use of org.nd4j.linalg.io.ClassPathResource in project deeplearning4j by deeplearning4j.
the class RegressionTest071 method regressionTestCNN1.
@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(Updater.RMSPROP, l0.getUpdater());
assertEquals(0.96, l0.getRmsDecay(), 1e-6);
assertEquals(0.15, l0.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", l1.getActivationFn().toString());
assertEquals(LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD, l2.getLossFunction());
//TODO
assertTrue(l2.getLossFn() instanceof LossNegativeLogLikelihood);
assertEquals(26 * 26 * 3, l2.getNIn());
assertEquals(5, l2.getNOut());
assertEquals(WeightInit.RELU, l0.getWeightInit());
assertEquals(Updater.RMSPROP, l0.getUpdater());
assertEquals(0.96, l0.getRmsDecay(), 1e-6);
assertEquals(0.15, l0.getLearningRate(), 1e-6);
assertTrue(conf.getInputPreProcess(2) instanceof CnnToFeedForwardPreProcessor);
int numParams = net.numParams();
assertEquals(Nd4j.linspace(1, numParams, numParams), net.params());
int updaterSize = net.getUpdater().stateSizeForLayer(net);
assertEquals(Nd4j.linspace(1, updaterSize, updaterSize), net.getUpdater().getStateViewArray());
}
use of org.nd4j.linalg.io.ClassPathResource in project deeplearning4j by deeplearning4j.
the class ModelGuesserTest method testModelGuess.
@Test
public void testModelGuess() throws Exception {
ClassPathResource sequenceResource = new ClassPathResource("modelimport/keras/examples/mnist_mlp/mnist_mlp_tf_model.h5");
assertTrue(sequenceResource.exists());
File f = getTempFile(sequenceResource);
Model guess1 = ModelGuesser.loadModelGuess(f.getAbsolutePath());
assumeNotNull(guess1);
ClassPathResource sequenceResource2 = new ClassPathResource("modelimport/keras/examples/mnist_cnn/mnist_cnn_tf_model.h5");
assertTrue(sequenceResource2.exists());
File f2 = getTempFile(sequenceResource);
Model guess2 = ModelGuesser.loadModelGuess(f2.getAbsolutePath());
assumeNotNull(guess2);
}
use of org.nd4j.linalg.io.ClassPathResource in project deeplearning4j by deeplearning4j.
the class BarnesHutTsneTest method testTsne.
@Test
public void testTsne() throws Exception {
Nd4j.ENFORCE_NUMERICAL_STABILITY = true;
DataTypeUtil.setDTypeForContext(DataBuffer.Type.DOUBLE);
Nd4j.getRandom().setSeed(123);
BarnesHutTsne b = new BarnesHutTsne.Builder().stopLyingIteration(10).setMaxIter(10).theta(0.5).learningRate(500).useAdaGrad(false).build();
ClassPathResource resource = new ClassPathResource("/mnist2500_X.txt");
File f = resource.getTempFileFromArchive();
INDArray data = Nd4j.readNumpy(f.getAbsolutePath(), " ").get(NDArrayIndex.interval(0, 100), NDArrayIndex.interval(0, 784));
ClassPathResource labels = new ClassPathResource("mnist2500_labels.txt");
List<String> labelsList = IOUtils.readLines(labels.getInputStream()).subList(0, 100);
b.fit(data);
}
use of org.nd4j.linalg.io.ClassPathResource in project deeplearning4j by deeplearning4j.
the class RegressionTest050 method regressionTestMLP2.
@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(Updater.RMSPROP, l0.getUpdater());
assertEquals(0.96, l0.getRmsDecay(), 1e-6);
assertEquals(0.15, l0.getLearningRate(), 1e-6);
assertEquals(0.6, l0.getDropOut(), 1e-6);
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());
assertEquals(LossFunctions.LossFunction.MSE, l1.getLossFunction());
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(Updater.RMSPROP, l0.getUpdater());
assertEquals(0.96, l1.getRmsDecay(), 1e-6);
assertEquals(0.15, l1.getLearningRate(), 1e-6);
assertEquals(0.6, l1.getDropOut(), 1e-6);
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 = net.getUpdater().stateSizeForLayer(net);
assertEquals(Nd4j.linspace(1, updaterSize, updaterSize), net.getUpdater().getStateViewArray());
}
use of org.nd4j.linalg.io.ClassPathResource in project deeplearning4j by deeplearning4j.
the class RegressionTest060 method regressionTestCNN1.
@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(Updater.RMSPROP, l0.getUpdater());
assertEquals(0.96, l0.getRmsDecay(), 1e-6);
assertEquals(0.15, l0.getLearningRate(), 1e-6);
assertArrayEquals(new int[] { 2, 2 }, l0.getKernelSize());
assertArrayEquals(new int[] { 1, 1 }, l0.getStride());
assertArrayEquals(new int[] { 0, 0 }, l0.getPadding());
//Pre-0.7.0: no ConvolutionMode. Want to default to truncate here if not set
assertEquals(l0.getConvolutionMode(), ConvolutionMode.Truncate);
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());
//Pre-0.7.0: no ConvolutionMode. Want to default to truncate here if not set
assertEquals(l1.getConvolutionMode(), ConvolutionMode.Truncate);
OutputLayer l2 = (OutputLayer) conf.getConf(2).getLayer();
assertEquals("sigmoid", l1.getActivationFn().toString());
assertEquals(LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD, l2.getLossFunction());
//TODO
assertTrue(l2.getLossFn() instanceof LossNegativeLogLikelihood);
assertEquals(26 * 26 * 3, l2.getNIn());
assertEquals(5, l2.getNOut());
assertEquals(WeightInit.RELU, l0.getWeightInit());
assertEquals(Updater.RMSPROP, l0.getUpdater());
assertEquals(0.96, l0.getRmsDecay(), 1e-6);
assertEquals(0.15, l0.getLearningRate(), 1e-6);
assertTrue(conf.getInputPreProcess(2) instanceof CnnToFeedForwardPreProcessor);
int numParams = net.numParams();
assertEquals(Nd4j.linspace(1, numParams, numParams), net.params());
int updaterSize = net.getUpdater().stateSizeForLayer(net);
assertEquals(Nd4j.linspace(1, updaterSize, updaterSize), net.getUpdater().getStateViewArray());
}
Aggregations