Examples with DuplicateToTimeSeriesVertex org.deeplearning4j.nn.conf.graph.rnn.DuplicateToTimeSeriesVertex used on opensource projects

Example 1 with DuplicateToTimeSeriesVertex

use of org.deeplearning4j.nn.conf.graph.rnn.DuplicateToTimeSeriesVertex in project deeplearning4j by deeplearning4j.

the class TestGraphNodes method testDuplicateToTimeSeriesVertex.

@Test
public void testDuplicateToTimeSeriesVertex() {
    ComputationGraphConfiguration conf = new NeuralNetConfiguration.Builder().graphBuilder().addInputs("in2d", "in3d").addVertex("duplicateTS", new DuplicateToTimeSeriesVertex("in3d"), "in2d").addLayer("out", new OutputLayer.Builder().nIn(1).nOut(1).build(), "duplicateTS").setOutputs("out").build();
    ComputationGraph graph = new ComputationGraph(conf);
    graph.init();
    INDArray in2d = Nd4j.rand(3, 5);
    INDArray in3d = Nd4j.rand(new int[] { 3, 2, 7 });
    graph.setInputs(in2d, in3d);
    INDArray expOut = Nd4j.zeros(3, 5, 7);
    for (int i = 0; i < 7; i++) {
        expOut.put(new INDArrayIndex[] { NDArrayIndex.all(), NDArrayIndex.all(), NDArrayIndex.point(i) }, in2d);
    }
    GraphVertex gv = graph.getVertex("duplicateTS");
    gv.setInputs(in2d);
    INDArray outFwd = gv.doForward(true);
    assertEquals(expOut, outFwd);
    INDArray expOutBackward = expOut.sum(2);
    gv.setEpsilon(expOut);
    INDArray outBwd = gv.doBackward(false).getSecond()[0];
    assertEquals(expOutBackward, outBwd);
    String json = conf.toJson();
    ComputationGraphConfiguration conf2 = ComputationGraphConfiguration.fromJson(json);
    assertEquals(conf, conf2);
}

Example 2 with DuplicateToTimeSeriesVertex

use of org.deeplearning4j.nn.conf.graph.rnn.DuplicateToTimeSeriesVertex in project deeplearning4j by deeplearning4j.

the class GradientCheckTestsComputationGraph method testLSTMWithDuplicateToTimeSeries.

@Test
public void testLSTMWithDuplicateToTimeSeries() {
    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("input1", "input2").setOutputs("out").addLayer("lstm1", new GravesLSTM.Builder().nIn(3).nOut(4).activation(Activation.TANH).build(), "input1").addLayer("lstm2", new GravesLSTM.Builder().nIn(4).nOut(5).activation(Activation.SOFTSIGN).build(), "input2").addVertex("lastTS", new LastTimeStepVertex("input2"), "lstm2").addVertex("duplicate", new DuplicateToTimeSeriesVertex("input2"), "lastTS").addLayer("out", new RnnOutputLayer.Builder().nIn(5 + 4).nOut(3).activation(Activation.SOFTMAX).lossFunction(LossFunctions.LossFunction.MCXENT).build(), "lstm1", "duplicate").pretrain(false).backprop(true).build();
    ComputationGraph graph = new ComputationGraph(conf);
    graph.init();
    Random r = new Random(12345);
    INDArray input1 = Nd4j.rand(new int[] { 3, 3, 5 });
    INDArray input2 = Nd4j.rand(new int[] { 3, 4, 5 });
    INDArray labels = Nd4j.zeros(3, 3, 5);
    for (int i = 0; i < 3; i++) {
        for (int j = 0; j < 5; j++) {
            labels.putScalar(new int[] { i, r.nextInt(3), j }, 1.0);
        }
    }
    if (PRINT_RESULTS) {
        System.out.println("testLSTMWithDuplicateToTimeSeries()");
        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[] { input1, input2 }, new INDArray[] { labels });
    String msg = "testLSTMWithDuplicateToTimeSeries()";
    assertTrue(msg, gradOK);
}

Example 3 with DuplicateToTimeSeriesVertex

use of org.deeplearning4j.nn.conf.graph.rnn.DuplicateToTimeSeriesVertex in project deeplearning4j by deeplearning4j.

the class TestGraphNodes method testJSON.

@Test
public void testJSON() {
    //The config here is non-sense, but that doesn't matter for config -> json -> config test
    ComputationGraphConfiguration conf = new NeuralNetConfiguration.Builder().graphBuilder().addInputs("in").addVertex("v1", new ElementWiseVertex(ElementWiseVertex.Op.Add), "in").addVertex("v2", new org.deeplearning4j.nn.conf.graph.MergeVertex(), "in", "in").addVertex("v3", new PreprocessorVertex(new CnnToFeedForwardPreProcessor(1, 2, 1)), "in").addVertex("v4", new org.deeplearning4j.nn.conf.graph.SubsetVertex(0, 1), "in").addVertex("v5", new DuplicateToTimeSeriesVertex("in"), "in").addVertex("v6", new LastTimeStepVertex("in"), "in").addVertex("v7", new org.deeplearning4j.nn.conf.graph.StackVertex(), "in").addVertex("v8", new org.deeplearning4j.nn.conf.graph.UnstackVertex(0, 1), "in").addLayer("out", new OutputLayer.Builder().nIn(1).nOut(1).build(), "in").setOutputs("out").build();
    String json = conf.toJson();
    ComputationGraphConfiguration conf2 = ComputationGraphConfiguration.fromJson(json);
    assertEquals(conf, conf2);
}

Example 4 with DuplicateToTimeSeriesVertex

use of org.deeplearning4j.nn.conf.graph.rnn.DuplicateToTimeSeriesVertex in project deeplearning4j by deeplearning4j.

the class FlowIterationListenerTest method setUp.

@Before
public void setUp() throws Exception {
    if (graph == null) {
        int VOCAB_SIZE = 1000;
        ComputationGraphConfiguration configuration = new NeuralNetConfiguration.Builder().regularization(true).l2(0.0001).weightInit(WeightInit.XAVIER).learningRate(0.01).updater(Updater.RMSPROP).optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT).iterations(1).graphBuilder().addInputs("inEn", "inFr").setInputTypes(InputType.recurrent(VOCAB_SIZE + 1), InputType.recurrent(VOCAB_SIZE + 1)).addLayer("embeddingEn", new EmbeddingLayer.Builder().nIn(VOCAB_SIZE + 1).nOut(128).activation(Activation.IDENTITY).build(), "inEn").addLayer("encoder", new GravesLSTM.Builder().nIn(128).nOut(256).activation(Activation.SOFTSIGN).build(), "embeddingEn").addVertex("lastTimeStep", new LastTimeStepVertex("inEn"), "encoder").addVertex("duplicateTimeStep", new DuplicateToTimeSeriesVertex("inFr"), "lastTimeStep").addLayer("embeddingFr", new EmbeddingLayer.Builder().nIn(VOCAB_SIZE + 1).nOut(128).activation(Activation.IDENTITY).build(), "inFr").addVertex("embeddingFrSeq", new PreprocessorVertex(new FeedForwardToRnnPreProcessor()), "embeddingFr").addLayer("decoder", new GravesLSTM.Builder().nIn(128 + 256).nOut(256).activation(Activation.SOFTSIGN).build(), "embeddingFrSeq", "duplicateTimeStep").addLayer("output", new RnnOutputLayer.Builder().nIn(256).nOut(VOCAB_SIZE + 1).activation(Activation.SOFTMAX).build(), "decoder").setOutputs("output").pretrain(false).backprop(true).build();
        graph = new ComputationGraph(configuration);
        graph.init();
        INDArray input = Nd4j.zeros(10, VOCAB_SIZE, 20);
        graph.setInputs(input, input);
    }
    if (network == null) {
        final int numRows = 40;
        final int numColumns = 40;
        int nChannels = 3;
        int outputNum = LFWLoader.NUM_LABELS;
        int numSamples = LFWLoader.NUM_IMAGES;
        boolean useSubset = false;
        // numSamples/10;
        int batchSize = 200;
        int iterations = 5;
        int splitTrainNum = (int) (batchSize * .8);
        int seed = 123;
        int listenerFreq = iterations / 5;
        DataSet lfwNext;
        SplitTestAndTrain trainTest;
        DataSet trainInput;
        List<INDArray> testInput = new ArrayList<>();
        List<INDArray> testLabels = new ArrayList<>();
        MultiLayerConfiguration.Builder builder = new NeuralNetConfiguration.Builder().seed(seed).iterations(iterations).activation(Activation.RELU).weightInit(WeightInit.XAVIER).gradientNormalization(GradientNormalization.RenormalizeL2PerLayer).optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT).learningRate(0.01).momentum(0.9).regularization(true).updater(Updater.ADAGRAD).useDropConnect(true).list().layer(0, new ConvolutionLayer.Builder(4, 4).name("cnn1").nIn(nChannels).stride(1, 1).nOut(20).build()).layer(1, new SubsamplingLayer.Builder(SubsamplingLayer.PoolingType.MAX, new int[] { 2, 2 }).name("pool1").build()).layer(2, new ConvolutionLayer.Builder(3, 3).name("cnn2").stride(1, 1).nOut(40).build()).layer(3, new SubsamplingLayer.Builder(SubsamplingLayer.PoolingType.MAX, new int[] { 2, 2 }).name("pool2").build()).layer(4, new ConvolutionLayer.Builder(3, 3).name("cnn3").stride(1, 1).nOut(60).build()).layer(5, new SubsamplingLayer.Builder(SubsamplingLayer.PoolingType.MAX, new int[] { 2, 2 }).name("pool3").build()).layer(6, new ConvolutionLayer.Builder(2, 2).name("cnn4").stride(1, 1).nOut(80).build()).layer(7, new DenseLayer.Builder().name("ffn1").nOut(160).dropOut(0.5).build()).layer(8, new OutputLayer.Builder(LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD).nOut(outputNum).activation(Activation.SOFTMAX).build()).backprop(true).pretrain(false);
        new ConvolutionLayerSetup(builder, numRows, numColumns, nChannels);
        network = new MultiLayerNetwork(builder.build());
        network.init();
        INDArray input = Nd4j.zeros(10, nChannels, numRows, numColumns);
        network.setInput(input);
    }
}