn + ", lossFn=" + lf + ", outputActivation=" + outputActivation + ", doLearningFirst=" + doLearningFirst);
                    for (int j = 0; j < mln.getnLayers(); j++) System.out.println("Layer " + j + " # params: " + mln.getLayer(j).numParams());
                }
                boolean gradOK = GradientCheckUtil.checkGradients(mln, DEFAULT_EPS, DEFAULT_MAX_REL_ERROR, DEFAULT_MIN_ABS_ERROR, PRINT_RESULTS, RETURN_ON_FIRST_FAILURE, input, labels);
                assertTrue(gradOK);
            }
        }
    }
}