Examples with OutputLayer org.deeplearning4j.nn.layers.OutputLayer used on opensource projects

Example 1 with OutputLayer

use of org.deeplearning4j.nn.layers.OutputLayer in project deeplearning4j by deeplearning4j.

the class DL4jWorker method call.

@Override
public INDArray call(DataSet v1) throws Exception {
    try {
        Layer network = (Layer) this.network;
        if (network instanceof OutputLayer) {
            OutputLayer o = (OutputLayer) network;
            o.fit(v1);
        } else
            network.fit(v1.getFeatureMatrix());
        return network.params();
    } catch (Exception e) {
        System.err.println("Error with dataset " + v1.numExamples());
        throw e;
    }
}

Example 2 with OutputLayer

use of org.deeplearning4j.nn.layers.OutputLayer in project deeplearning4j by deeplearning4j.

the class BackTrackLineSearchTest method testSingleMaxLineSearch.

@Test
public void testSingleMaxLineSearch() throws Exception {
    double score1, score2;
    OutputLayer layer = getIrisLogisticLayerConfig(Activation.SOFTMAX, 100, LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD);
    int nParams = layer.numParams();
    layer.setBackpropGradientsViewArray(Nd4j.create(1, nParams));
    layer.setInput(irisData.getFeatureMatrix());
    layer.setLabels(irisData.getLabels());
    layer.computeGradientAndScore();
    score1 = layer.score();
    BackTrackLineSearch lineSearch = new BackTrackLineSearch(layer, new NegativeDefaultStepFunction(), layer.getOptimizer());
    double step = lineSearch.optimize(layer.params(), layer.gradient().gradient(), layer.gradient().gradient());
    assertEquals(1.0, step, 1e-3);
}

Example 3 with OutputLayer

use of org.deeplearning4j.nn.layers.OutputLayer in project deeplearning4j by deeplearning4j.

the class BackTrackLineSearchTest method testMultMinLineSearch.

@Test
public void testMultMinLineSearch() throws Exception {
    double score1, score2;
    OutputLayer layer = getIrisLogisticLayerConfig(Activation.SOFTMAX, 100, LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD);
    int nParams = layer.numParams();
    layer.setBackpropGradientsViewArray(Nd4j.create(1, nParams));
    layer.setInput(irisData.getFeatureMatrix());
    layer.setLabels(irisData.getLabels());
    layer.computeGradientAndScore();
    score1 = layer.score();
    INDArray origGradient = layer.gradient().gradient().dup();
    NegativeDefaultStepFunction sf = new NegativeDefaultStepFunction();
    BackTrackLineSearch lineSearch = new BackTrackLineSearch(layer, sf, layer.getOptimizer());
    double step = lineSearch.optimize(layer.params(), layer.gradient().gradient(), layer.gradient().gradient());
    INDArray currParams = layer.params();
    sf.step(currParams, origGradient, step);
    layer.setParams(currParams);
    layer.computeGradientAndScore();
    score2 = layer.score();
    assertTrue("score1=" + score1 + ", score2=" + score2, score1 > score2);
}

Example 4 with OutputLayer

use of org.deeplearning4j.nn.layers.OutputLayer in project deeplearning4j by deeplearning4j.

the class TestSparkLayer method testIris2.

@Test
public void testIris2() throws Exception {
    NeuralNetConfiguration conf = new NeuralNetConfiguration.Builder().optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT).iterations(10).learningRate(1e-1).layer(new org.deeplearning4j.nn.conf.layers.OutputLayer.Builder(LossFunctions.LossFunction.MCXENT).nIn(4).nOut(3).weightInit(WeightInit.XAVIER).activation(Activation.SOFTMAX).build()).build();
    System.out.println("Initializing network");
    SparkDl4jLayer master = new SparkDl4jLayer(sc, conf);
    DataSet d = new IrisDataSetIterator(150, 150).next();
    d.normalizeZeroMeanZeroUnitVariance();
    d.shuffle();
    List<DataSet> next = d.asList();
    JavaRDD<DataSet> data = sc.parallelize(next);
    OutputLayer network2 = (OutputLayer) master.fitDataSet(data);
    Evaluation evaluation = new Evaluation();
    evaluation.eval(d.getLabels(), network2.output(d.getFeatureMatrix()));
    System.out.println(evaluation.stats());
}

Example 5 with OutputLayer

use of org.deeplearning4j.nn.layers.OutputLayer in project deeplearning4j by deeplearning4j.

the class BackTrackLineSearchTest method getIrisLogisticLayerConfig.

private static OutputLayer getIrisLogisticLayerConfig(Activation activationFunction, int maxIterations, LossFunctions.LossFunction lossFunction) {
    NeuralNetConfiguration conf = new NeuralNetConfiguration.Builder().seed(12345L).iterations(1).miniBatch(true).maxNumLineSearchIterations(maxIterations).layer(new org.deeplearning4j.nn.conf.layers.OutputLayer.Builder(lossFunction).nIn(4).nOut(3).activation(activationFunction).weightInit(WeightInit.XAVIER).build()).build();
    int numParams = conf.getLayer().initializer().numParams(conf);
    INDArray params = Nd4j.create(1, numParams);
    return (OutputLayer) conf.getLayer().instantiate(conf, null, 0, params, true);
}