Examples with MultiLayerConfiguration org.deeplearning4j.nn.conf.MultiLayerConfiguration used on opensource projects

Example 16 with MultiLayerConfiguration

use of org.deeplearning4j.nn.conf.MultiLayerConfiguration in project deeplearning4j by deeplearning4j.

the class TestConvolutionModes method testStrictTruncateConvolutionModeOutput.

@Test
public void testStrictTruncateConvolutionModeOutput() {
    //Idea: with convolution mode == Truncate, input size shouldn't matter (within the bounds of truncated edge),
    // and edge data shouldn't affect the output
    //Use: 9x9, kernel 3, stride 3, padding 0
    // Should get same output for 10x10 and 11x11...
    Nd4j.getRandom().setSeed(12345);
    int[] minibatches = { 1, 3 };
    int[] inDepths = { 1, 3 };
    int[] inSizes = { 9, 10, 11 };
    for (boolean isSubsampling : new boolean[] { false, true }) {
        for (int minibatch : minibatches) {
            for (int inDepth : inDepths) {
                INDArray origData = Nd4j.rand(new int[] { minibatch, inDepth, 9, 9 });
                for (int inSize : inSizes) {
                    for (ConvolutionMode cm : new ConvolutionMode[] { ConvolutionMode.Strict, ConvolutionMode.Truncate }) {
                        INDArray inputData = Nd4j.rand(new int[] { minibatch, inDepth, inSize, inSize });
                        inputData.get(NDArrayIndex.all(), NDArrayIndex.all(), NDArrayIndex.interval(0, 9), NDArrayIndex.interval(0, 9)).assign(origData);
                        Layer layer;
                        if (isSubsampling) {
                            layer = new SubsamplingLayer.Builder().kernelSize(3, 3).stride(3, 3).padding(0, 0).build();
                        } else {
                            layer = new ConvolutionLayer.Builder().kernelSize(3, 3).stride(3, 3).padding(0, 0).nOut(3).build();
                        }
                        MultiLayerNetwork net = null;
                        try {
                            MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder().weightInit(WeightInit.XAVIER).convolutionMode(cm).list().layer(0, layer).layer(1, new OutputLayer.Builder().lossFunction(LossFunctions.LossFunction.MCXENT).nOut(3).build()).setInputType(InputType.convolutional(inSize, inSize, inDepth)).build();
                            net = new MultiLayerNetwork(conf);
                            net.init();
                            if (inSize > 9 && cm == ConvolutionMode.Strict) {
                                fail("Expected exception");
                            }
                        } catch (DL4JException e) {
                            if (inSize == 9 || cm != ConvolutionMode.Strict) {
                                e.printStackTrace();
                                fail("Unexpected exception");
                            }
                            //Expected exception
                            continue;
                        } catch (Exception e) {
                            e.printStackTrace();
                            fail("Unexpected exception");
                        }
                        INDArray out = net.output(origData);
                        INDArray out2 = net.output(inputData);
                        assertEquals(out, out2);
                    }
                }
            }
        }
    }
}

Example 17 with MultiLayerConfiguration

use of org.deeplearning4j.nn.conf.MultiLayerConfiguration in project deeplearning4j by deeplearning4j.

the class TestConvolutionModes method testGlobalLocalConfig.

@Test
public void testGlobalLocalConfig() {
    for (ConvolutionMode cm : new ConvolutionMode[] { ConvolutionMode.Strict, ConvolutionMode.Truncate }) {
        MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder().weightInit(WeightInit.XAVIER).convolutionMode(cm).list().layer(0, new ConvolutionLayer.Builder().kernelSize(3, 3).stride(3, 3).padding(0, 0).nIn(3).nOut(3).build()).layer(1, new ConvolutionLayer.Builder().convolutionMode(ConvolutionMode.Strict).kernelSize(3, 3).stride(3, 3).padding(0, 0).nIn(3).nOut(3).build()).layer(2, new ConvolutionLayer.Builder().convolutionMode(ConvolutionMode.Truncate).kernelSize(3, 3).stride(3, 3).padding(0, 0).nIn(3).nOut(3).build()).layer(3, new ConvolutionLayer.Builder().convolutionMode(ConvolutionMode.Same).kernelSize(3, 3).stride(3, 3).padding(0, 0).nIn(3).nOut(3).build()).layer(4, new SubsamplingLayer.Builder().kernelSize(3, 3).stride(3, 3).padding(0, 0).build()).layer(5, new SubsamplingLayer.Builder().convolutionMode(ConvolutionMode.Strict).kernelSize(3, 3).stride(3, 3).padding(0, 0).build()).layer(6, new SubsamplingLayer.Builder().convolutionMode(ConvolutionMode.Truncate).kernelSize(3, 3).stride(3, 3).padding(0, 0).build()).layer(7, new SubsamplingLayer.Builder().convolutionMode(ConvolutionMode.Same).kernelSize(3, 3).stride(3, 3).padding(0, 0).build()).layer(8, new OutputLayer.Builder().lossFunction(LossFunctions.LossFunction.MCXENT).nOut(3).build()).build();
        assertEquals(cm, ((ConvolutionLayer) conf.getConf(0).getLayer()).getConvolutionMode());
        assertEquals(ConvolutionMode.Strict, ((ConvolutionLayer) conf.getConf(1).getLayer()).getConvolutionMode());
        assertEquals(ConvolutionMode.Truncate, ((ConvolutionLayer) conf.getConf(2).getLayer()).getConvolutionMode());
        assertEquals(ConvolutionMode.Same, ((ConvolutionLayer) conf.getConf(3).getLayer()).getConvolutionMode());
        assertEquals(cm, ((SubsamplingLayer) conf.getConf(4).getLayer()).getConvolutionMode());
        assertEquals(ConvolutionMode.Strict, ((SubsamplingLayer) conf.getConf(5).getLayer()).getConvolutionMode());
        assertEquals(ConvolutionMode.Truncate, ((SubsamplingLayer) conf.getConf(6).getLayer()).getConvolutionMode());
        assertEquals(ConvolutionMode.Same, ((SubsamplingLayer) conf.getConf(7).getLayer()).getConvolutionMode());
    }
}

Example 18 with MultiLayerConfiguration

use of org.deeplearning4j.nn.conf.MultiLayerConfiguration in project deeplearning4j by deeplearning4j.

the class EmbeddingLayerTest method testEmbeddingBackwardPass.

@Test
public void testEmbeddingBackwardPass() {
    //With the same parameters, embedding layer should have same activations as the equivalent one-hot representation
    // input with a DenseLayer
    int nClassesIn = 10;
    MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder().activation(Activation.TANH).list().layer(0, new EmbeddingLayer.Builder().nIn(nClassesIn).nOut(5).build()).layer(1, new OutputLayer.Builder(LossFunctions.LossFunction.MCXENT).nIn(5).nOut(4).activation(Activation.SOFTMAX).build()).pretrain(false).backprop(true).build();
    MultiLayerConfiguration conf2 = new NeuralNetConfiguration.Builder().activation(Activation.TANH).weightInit(WeightInit.XAVIER).list().layer(0, new DenseLayer.Builder().nIn(nClassesIn).nOut(5).build()).layer(1, new OutputLayer.Builder(LossFunctions.LossFunction.MCXENT).nIn(5).nOut(4).activation(Activation.SOFTMAX).build()).pretrain(false).backprop(true).build();
    MultiLayerNetwork net = new MultiLayerNetwork(conf);
    MultiLayerNetwork net2 = new MultiLayerNetwork(conf2);
    net.init();
    net2.init();
    net2.setParams(net.params().dup());
    int batchSize = 3;
    INDArray inEmbedding = Nd4j.create(batchSize, 1);
    INDArray inOneHot = Nd4j.create(batchSize, nClassesIn);
    INDArray outLabels = Nd4j.create(batchSize, 4);
    Random r = new Random(12345);
    for (int i = 0; i < batchSize; i++) {
        int classIdx = r.nextInt(nClassesIn);
        inEmbedding.putScalar(i, classIdx);
        inOneHot.putScalar(new int[] { i, classIdx }, 1.0);
        int labelIdx = r.nextInt(4);
        outLabels.putScalar(new int[] { i, labelIdx }, 1.0);
    }
    net.setInput(inEmbedding);
    net2.setInput(inOneHot);
    net.setLabels(outLabels);
    net2.setLabels(outLabels);
    net.computeGradientAndScore();
    net2.computeGradientAndScore();
    System.out.println(net.score() + "\t" + net2.score());
    assertEquals(net2.score(), net.score(), 1e-6);
    Map<String, INDArray> gradient = net.gradient().gradientForVariable();
    Map<String, INDArray> gradient2 = net2.gradient().gradientForVariable();
    assertEquals(gradient.size(), gradient2.size());
    for (String s : gradient.keySet()) {
        assertEquals(gradient2.get(s), gradient.get(s));
    }
}

Example 19 with MultiLayerConfiguration

use of org.deeplearning4j.nn.conf.MultiLayerConfiguration in project deeplearning4j by deeplearning4j.

the class EmbeddingLayerTest method testEmbeddingForwardPass.

@Test
public void testEmbeddingForwardPass() {
    //With the same parameters, embedding layer should have same activations as the equivalent one-hot representation
    // input with a DenseLayer
    int nClassesIn = 10;
    MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder().activation(Activation.TANH).list().layer(0, new EmbeddingLayer.Builder().nIn(nClassesIn).nOut(5).build()).layer(1, new OutputLayer.Builder().nIn(5).nOut(4).build()).pretrain(false).backprop(true).build();
    MultiLayerConfiguration conf2 = new NeuralNetConfiguration.Builder().activation(Activation.TANH).list().layer(0, new DenseLayer.Builder().nIn(nClassesIn).nOut(5).build()).layer(1, new OutputLayer.Builder().nIn(5).nOut(4).build()).pretrain(false).backprop(true).build();
    MultiLayerNetwork net = new MultiLayerNetwork(conf);
    MultiLayerNetwork net2 = new MultiLayerNetwork(conf2);
    net.init();
    net2.init();
    net2.setParams(net.params().dup());
    int batchSize = 3;
    INDArray inEmbedding = Nd4j.create(batchSize, 1);
    INDArray inOneHot = Nd4j.create(batchSize, nClassesIn);
    Random r = new Random(12345);
    for (int i = 0; i < batchSize; i++) {
        int classIdx = r.nextInt(nClassesIn);
        inEmbedding.putScalar(i, classIdx);
        inOneHot.putScalar(new int[] { i, classIdx }, 1.0);
    }
    List<INDArray> activationsEmbedding = net.feedForward(inEmbedding, false);
    List<INDArray> activationsDense = net2.feedForward(inOneHot, false);
    for (int i = 1; i < 3; i++) {
        INDArray actE = activationsEmbedding.get(i);
        INDArray actD = activationsDense.get(i);
        assertEquals(actE, actD);
    }
}

Example 20 with MultiLayerConfiguration

use of org.deeplearning4j.nn.conf.MultiLayerConfiguration in project deeplearning4j by deeplearning4j.

the class EmbeddingLayerTest method testEmbeddingLayerRNN.

@Test
public void testEmbeddingLayerRNN() {
    int nClassesIn = 10;
    MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder().activation(Activation.TANH).list().layer(0, new EmbeddingLayer.Builder().nIn(nClassesIn).nOut(5).build()).layer(1, new GravesLSTM.Builder().nIn(5).nOut(7).activation(Activation.SOFTSIGN).build()).layer(2, new RnnOutputLayer.Builder(LossFunctions.LossFunction.MCXENT).nIn(7).nOut(4).activation(Activation.SOFTMAX).build()).inputPreProcessor(0, new RnnToFeedForwardPreProcessor()).inputPreProcessor(1, new FeedForwardToRnnPreProcessor()).pretrain(false).backprop(true).build();
    MultiLayerConfiguration conf2 = new NeuralNetConfiguration.Builder().activation(Activation.TANH).weightInit(WeightInit.XAVIER).list().layer(0, new DenseLayer.Builder().nIn(nClassesIn).nOut(5).build()).layer(1, new GravesLSTM.Builder().nIn(5).nOut(7).activation(Activation.SOFTSIGN).build()).layer(2, new RnnOutputLayer.Builder(LossFunctions.LossFunction.MCXENT).nIn(7).nOut(4).activation(Activation.SOFTMAX).build()).inputPreProcessor(0, new RnnToFeedForwardPreProcessor()).inputPreProcessor(1, new FeedForwardToRnnPreProcessor()).pretrain(false).backprop(true).build();
    MultiLayerNetwork net = new MultiLayerNetwork(conf);
    MultiLayerNetwork net2 = new MultiLayerNetwork(conf2);
    net.init();
    net2.init();
    net2.setParams(net.params().dup());
    int batchSize = 3;
    int timeSeriesLength = 8;
    INDArray inEmbedding = Nd4j.create(batchSize, 1, timeSeriesLength);
    INDArray inOneHot = Nd4j.create(batchSize, nClassesIn, timeSeriesLength);
    INDArray outLabels = Nd4j.create(batchSize, 4, timeSeriesLength);
    Random r = new Random(12345);
    for (int i = 0; i < batchSize; i++) {
        for (int j = 0; j < timeSeriesLength; j++) {
            int classIdx = r.nextInt(nClassesIn);
            inEmbedding.putScalar(new int[] { i, 0, j }, classIdx);
            inOneHot.putScalar(new int[] { i, classIdx, j }, 1.0);
            int labelIdx = r.nextInt(4);
            outLabels.putScalar(new int[] { i, labelIdx, j }, 1.0);
        }
    }
    net.setInput(inEmbedding);
    net2.setInput(inOneHot);
    net.setLabels(outLabels);
    net2.setLabels(outLabels);
    net.computeGradientAndScore();
    net2.computeGradientAndScore();
    System.out.println(net.score() + "\t" + net2.score());
    assertEquals(net2.score(), net.score(), 1e-6);
    Map<String, INDArray> gradient = net.gradient().gradientForVariable();
    Map<String, INDArray> gradient2 = net2.gradient().gradientForVariable();
    assertEquals(gradient.size(), gradient2.size());
    for (String s : gradient.keySet()) {
        assertEquals(gradient2.get(s), gradient.get(s));
    }
}