Java Code Examples for org.deeplearning4j.nn.multilayer.MultiLayerNetwork#getnLayers()

The following examples show how to use org.deeplearning4j.nn.multilayer.MultiLayerNetwork#getnLayers() . You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.

Example 1

Source File: TrainUtil.java From FancyBing with GNU General Public License v3.0

5 votes

public static MultiLayerNetwork loadNetwork(String fn, double learningRate) throws Exception {
  	System.err.println("Loading model...");
  	File locationToSave = new File(System.getProperty("user.dir") + "/model/" + fn);
MultiLayerNetwork model = ModelSerializer.restoreMultiLayerNetwork(locationToSave);

int numLayers = model.getnLayers();
for (int i = 0; i < numLayers; i++) {
	model.getLayer(i).conf().setLearningRateByParam("W", learningRate);
	model.getLayer(i).conf().setLearningRateByParam("b", learningRate);
}
return model;
  }

Example 2

Source File: NetworkUtils.java From deeplearning4j with Apache License 2.0

5 votes

private static void setLearningRate(MultiLayerNetwork net, double newLr, ISchedule lrSchedule) {
    int nLayers = net.getnLayers();
    for (int i = 0; i < nLayers; i++) {
        setLearningRate(net, i, newLr, lrSchedule, false);
    }
    refreshUpdater(net);
}

Example 3

Source File: LSTMGradientCheckTests.java From deeplearning4j with Apache License 2.0

4 votes

@Test
public void testGradientCnnFfRnn() {
    //Test gradients with CNN -> FF -> LSTM -> RnnOutputLayer
    //time series input/output (i.e., video classification or similar)

    int nChannelsIn = 2;
    int inputSize = 6 * 6 * nChannelsIn; //10px x 10px x 3 channels
    int miniBatchSize = 2;
    int timeSeriesLength = 4;
    int nClasses = 2;

    //Generate
    Nd4j.getRandom().setSeed(12345);
    INDArray input = Nd4j.rand(new int[] {miniBatchSize, inputSize, timeSeriesLength});
    INDArray labels = Nd4j.zeros(miniBatchSize, nClasses, timeSeriesLength);
    Random r = new Random(12345);
    for (int i = 0; i < miniBatchSize; i++) {
        for (int j = 0; j < timeSeriesLength; j++) {
            int idx = r.nextInt(nClasses);
            labels.putScalar(new int[] {i, idx, j}, 1.0);
        }
    }


    MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder().updater(new NoOp()).seed(12345)
                    .dataType(DataType.DOUBLE)
                    .dist(new UniformDistribution(-2, 2)).list()
                    .layer(0, new ConvolutionLayer.Builder(3, 3).nIn(2).nOut(3).stride(1, 1)
                                    .activation(Activation.TANH).build()) //Out: (10-5)/1+1 = 6 -> 6x6x5
                    .layer(1, new SubsamplingLayer.Builder(SubsamplingLayer.PoolingType.MAX).kernelSize(2, 2)
                                    .stride(1, 1).build()) //Out: (6-2)/1+1 = 5 -> 5x5x5
                    .layer(2, new DenseLayer.Builder().nIn(27).nOut(4).activation(Activation.TANH).build())
                    .layer(3, new GravesLSTM.Builder().nIn(4).nOut(3).activation(Activation.TANH).build())
                    .layer(4, new RnnOutputLayer.Builder().lossFunction(LossFunction.MCXENT).nIn(3).nOut(nClasses)
                                    .activation(Activation.SOFTMAX).build())
                    .setInputType(InputType.convolutional(6, 6, 2)).build();

    //Here: ConvolutionLayerSetup in config builder doesn't know that we are expecting time series input, not standard FF input -> override it here
    conf.getInputPreProcessors().put(0, new RnnToCnnPreProcessor(6, 6, 2));

    MultiLayerNetwork mln = new MultiLayerNetwork(conf);
    mln.init();

    System.out.println("Params per layer:");
    for (int i = 0; i < mln.getnLayers(); i++) {
        System.out.println("layer " + i + "\t" + mln.getLayer(i).numParams());
    }

    boolean gradOK = GradientCheckUtil.checkGradients(new GradientCheckUtil.MLNConfig().net(mln).input(input)
            .labels(labels).subset(true).maxPerParam(32));
    assertTrue(gradOK);
    TestUtils.testModelSerialization(mln);
}

Example 4