Examples with MLPTrainer org.apache.ignite.ml.nn.MLPTrainer used on opensource projects

Example 1 with MLPTrainer

use of org.apache.ignite.ml.nn.MLPTrainer in project ignite by apache.

the class MLPTrainerExample method main.

/**
 * Executes example.
 *
 * @param args Command line arguments, none required.
 */
public static void main(String[] args) {
    // IMPL NOTE based on MLPGroupTrainerTest#testXOR
    System.out.println(">>> Distributed multilayer perceptron example started.");
    // Start ignite grid.
    try (Ignite ignite = Ignition.start("examples/config/example-ignite.xml")) {
        System.out.println(">>> Ignite grid started.");
        // Create cache with training data.
        CacheConfiguration<Integer, LabeledVector<double[]>> trainingSetCfg = new CacheConfiguration<>();
        trainingSetCfg.setName("TRAINING_SET");
        trainingSetCfg.setAffinity(new RendezvousAffinityFunction(false, 10));
        IgniteCache<Integer, LabeledVector<double[]>> trainingSet = null;
        try {
            trainingSet = ignite.createCache(trainingSetCfg);
            // Fill cache with training data.
            trainingSet.put(0, new LabeledVector<>(VectorUtils.of(0, 0), new double[] { 0 }));
            trainingSet.put(1, new LabeledVector<>(VectorUtils.of(0, 1), new double[] { 1 }));
            trainingSet.put(2, new LabeledVector<>(VectorUtils.of(1, 0), new double[] { 1 }));
            trainingSet.put(3, new LabeledVector<>(VectorUtils.of(1, 1), new double[] { 0 }));
            // Define a layered architecture.
            MLPArchitecture arch = new MLPArchitecture(2).withAddedLayer(10, true, Activators.RELU).withAddedLayer(1, false, Activators.SIGMOID);
            // Define a neural network trainer.
            MLPTrainer<SimpleGDParameterUpdate> trainer = new MLPTrainer<>(arch, LossFunctions.MSE, new UpdatesStrategy<>(new SimpleGDUpdateCalculator(0.1), SimpleGDParameterUpdate.SUM_LOCAL, SimpleGDParameterUpdate.AVG), 3000, 4, 50, 123L);
            // Train neural network and get multilayer perceptron model.
            MultilayerPerceptron mlp = trainer.fit(ignite, trainingSet, new LabeledDummyVectorizer<>());
            int totalCnt = 4;
            int failCnt = 0;
            // Calculate score.
            for (int i = 0; i < 4; i++) {
                LabeledVector<double[]> pnt = trainingSet.get(i);
                Matrix predicted = mlp.predict(new DenseMatrix(new double[][] { { pnt.features().get(0), pnt.features().get(1) } }));
                double predictedVal = predicted.get(0, 0);
                double lbl = pnt.label()[0];
                System.out.printf(">>> key: %d\t\t predicted: %.4f\t\tlabel: %.4f\n", i, predictedVal, lbl);
                failCnt += Math.abs(predictedVal - lbl) < 0.5 ? 0 : 1;
            }
            double failRatio = (double) failCnt / totalCnt;
            System.out.println("\n>>> Fail percentage: " + (failRatio * 100) + "%.");
            System.out.println("\n>>> Distributed multilayer perceptron example completed.");
        } finally {
            trainingSet.destroy();
        }
    } finally {
        System.out.flush();
    }
}

Example 2 with MLPTrainer

use of org.apache.ignite.ml.nn.MLPTrainer in project ignite by apache.

the class StackingTest method testSimpleStack.

/**
 * Tests simple stack training.
 */
@Test
public void testSimpleStack() {
    StackedDatasetTrainer<Vector, Vector, Double, LinearRegressionModel, Double> trainer = new StackedDatasetTrainer<>();
    UpdatesStrategy<SmoothParametrized, SimpleGDParameterUpdate> updatesStgy = new UpdatesStrategy<>(new SimpleGDUpdateCalculator(0.2), SimpleGDParameterUpdate.SUM_LOCAL, SimpleGDParameterUpdate.AVG);
    MLPArchitecture arch = new MLPArchitecture(2).withAddedLayer(10, true, Activators.RELU).withAddedLayer(1, false, Activators.SIGMOID);
    MLPTrainer<SimpleGDParameterUpdate> trainer1 = new MLPTrainer<>(arch, LossFunctions.MSE, updatesStgy, 3000, 10, 50, 123L);
    // Convert model trainer to produce Vector -> Vector model
    DatasetTrainer<AdaptableDatasetModel<Vector, Vector, Matrix, Matrix, MultilayerPerceptron>, Double> mlpTrainer = AdaptableDatasetTrainer.of(trainer1).beforeTrainedModel((Vector v) -> new DenseMatrix(v.asArray(), 1)).afterTrainedModel((Matrix mtx) -> mtx.getRow(0)).withConvertedLabels(VectorUtils::num2Arr);
    final double factor = 3;
    StackedModel<Vector, Vector, Double, LinearRegressionModel> mdl = trainer.withAggregatorTrainer(new LinearRegressionLSQRTrainer().withConvertedLabels(x -> x * factor)).addTrainer(mlpTrainer).withAggregatorInputMerger(VectorUtils::concat).withSubmodelOutput2VectorConverter(IgniteFunction.identity()).withVector2SubmodelInputConverter(IgniteFunction.identity()).withOriginalFeaturesKept(IgniteFunction.identity()).withEnvironmentBuilder(TestUtils.testEnvBuilder()).fit(getCacheMock(xor), parts, new DoubleArrayVectorizer<Integer>().labeled(Vectorizer.LabelCoordinate.LAST));
    assertEquals(0.0 * factor, mdl.predict(VectorUtils.of(0.0, 0.0)), 0.3);
    assertEquals(1.0 * factor, mdl.predict(VectorUtils.of(0.0, 1.0)), 0.3);
    assertEquals(1.0 * factor, mdl.predict(VectorUtils.of(1.0, 0.0)), 0.3);
    assertEquals(0.0 * factor, mdl.predict(VectorUtils.of(1.0, 1.0)), 0.3);
}

Example 3 with MLPTrainer

use of org.apache.ignite.ml.nn.MLPTrainer in project ignite by apache.

the class LinearRegressionSGDTrainer method updateModel.

/**
 * {@inheritDoc}
 */
@Override
protected <K, V> LinearRegressionModel updateModel(LinearRegressionModel mdl, DatasetBuilder<K, V> datasetBuilder, Preprocessor<K, V> extractor) {
    assert updatesStgy != null;
    IgniteFunction<Dataset<EmptyContext, SimpleLabeledDatasetData>, MLPArchitecture> archSupplier = dataset -> {
        int cols = dataset.compute(data -> {
            if (data.getFeatures() == null)
                return null;
            return data.getFeatures().length / data.getRows();
        }, (a, b) -> {
            if (a == null)
                return b == null ? 0 : b;
            if (b == null)
                return a;
            return b;
        });
        MLPArchitecture architecture = new MLPArchitecture(cols);
        architecture = architecture.withAddedLayer(1, true, Activators.LINEAR);
        return architecture;
    };
    MLPTrainer<?> trainer = new MLPTrainer<>(archSupplier, LossFunctions.MSE, updatesStgy, maxIterations, batchSize, locIterations, seed);
    IgniteFunction<LabeledVector<Double>, LabeledVector<double[]>> func = lv -> new LabeledVector<>(lv.features(), new double[] { lv.label() });
    PatchedPreprocessor<K, V, Double, double[]> patchedPreprocessor = new PatchedPreprocessor<>(func, extractor);
    MultilayerPerceptron mlp = Optional.ofNullable(mdl).map(this::restoreMLPState).map(m -> trainer.update(m, datasetBuilder, patchedPreprocessor)).orElseGet(() -> trainer.fit(datasetBuilder, patchedPreprocessor));
    double[] p = mlp.parameters().getStorage().data();
    return new LinearRegressionModel(new DenseVector(Arrays.copyOf(p, p.length - 1)), p[p.length - 1]);
}

Example 4 with MLPTrainer

use of org.apache.ignite.ml.nn.MLPTrainer in project ignite by apache.

the class LogisticRegressionSGDTrainer method updateModel.

/**
 * {@inheritDoc}
 */
@Override
protected <K, V> LogisticRegressionModel updateModel(LogisticRegressionModel mdl, DatasetBuilder<K, V> datasetBuilder, Preprocessor<K, V> extractor) {
    IgniteFunction<Dataset<EmptyContext, SimpleLabeledDatasetData>, MLPArchitecture> archSupplier = dataset -> {
        Integer cols = dataset.compute(data -> {
            if (data.getFeatures() == null)
                return null;
            return data.getFeatures().length / data.getRows();
        }, (a, b) -> {
            // If both are null then zero will be propagated, no good.
            if (a == null)
                return b;
            return a;
        });
        if (cols == null)
            throw new IllegalStateException("Cannot train on empty dataset");
        MLPArchitecture architecture = new MLPArchitecture(cols);
        architecture = architecture.withAddedLayer(1, true, Activators.SIGMOID);
        return architecture;
    };
    MLPTrainer<?> trainer = new MLPTrainer<>(archSupplier, LossFunctions.L2, updatesStgy, maxIterations, batchSize, locIterations, seed).withEnvironmentBuilder(envBuilder);
    MultilayerPerceptron mlp;
    IgniteFunction<LabeledVector<Double>, LabeledVector<double[]>> func = lv -> new LabeledVector<>(lv.features(), new double[] { lv.label() });
    PatchedPreprocessor<K, V, Double, double[]> patchedPreprocessor = new PatchedPreprocessor<>(func, extractor);
    if (mdl != null) {
        mlp = restoreMLPState(mdl);
        mlp = trainer.update(mlp, datasetBuilder, patchedPreprocessor);
    } else
        mlp = trainer.fit(datasetBuilder, patchedPreprocessor);
    double[] params = mlp.parameters().getStorage().data();
    return new LogisticRegressionModel(new DenseVector(Arrays.copyOf(params, params.length - 1)), params[params.length - 1]);
}