当前位置: 首页>>代码示例>>Java>>正文

Java MultiLayerNetwork.numParams方法代码示例

本文整理汇总了Java中org.deeplearning4j.nn.multilayer.MultiLayerNetwork.numParams方法的典型用法代码示例。如果您正苦于以下问题：Java MultiLayerNetwork.numParams方法的具体用法？Java MultiLayerNetwork.numParams怎么用？Java MultiLayerNetwork.numParams使用的例子？那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类org.deeplearning4j.nn.multilayer.MultiLayerNetwork的用法示例。


在下文中一共展示了MultiLayerNetwork.numParams方法的15个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Java代码示例。

示例1: getVaeLayer

import org.deeplearning4j.nn.multilayer.MultiLayerNetwork; //导入方法依赖的package包/类
@Override
public VariationalAutoencoder getVaeLayer() {
    MultiLayerNetwork network =
                    new MultiLayerNetwork(MultiLayerConfiguration.fromJson((String) jsonConfig.getValue()));
    network.init();
    INDArray val = ((INDArray) params.value()).unsafeDuplication();
    if (val.length() != network.numParams(false))
        throw new IllegalStateException(
                        "Network did not have same number of parameters as the broadcast set parameters");
    network.setParameters(val);

    Layer l = network.getLayer(0);
    if (!(l instanceof VariationalAutoencoder)) {
        throw new RuntimeException(
                        "Cannot use VaeReconstructionProbWithKeyFunction on network that doesn't have a VAE "
                                        + "layer as layer 0. Layer type: " + l.getClass());
    }
    return (VariationalAutoencoder) l;
}
开发者ID:deeplearning4j，项目名称:deeplearning4j，代码行数:20，代码来源:VaeReconstructionProbWithKeyFunction.java

示例2: getVaeLayer

import org.deeplearning4j.nn.multilayer.MultiLayerNetwork; //导入方法依赖的package包/类
@Override
public VariationalAutoencoder getVaeLayer() {
    MultiLayerNetwork network =
                    new MultiLayerNetwork(MultiLayerConfiguration.fromJson((String) jsonConfig.getValue()));
    network.init();
    INDArray val = ((INDArray) params.value()).unsafeDuplication();
    if (val.length() != network.numParams(false))
        throw new IllegalStateException(
                        "Network did not have same number of parameters as the broadcast set parameters");
    network.setParameters(val);

    Layer l = network.getLayer(0);
    if (!(l instanceof VariationalAutoencoder)) {
        throw new RuntimeException(
                        "Cannot use VaeReconstructionErrorWithKeyFunction on network that doesn't have a VAE "
                                        + "layer as layer 0. Layer type: " + l.getClass());
    }
    return (VariationalAutoencoder) l;
}
开发者ID:deeplearning4j，项目名称:deeplearning4j，代码行数:20，代码来源:VaeReconstructionErrorWithKeyFunction.java

示例3: regressionTestMLP1

import org.deeplearning4j.nn.multilayer.MultiLayerNetwork; //导入方法依赖的package包/类
@Test
public void regressionTestMLP1() throws Exception {

    File f = new ClassPathResource("regression_testing/050/050_ModelSerializer_Regression_MLP_1.zip")
                    .getTempFileFromArchive();

    MultiLayerNetwork net = ModelSerializer.restoreMultiLayerNetwork(f, true);

    MultiLayerConfiguration conf = net.getLayerWiseConfigurations();
    assertEquals(2, conf.getConfs().size());

    assertTrue(conf.isBackprop());
    assertFalse(conf.isPretrain());

    DenseLayer l0 = (DenseLayer) conf.getConf(0).getLayer();
    assertEquals("relu", l0.getActivationFn().toString());
    assertEquals(3, l0.getNIn());
    assertEquals(4, l0.getNOut());
    assertEquals(WeightInit.XAVIER, l0.getWeightInit());
    assertEquals(new Nesterovs(0.15, 0.9), l0.getIUpdater());
    assertEquals(0.15, ((Nesterovs)l0.getIUpdater()).getLearningRate(), 1e-6);

    OutputLayer l1 = (OutputLayer) conf.getConf(1).getLayer();
    assertEquals("softmax", l1.getActivationFn().toString());
    assertTrue(l1.getLossFn() instanceof LossMCXENT);
    assertEquals(4, l1.getNIn());
    assertEquals(5, l1.getNOut());
    assertEquals(WeightInit.XAVIER, l1.getWeightInit());
    assertEquals(new Nesterovs(0.15, 0.9), l1.getIUpdater());
    assertEquals(0.9, ((Nesterovs)l1.getIUpdater()).getMomentum(), 1e-6);
    assertEquals(0.15, ((Nesterovs)l1.getIUpdater()).getLearningRate(), 1e-6);

    int numParams = net.numParams();
    assertEquals(Nd4j.linspace(1, numParams, numParams), net.params());
    int updaterSize = (int) new Nesterovs().stateSize(net.numParams());
    assertEquals(Nd4j.linspace(1, updaterSize, updaterSize), net.getUpdater().getStateViewArray());
}
开发者ID:deeplearning4j，项目名称:deeplearning4j，代码行数:38，代码来源:RegressionTest050.java

示例4: regressionTestMLP1

import org.deeplearning4j.nn.multilayer.MultiLayerNetwork; //导入方法依赖的package包/类
@Test
public void regressionTestMLP1() throws Exception {

    File f = new ClassPathResource("regression_testing/071/071_ModelSerializer_Regression_MLP_1.zip")
                    .getTempFileFromArchive();

    MultiLayerNetwork net = ModelSerializer.restoreMultiLayerNetwork(f, true);

    MultiLayerConfiguration conf = net.getLayerWiseConfigurations();
    assertEquals(2, conf.getConfs().size());

    assertTrue(conf.isBackprop());
    assertFalse(conf.isPretrain());

    DenseLayer l0 = (DenseLayer) conf.getConf(0).getLayer();
    assertEquals("relu", l0.getActivationFn().toString());
    assertEquals(3, l0.getNIn());
    assertEquals(4, l0.getNOut());
    assertEquals(WeightInit.XAVIER, l0.getWeightInit());
    assertEquals(new Nesterovs(0.15, 0.9), l0.getIUpdater());
    assertEquals(0.15, ((Nesterovs)l0.getIUpdater()).getLearningRate(), 1e-6);

    OutputLayer l1 = (OutputLayer) conf.getConf(1).getLayer();
    assertEquals("softmax", l1.getActivationFn().toString());
    assertTrue(l1.getLossFn() instanceof LossMCXENT);
    assertEquals(4, l1.getNIn());
    assertEquals(5, l1.getNOut());
    assertEquals(WeightInit.XAVIER, l1.getWeightInit());
    assertEquals(0.9, ((Nesterovs)l1.getIUpdater()).getMomentum(), 1e-6);
    assertEquals(0.9, ((Nesterovs)l1.getIUpdater()).getMomentum(), 1e-6);
    assertEquals(0.15, ((Nesterovs)l1.getIUpdater()).getLearningRate(), 1e-6);

    int numParams = net.numParams();
    assertEquals(Nd4j.linspace(1, numParams, numParams), net.params());
    int updaterSize = (int) new Nesterovs().stateSize(numParams);
    assertEquals(Nd4j.linspace(1, updaterSize, updaterSize), net.getUpdater().getStateViewArray());
}
开发者ID:deeplearning4j，项目名称:deeplearning4j，代码行数:38，代码来源:RegressionTest071.java

示例5: regressionTestMLP1

import org.deeplearning4j.nn.multilayer.MultiLayerNetwork; //导入方法依赖的package包/类
@Test
public void regressionTestMLP1() throws Exception {

    File f = new ClassPathResource("regression_testing/060/060_ModelSerializer_Regression_MLP_1.zip")
                    .getTempFileFromArchive();

    MultiLayerNetwork net = ModelSerializer.restoreMultiLayerNetwork(f, true);

    MultiLayerConfiguration conf = net.getLayerWiseConfigurations();
    assertEquals(2, conf.getConfs().size());

    assertTrue(conf.isBackprop());
    assertFalse(conf.isPretrain());

    DenseLayer l0 = (DenseLayer) conf.getConf(0).getLayer();
    assertEquals("relu", l0.getActivationFn().toString());
    assertEquals(3, l0.getNIn());
    assertEquals(4, l0.getNOut());
    assertEquals(WeightInit.XAVIER, l0.getWeightInit());
    assertEquals(new Nesterovs(0.15, 0.9), l0.getIUpdater());
    assertEquals(0.15, ((Nesterovs)l0.getIUpdater()).getLearningRate(), 1e-6);

    OutputLayer l1 = (OutputLayer) conf.getConf(1).getLayer();
    assertEquals("softmax", l1.getActivationFn().toString());
    assertTrue(l1.getLossFn() instanceof LossMCXENT);
    assertEquals(4, l1.getNIn());
    assertEquals(5, l1.getNOut());
    assertEquals(WeightInit.XAVIER, l1.getWeightInit());
    assertEquals(new Nesterovs(0.15, 0.9), l1.getIUpdater());
    assertEquals(0.9, ((Nesterovs)l1.getIUpdater()).getMomentum(), 1e-6);
    assertEquals(0.15, ((Nesterovs)l1.getIUpdater()).getLearningRate(), 1e-6);

    int numParams = net.numParams();
    assertEquals(Nd4j.linspace(1, numParams, numParams), net.params());
    int updaterSize = (int) new Nesterovs().stateSize(numParams);
    assertEquals(Nd4j.linspace(1, updaterSize, updaterSize), net.getUpdater().getStateViewArray());
}
开发者ID:deeplearning4j，项目名称:deeplearning4j，代码行数:38，代码来源:RegressionTest060.java

示例6: call

import org.deeplearning4j.nn.multilayer.MultiLayerNetwork; //导入方法依赖的package包/类
@Override
public Iterable<Tuple2<Integer, Double>> call(Iterator<DataSet> dataSetIterator) throws Exception {
    if (!dataSetIterator.hasNext()) {
        return Collections.singletonList(new Tuple2<>(0, 0.0));
    }

    DataSetIterator iter = new IteratorDataSetIterator(dataSetIterator, minibatchSize); //Does batching where appropriate

    MultiLayerNetwork network = new MultiLayerNetwork(MultiLayerConfiguration.fromJson(json));
    network.init();
    INDArray val = params.value().unsafeDuplication(); //.value() object will be shared by all executors on each machine -> OK, as params are not modified by score function
    if (val.length() != network.numParams(false))
        throw new IllegalStateException(
                        "Network did not have same number of parameters as the broadcast set parameters");
    network.setParameters(val);

    List<Tuple2<Integer, Double>> out = new ArrayList<>();
    while (iter.hasNext()) {
        DataSet ds = iter.next();
        double score = network.score(ds, false);
        int numExamples = ds.getFeatureMatrix().size(0);
        out.add(new Tuple2<>(numExamples, score * numExamples));
    }

    Nd4j.getExecutioner().commit();

    return out;
}
开发者ID:deeplearning4j，项目名称:deeplearning4j，代码行数:29，代码来源:ScoreFlatMapFunction.java

示例7: regressionTestMLP2

import org.deeplearning4j.nn.multilayer.MultiLayerNetwork; //导入方法依赖的package包/类
@Test
public void regressionTestMLP2() throws Exception {

    File f = new ClassPathResource("regression_testing/050/050_ModelSerializer_Regression_MLP_2.zip")
                    .getTempFileFromArchive();

    MultiLayerNetwork net = ModelSerializer.restoreMultiLayerNetwork(f, true);

    MultiLayerConfiguration conf = net.getLayerWiseConfigurations();
    assertEquals(2, conf.getConfs().size());

    assertTrue(conf.isBackprop());
    assertFalse(conf.isPretrain());

    DenseLayer l0 = (DenseLayer) conf.getConf(0).getLayer();
    assertTrue(l0.getActivationFn() instanceof ActivationLReLU);
    assertEquals(3, l0.getNIn());
    assertEquals(4, l0.getNOut());
    assertEquals(WeightInit.DISTRIBUTION, l0.getWeightInit());
    assertEquals(new NormalDistribution(0.1, 1.2), l0.getDist());
    assertEquals(new RmsProp(0.15, 0.96, RmsProp.DEFAULT_RMSPROP_EPSILON), l0.getIUpdater());
    assertEquals(0.15, ((RmsProp)l0.getIUpdater()).getLearningRate(), 1e-6);
    assertEquals(new Dropout(0.6), l0.getIDropout());
    assertEquals(0.1, l0.getL1(), 1e-6);
    assertEquals(0.2, l0.getL2(), 1e-6);

    OutputLayer l1 = (OutputLayer) conf.getConf(1).getLayer();
    assertEquals("identity", l1.getActivationFn().toString());
    assertTrue(l1.getLossFn() instanceof LossMSE);
    assertEquals(4, l1.getNIn());
    assertEquals(5, l1.getNOut());
    assertEquals(WeightInit.DISTRIBUTION, l0.getWeightInit());
    assertEquals(new NormalDistribution(0.1, 1.2), l0.getDist());
    assertEquals(new RmsProp(0.15, 0.96, RmsProp.DEFAULT_RMSPROP_EPSILON), l1.getIUpdater());
    assertEquals(0.15, ((RmsProp)l1.getIUpdater()).getLearningRate(), 1e-6);
    assertEquals(new Dropout(0.6), l1.getIDropout());
    assertEquals(0.1, l1.getL1(), 1e-6);
    assertEquals(0.2, l1.getL2(), 1e-6);

    int numParams = net.numParams();
    assertEquals(Nd4j.linspace(1, numParams, numParams), net.params());
    int updaterSize = (int) new RmsProp().stateSize(numParams);
    assertEquals(Nd4j.linspace(1, updaterSize, updaterSize), net.getUpdater().getStateViewArray());
}
开发者ID:deeplearning4j，项目名称:deeplearning4j，代码行数:45，代码来源:RegressionTest050.java

示例8: regressionTestCNN1

import org.deeplearning4j.nn.multilayer.MultiLayerNetwork; //导入方法依赖的package包/类
@Test
public void regressionTestCNN1() throws Exception {

    File f = new ClassPathResource("regression_testing/050/050_ModelSerializer_Regression_CNN_1.zip")
                    .getTempFileFromArchive();

    MultiLayerNetwork net = ModelSerializer.restoreMultiLayerNetwork(f, true);

    MultiLayerConfiguration conf = net.getLayerWiseConfigurations();
    assertEquals(3, conf.getConfs().size());

    assertTrue(conf.isBackprop());
    assertFalse(conf.isPretrain());

    ConvolutionLayer l0 = (ConvolutionLayer) conf.getConf(0).getLayer();
    assertEquals("tanh", l0.getActivationFn().toString());
    assertEquals(3, l0.getNIn());
    assertEquals(3, l0.getNOut());
    assertEquals(WeightInit.RELU, l0.getWeightInit());
    assertEquals(new RmsProp(0.15, 0.96, RmsProp.DEFAULT_RMSPROP_EPSILON), l0.getIUpdater());
    assertEquals(0.15, ((RmsProp)l0.getIUpdater()).getLearningRate(), 1e-6);
    assertArrayEquals(new int[] {2, 2}, l0.getKernelSize());
    assertArrayEquals(new int[] {1, 1}, l0.getStride());
    assertArrayEquals(new int[] {0, 0}, l0.getPadding());
    assertEquals(l0.getConvolutionMode(), ConvolutionMode.Truncate); //Pre-0.7.0: no ConvolutionMode. Want to default to truncate here if not set

    SubsamplingLayer l1 = (SubsamplingLayer) conf.getConf(1).getLayer();
    assertArrayEquals(new int[] {2, 2}, l1.getKernelSize());
    assertArrayEquals(new int[] {1, 1}, l1.getStride());
    assertArrayEquals(new int[] {0, 0}, l1.getPadding());
    assertEquals(PoolingType.MAX, l1.getPoolingType());
    assertEquals(l1.getConvolutionMode(), ConvolutionMode.Truncate); //Pre-0.7.0: no ConvolutionMode. Want to default to truncate here if not set

    OutputLayer l2 = (OutputLayer) conf.getConf(2).getLayer();
    assertEquals("sigmoid", l2.getActivationFn().toString());
    assertTrue(l2.getLossFn() instanceof LossNegativeLogLikelihood);
    assertEquals(26 * 26 * 3, l2.getNIn());
    assertEquals(5, l2.getNOut());
    assertEquals(WeightInit.RELU, l0.getWeightInit());
    assertEquals(new RmsProp(0.15, 0.96, RmsProp.DEFAULT_RMSPROP_EPSILON), l0.getIUpdater());
    assertEquals(0.15, ((RmsProp)l0.getIUpdater()).getLearningRate(), 1e-6);

    int numParams = net.numParams();
    assertEquals(Nd4j.linspace(1, numParams, numParams), net.params());
    int updaterSize = (int) new RmsProp().stateSize(numParams);
    assertEquals(Nd4j.linspace(1, updaterSize, updaterSize), net.getUpdater().getStateViewArray());
}
开发者ID:deeplearning4j，项目名称:deeplearning4j，代码行数:48，代码来源:RegressionTest050.java

示例9: regressionTestMLP1

import org.deeplearning4j.nn.multilayer.MultiLayerNetwork; //导入方法依赖的package包/类
@Test
public void regressionTestMLP1() throws Exception {

    File f = new ClassPathResource("regression_testing/080/080_ModelSerializer_Regression_MLP_1.zip")
                    .getTempFileFromArchive();

    MultiLayerNetwork net = ModelSerializer.restoreMultiLayerNetwork(f, true);

    MultiLayerConfiguration conf = net.getLayerWiseConfigurations();
    assertEquals(2, conf.getConfs().size());

    assertTrue(conf.isBackprop());
    assertFalse(conf.isPretrain());

    DenseLayer l0 = (DenseLayer) conf.getConf(0).getLayer();
    assertTrue(l0.getActivationFn() instanceof ActivationReLU);
    assertEquals(3, l0.getNIn());
    assertEquals(4, l0.getNOut());
    assertEquals(WeightInit.XAVIER, l0.getWeightInit());
    assertTrue(l0.getIUpdater() instanceof Nesterovs);
    Nesterovs n = (Nesterovs) l0.getIUpdater();
    assertEquals(0.9, n.getMomentum(), 1e-6);
    assertEquals(0.15, ((Nesterovs)l0.getIUpdater()).getLearningRate(), 1e-6);
    assertEquals(0.15, n.getLearningRate(), 1e-6);


    OutputLayer l1 = (OutputLayer) conf.getConf(1).getLayer();
    assertTrue(l1.getActivationFn() instanceof ActivationSoftmax);
    assertTrue(l1.getLossFn() instanceof LossMCXENT);
    assertEquals(4, l1.getNIn());
    assertEquals(5, l1.getNOut());
    assertEquals(WeightInit.XAVIER, l1.getWeightInit());
    assertTrue(l1.getIUpdater() instanceof Nesterovs);
    assertEquals(0.9, ((Nesterovs)l1.getIUpdater()).getMomentum(), 1e-6);
    assertEquals(0.15, ((Nesterovs)l1.getIUpdater()).getLearningRate(), 1e-6);
    assertEquals(0.15, n.getLearningRate(), 1e-6);

    int numParams = net.numParams();
    assertEquals(Nd4j.linspace(1, numParams, numParams), net.params());
    int updaterSize = (int) new Nesterovs().stateSize(numParams);
    assertEquals(Nd4j.linspace(1, updaterSize, updaterSize), net.getUpdater().getStateViewArray());
}
开发者ID:deeplearning4j，项目名称:deeplearning4j，代码行数:43，代码来源:RegressionTest080.java

示例10: regressionTestMLP2

import org.deeplearning4j.nn.multilayer.MultiLayerNetwork; //导入方法依赖的package包/类
@Test
public void regressionTestMLP2() throws Exception {

    File f = new ClassPathResource("regression_testing/080/080_ModelSerializer_Regression_MLP_2.zip")
                    .getTempFileFromArchive();

    MultiLayerNetwork net = ModelSerializer.restoreMultiLayerNetwork(f, true);

    MultiLayerConfiguration conf = net.getLayerWiseConfigurations();
    assertEquals(2, conf.getConfs().size());

    assertTrue(conf.isBackprop());
    assertFalse(conf.isPretrain());

    DenseLayer l0 = (DenseLayer) conf.getConf(0).getLayer();
    assertTrue(l0.getActivationFn() instanceof ActivationLReLU);
    assertEquals(3, l0.getNIn());
    assertEquals(4, l0.getNOut());
    assertEquals(WeightInit.DISTRIBUTION, l0.getWeightInit());
    assertEquals(new NormalDistribution(0.1, 1.2), l0.getDist());
    assertTrue(l0.getIUpdater() instanceof RmsProp);
    RmsProp r = (RmsProp) l0.getIUpdater();
    assertEquals(0.96, r.getRmsDecay(), 1e-6);
    assertEquals(0.15, r.getLearningRate(), 1e-6);
    assertEquals(0.15, ((RmsProp)l0.getIUpdater()).getLearningRate(), 1e-6);
    assertEquals(new Dropout(0.6), l0.getIDropout());
    assertEquals(0.1, l0.getL1(), 1e-6);
    assertEquals(0.2, l0.getL2(), 1e-6);
    assertEquals(GradientNormalization.ClipElementWiseAbsoluteValue, l0.getGradientNormalization());
    assertEquals(1.5, l0.getGradientNormalizationThreshold(), 1e-5);

    OutputLayer l1 = (OutputLayer) conf.getConf(1).getLayer();
    assertTrue(l1.getActivationFn() instanceof ActivationIdentity);
    assertTrue(l1.getLossFn() instanceof LossMSE);
    assertEquals(4, l1.getNIn());
    assertEquals(5, l1.getNOut());
    assertEquals(WeightInit.DISTRIBUTION, l1.getWeightInit());
    assertEquals(new NormalDistribution(0.1, 1.2), l1.getDist());
    assertTrue(l1.getIUpdater() instanceof RmsProp);
    r = (RmsProp) l1.getIUpdater();
    assertEquals(0.96, r.getRmsDecay(), 1e-6);
    assertEquals(0.15, r.getLearningRate(), 1e-6);
    assertEquals(0.15, ((RmsProp)l0.getIUpdater()).getLearningRate(), 1e-6);
    assertEquals(new Dropout(0.6), l1.getIDropout());
    assertEquals(0.1, l1.getL1(), 1e-6);
    assertEquals(0.2, l1.getL2(), 1e-6);
    assertEquals(GradientNormalization.ClipElementWiseAbsoluteValue, l1.getGradientNormalization());
    assertEquals(1.5, l1.getGradientNormalizationThreshold(), 1e-5);

    int numParams = net.numParams();
    assertEquals(Nd4j.linspace(1, numParams, numParams), net.params());
    int updaterSize = (int) new RmsProp().stateSize(numParams);
    assertEquals(Nd4j.linspace(1, updaterSize, updaterSize), net.getUpdater().getStateViewArray());
}
开发者ID:deeplearning4j，项目名称:deeplearning4j，代码行数:55，代码来源:RegressionTest080.java

示例11: regressionTestCNN1

import org.deeplearning4j.nn.multilayer.MultiLayerNetwork; //导入方法依赖的package包/类
@Test
public void regressionTestCNN1() throws Exception {

    File f = new ClassPathResource("regression_testing/080/080_ModelSerializer_Regression_CNN_1.zip")
                    .getTempFileFromArchive();

    MultiLayerNetwork net = ModelSerializer.restoreMultiLayerNetwork(f, true);

    MultiLayerConfiguration conf = net.getLayerWiseConfigurations();
    assertEquals(3, conf.getConfs().size());

    assertTrue(conf.isBackprop());
    assertFalse(conf.isPretrain());

    ConvolutionLayer l0 = (ConvolutionLayer) conf.getConf(0).getLayer();
    assertTrue(l0.getActivationFn() instanceof ActivationTanH);
    assertEquals(3, l0.getNIn());
    assertEquals(3, l0.getNOut());
    assertEquals(WeightInit.RELU, l0.getWeightInit());
    assertTrue(l0.getIUpdater() instanceof RmsProp);
    RmsProp r = (RmsProp) l0.getIUpdater();
    assertEquals(0.96, r.getRmsDecay(), 1e-6);
    assertEquals(0.15, r.getLearningRate(), 1e-6);
    assertEquals(0.15, ((RmsProp)l0.getIUpdater()).getLearningRate(), 1e-6);
    assertArrayEquals(new int[] {2, 2}, l0.getKernelSize());
    assertArrayEquals(new int[] {1, 1}, l0.getStride());
    assertArrayEquals(new int[] {0, 0}, l0.getPadding());
    assertEquals(l0.getConvolutionMode(), ConvolutionMode.Same);

    SubsamplingLayer l1 = (SubsamplingLayer) conf.getConf(1).getLayer();
    assertArrayEquals(new int[] {2, 2}, l1.getKernelSize());
    assertArrayEquals(new int[] {1, 1}, l1.getStride());
    assertArrayEquals(new int[] {0, 0}, l1.getPadding());
    assertEquals(PoolingType.MAX, l1.getPoolingType());
    assertEquals(l1.getConvolutionMode(), ConvolutionMode.Same);

    OutputLayer l2 = (OutputLayer) conf.getConf(2).getLayer();
    assertTrue(l2.getActivationFn() instanceof ActivationSigmoid);
    assertTrue(l2.getLossFn() instanceof LossNegativeLogLikelihood);
    assertEquals(26 * 26 * 3, l2.getNIn());
    assertEquals(5, l2.getNOut());
    assertEquals(WeightInit.RELU, l2.getWeightInit());
    assertTrue(l2.getIUpdater() instanceof RmsProp);
    r = (RmsProp) l2.getIUpdater();
    assertEquals(0.96, r.getRmsDecay(), 1e-6);
    assertEquals(0.15, r.getLearningRate(), 1e-6);

    assertTrue(conf.getInputPreProcess(2) instanceof CnnToFeedForwardPreProcessor);

    int numParams = net.numParams();
    assertEquals(Nd4j.linspace(1, numParams, numParams), net.params());
    int updaterSize = (int) new RmsProp().stateSize(numParams);
    assertEquals(Nd4j.linspace(1, updaterSize, updaterSize), net.getUpdater().getStateViewArray());
}
开发者ID:deeplearning4j，项目名称:deeplearning4j，代码行数:55，代码来源:RegressionTest080.java

示例12: regressionTestMLP2

import org.deeplearning4j.nn.multilayer.MultiLayerNetwork; //导入方法依赖的package包/类
@Test
public void regressionTestMLP2() throws Exception {

    File f = new ClassPathResource("regression_testing/071/071_ModelSerializer_Regression_MLP_2.zip")
                    .getTempFileFromArchive();

    MultiLayerNetwork net = ModelSerializer.restoreMultiLayerNetwork(f, true);

    MultiLayerConfiguration conf = net.getLayerWiseConfigurations();
    assertEquals(2, conf.getConfs().size());

    assertTrue(conf.isBackprop());
    assertFalse(conf.isPretrain());

    DenseLayer l0 = (DenseLayer) conf.getConf(0).getLayer();
    assertTrue(l0.getActivationFn() instanceof ActivationLReLU);
    assertEquals(3, l0.getNIn());
    assertEquals(4, l0.getNOut());
    assertEquals(WeightInit.DISTRIBUTION, l0.getWeightInit());
    assertEquals(new NormalDistribution(0.1, 1.2), l0.getDist());
    assertEquals(new RmsProp(0.15, 0.96, RmsProp.DEFAULT_RMSPROP_EPSILON), l0.getIUpdater());
    assertEquals(0.15, ((RmsProp)l0.getIUpdater()).getLearningRate(), 1e-6);
    assertEquals(new Dropout(0.6), l0.getIDropout());
    assertEquals(0.1, l0.getL1(), 1e-6);
    assertEquals(0.2, l0.getL2(), 1e-6);
    assertEquals(GradientNormalization.ClipElementWiseAbsoluteValue, l0.getGradientNormalization());
    assertEquals(1.5, l0.getGradientNormalizationThreshold(), 1e-5);

    OutputLayer l1 = (OutputLayer) conf.getConf(1).getLayer();
    assertTrue(l1.getActivationFn() instanceof ActivationIdentity);
    assertTrue(l1.getLossFn() instanceof LossMSE);
    assertEquals(4, l1.getNIn());
    assertEquals(5, l1.getNOut());
    assertEquals(WeightInit.DISTRIBUTION, l0.getWeightInit());
    assertEquals(new NormalDistribution(0.1, 1.2), l0.getDist());
    assertEquals(new RmsProp(0.15, 0.96, RmsProp.DEFAULT_RMSPROP_EPSILON), l1.getIUpdater());
    assertEquals(0.15, ((RmsProp)l0.getIUpdater()).getLearningRate(), 1e-6);
    assertEquals(new Dropout(0.6), l1.getIDropout());
    assertEquals(0.1, l1.getL1(), 1e-6);
    assertEquals(0.2, l1.getL2(), 1e-6);
    assertEquals(GradientNormalization.ClipElementWiseAbsoluteValue, l1.getGradientNormalization());
    assertEquals(1.5, l1.getGradientNormalizationThreshold(), 1e-5);

    int numParams = net.numParams();
    assertEquals(Nd4j.linspace(1, numParams, numParams), net.params());
    int updaterSize = (int) new RmsProp().stateSize(numParams);
    assertEquals(Nd4j.linspace(1, updaterSize, updaterSize), net.getUpdater().getStateViewArray());
}
开发者ID:deeplearning4j，项目名称:deeplearning4j，代码行数:49，代码来源:RegressionTest071.java

示例13: regressionTestCNN1

import org.deeplearning4j.nn.multilayer.MultiLayerNetwork; //导入方法依赖的package包/类
@Test
public void regressionTestCNN1() throws Exception {

    File f = new ClassPathResource("regression_testing/071/071_ModelSerializer_Regression_CNN_1.zip")
                    .getTempFileFromArchive();

    MultiLayerNetwork net = ModelSerializer.restoreMultiLayerNetwork(f, true);

    MultiLayerConfiguration conf = net.getLayerWiseConfigurations();
    assertEquals(3, conf.getConfs().size());

    assertTrue(conf.isBackprop());
    assertFalse(conf.isPretrain());

    ConvolutionLayer l0 = (ConvolutionLayer) conf.getConf(0).getLayer();
    assertEquals("tanh", l0.getActivationFn().toString());
    assertEquals(3, l0.getNIn());
    assertEquals(3, l0.getNOut());
    assertEquals(WeightInit.RELU, l0.getWeightInit());
    assertEquals(new RmsProp(0.15, 0.96, RmsProp.DEFAULT_RMSPROP_EPSILON), l0.getIUpdater());
    assertEquals(0.15, ((RmsProp)l0.getIUpdater()).getLearningRate(), 1e-6);
    assertArrayEquals(new int[] {2, 2}, l0.getKernelSize());
    assertArrayEquals(new int[] {1, 1}, l0.getStride());
    assertArrayEquals(new int[] {0, 0}, l0.getPadding());
    assertEquals(l0.getConvolutionMode(), ConvolutionMode.Same);

    SubsamplingLayer l1 = (SubsamplingLayer) conf.getConf(1).getLayer();
    assertArrayEquals(new int[] {2, 2}, l1.getKernelSize());
    assertArrayEquals(new int[] {1, 1}, l1.getStride());
    assertArrayEquals(new int[] {0, 0}, l1.getPadding());
    assertEquals(PoolingType.MAX, l1.getPoolingType());
    assertEquals(l1.getConvolutionMode(), ConvolutionMode.Same);

    OutputLayer l2 = (OutputLayer) conf.getConf(2).getLayer();
    assertEquals("sigmoid", l2.getActivationFn().toString());
    assertTrue(l2.getLossFn() instanceof LossNegativeLogLikelihood); //TODO
    assertEquals(26 * 26 * 3, l2.getNIn());
    assertEquals(5, l2.getNOut());
    assertEquals(WeightInit.RELU, l0.getWeightInit());
    assertEquals(new RmsProp(0.15, 0.96, RmsProp.DEFAULT_RMSPROP_EPSILON), l0.getIUpdater());
    assertEquals(0.15, ((RmsProp)l0.getIUpdater()).getLearningRate(), 1e-6);

    assertTrue(conf.getInputPreProcess(2) instanceof CnnToFeedForwardPreProcessor);

    int numParams = net.numParams();
    assertEquals(Nd4j.linspace(1, numParams, numParams), net.params());
    int updaterSize = (int) new RmsProp().stateSize(numParams);
    assertEquals(Nd4j.linspace(1, updaterSize, updaterSize), net.getUpdater().getStateViewArray());
}
开发者ID:deeplearning4j，项目名称:deeplearning4j，代码行数:50，代码来源:RegressionTest071.java

示例14: regressionTestMLP2

import org.deeplearning4j.nn.multilayer.MultiLayerNetwork; //导入方法依赖的package包/类
@Test
public void regressionTestMLP2() throws Exception {

    File f = new ClassPathResource("regression_testing/060/060_ModelSerializer_Regression_MLP_2.zip")
                    .getTempFileFromArchive();

    MultiLayerNetwork net = ModelSerializer.restoreMultiLayerNetwork(f, true);

    MultiLayerConfiguration conf = net.getLayerWiseConfigurations();
    assertEquals(2, conf.getConfs().size());

    assertTrue(conf.isBackprop());
    assertFalse(conf.isPretrain());

    DenseLayer l0 = (DenseLayer) conf.getConf(0).getLayer();
    assertTrue(l0.getActivationFn() instanceof ActivationLReLU);
    assertEquals(3, l0.getNIn());
    assertEquals(4, l0.getNOut());
    assertEquals(WeightInit.DISTRIBUTION, l0.getWeightInit());
    assertEquals(new NormalDistribution(0.1, 1.2), l0.getDist());
    assertEquals(new RmsProp(0.15, 0.96, RmsProp.DEFAULT_RMSPROP_EPSILON), l0.getIUpdater());
    assertEquals(0.15, ((RmsProp)l0.getIUpdater()).getLearningRate(), 1e-6);
    assertEquals(new Dropout(0.6), l0.getIDropout());
    assertEquals(0.1, l0.getL1(), 1e-6);
    assertEquals(0.2, l0.getL2(), 1e-6);
    assertEquals(GradientNormalization.ClipElementWiseAbsoluteValue, l0.getGradientNormalization());
    assertEquals(1.5, l0.getGradientNormalizationThreshold(), 1e-5);

    OutputLayer l1 = (OutputLayer) conf.getConf(1).getLayer();
    assertEquals("identity", l1.getActivationFn().toString());
    assertTrue(l1.getLossFn() instanceof LossMSE);
    assertEquals(4, l1.getNIn());
    assertEquals(5, l1.getNOut());
    assertEquals(WeightInit.DISTRIBUTION, l0.getWeightInit());
    assertEquals(new NormalDistribution(0.1, 1.2), l0.getDist());
    assertEquals(new RmsProp(0.15, 0.96, RmsProp.DEFAULT_RMSPROP_EPSILON), l1.getIUpdater());
    assertEquals(0.15, ((RmsProp)l1.getIUpdater()).getLearningRate(), 1e-6);
    assertEquals(new Dropout(0.6), l1.getIDropout());
    assertEquals(0.1, l1.getL1(), 1e-6);
    assertEquals(0.2, l1.getL2(), 1e-6);
    assertEquals(GradientNormalization.ClipElementWiseAbsoluteValue, l1.getGradientNormalization());
    assertEquals(1.5, l1.getGradientNormalizationThreshold(), 1e-5);

    int numParams = net.numParams();
    assertEquals(Nd4j.linspace(1, numParams, numParams), net.params());
    int updaterSize = (int) new RmsProp().stateSize(numParams);
    assertEquals(Nd4j.linspace(1, updaterSize, updaterSize), net.getUpdater().getStateViewArray());
}
开发者ID:deeplearning4j，项目名称:deeplearning4j，代码行数:49，代码来源:RegressionTest060.java

示例15: regressionTestCNN1

import org.deeplearning4j.nn.multilayer.MultiLayerNetwork; //导入方法依赖的package包/类
@Test
public void regressionTestCNN1() throws Exception {

    File f = new ClassPathResource("regression_testing/060/060_ModelSerializer_Regression_CNN_1.zip")
                    .getTempFileFromArchive();

    MultiLayerNetwork net = ModelSerializer.restoreMultiLayerNetwork(f, true);

    MultiLayerConfiguration conf = net.getLayerWiseConfigurations();
    assertEquals(3, conf.getConfs().size());

    assertTrue(conf.isBackprop());
    assertFalse(conf.isPretrain());

    ConvolutionLayer l0 = (ConvolutionLayer) conf.getConf(0).getLayer();
    assertEquals("tanh", l0.getActivationFn().toString());
    assertEquals(3, l0.getNIn());
    assertEquals(3, l0.getNOut());
    assertEquals(WeightInit.RELU, l0.getWeightInit());
    assertEquals(new RmsProp(0.15, 0.96, RmsProp.DEFAULT_RMSPROP_EPSILON), l0.getIUpdater());
    assertEquals(0.15, ((RmsProp)l0.getIUpdater()).getLearningRate(), 1e-6);
    assertArrayEquals(new int[] {2, 2}, l0.getKernelSize());
    assertArrayEquals(new int[] {1, 1}, l0.getStride());
    assertArrayEquals(new int[] {0, 0}, l0.getPadding());
    assertEquals(l0.getConvolutionMode(), ConvolutionMode.Truncate); //Pre-0.7.0: no ConvolutionMode. Want to default to truncate here if not set

    SubsamplingLayer l1 = (SubsamplingLayer) conf.getConf(1).getLayer();
    assertArrayEquals(new int[] {2, 2}, l1.getKernelSize());
    assertArrayEquals(new int[] {1, 1}, l1.getStride());
    assertArrayEquals(new int[] {0, 0}, l1.getPadding());
    assertEquals(PoolingType.MAX, l1.getPoolingType());
    assertEquals(l1.getConvolutionMode(), ConvolutionMode.Truncate); //Pre-0.7.0: no ConvolutionMode. Want to default to truncate here if not set

    OutputLayer l2 = (OutputLayer) conf.getConf(2).getLayer();
    assertEquals("sigmoid", l2.getActivationFn().toString());
    assertTrue(l2.getLossFn() instanceof LossNegativeLogLikelihood); //TODO
    assertEquals(26 * 26 * 3, l2.getNIn());
    assertEquals(5, l2.getNOut());
    assertEquals(WeightInit.RELU, l0.getWeightInit());
    assertEquals(new RmsProp(0.15, 0.96, RmsProp.DEFAULT_RMSPROP_EPSILON), l0.getIUpdater());
    assertEquals(0.15, ((RmsProp)l0.getIUpdater()).getLearningRate(), 1e-6);

    assertTrue(conf.getInputPreProcess(2) instanceof CnnToFeedForwardPreProcessor);

    int numParams = net.numParams();
    assertEquals(Nd4j.linspace(1, numParams, numParams), net.params());
    int updaterSize = (int) new RmsProp().stateSize(numParams);
    assertEquals(Nd4j.linspace(1, updaterSize, updaterSize), net.getUpdater().getStateViewArray());
}
开发者ID:deeplearning4j，项目名称:deeplearning4j，代码行数:50，代码来源:RegressionTest060.java


注：本文中的org.deeplearning4j.nn.multilayer.MultiLayerNetwork.numParams方法示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台，相关代码片段筛选自各路编程大神贡献的开源项目，源码版权归原作者所有，传播和使用请参考对应项目的License；未经允许，请勿转载。