use of org.deeplearning4j.nn.conf.layers.DenseLayer in project deeplearning4j by deeplearning4j.
the class DenseTest method testDenseBiasInit.
@Test
public void testDenseBiasInit() {
DenseLayer build = new DenseLayer.Builder().nIn(1).nOut(3).biasInit(1).build();
NeuralNetConfiguration conf = new NeuralNetConfiguration.Builder().layer(build).build();
int numParams = conf.getLayer().initializer().numParams(conf);
INDArray params = Nd4j.create(1, numParams);
Layer layer = conf.getLayer().instantiate(conf, null, 0, params, true);
assertEquals(1, layer.getParam("b").size(0));
}
use of org.deeplearning4j.nn.conf.layers.DenseLayer in project deeplearning4j by deeplearning4j.
the class MultiLayerTestRNN method testRnnTimeStepGravesLSTM.
@Test
public void testRnnTimeStepGravesLSTM() {
Nd4j.getRandom().setSeed(12345);
int timeSeriesLength = 12;
//4 layer network: 2 GravesLSTM + DenseLayer + RnnOutputLayer. Hence also tests preprocessors.
MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder().seed(12345).list().layer(0, new org.deeplearning4j.nn.conf.layers.GravesLSTM.Builder().nIn(5).nOut(7).activation(Activation.TANH).weightInit(WeightInit.DISTRIBUTION).dist(new NormalDistribution(0, 0.5)).build()).layer(1, new org.deeplearning4j.nn.conf.layers.GravesLSTM.Builder().nIn(7).nOut(8).activation(Activation.TANH).weightInit(WeightInit.DISTRIBUTION).dist(new NormalDistribution(0, 0.5)).build()).layer(2, new DenseLayer.Builder().nIn(8).nOut(9).activation(Activation.TANH).weightInit(WeightInit.DISTRIBUTION).dist(new NormalDistribution(0, 0.5)).build()).layer(3, new RnnOutputLayer.Builder(LossFunction.MCXENT).weightInit(WeightInit.DISTRIBUTION).nIn(9).nOut(4).activation(Activation.SOFTMAX).weightInit(WeightInit.DISTRIBUTION).dist(new NormalDistribution(0, 0.5)).build()).inputPreProcessor(2, new RnnToFeedForwardPreProcessor()).inputPreProcessor(3, new FeedForwardToRnnPreProcessor()).build();
MultiLayerNetwork mln = new MultiLayerNetwork(conf);
INDArray input = Nd4j.rand(new int[] { 3, 5, timeSeriesLength });
List<INDArray> allOutputActivations = mln.feedForward(input, true);
INDArray fullOutL0 = allOutputActivations.get(1);
INDArray fullOutL1 = allOutputActivations.get(2);
INDArray fullOutL3 = allOutputActivations.get(4);
int[] inputLengths = { 1, 2, 3, 4, 6, 12 };
//Should get the same result regardless of step size; should be identical to standard forward pass
for (int i = 0; i < inputLengths.length; i++) {
int inLength = inputLengths[i];
//each of length inLength
int nSteps = timeSeriesLength / inLength;
mln.rnnClearPreviousState();
//Reset; should be set by rnnTimeStep method
mln.setInputMiniBatchSize(1);
for (int j = 0; j < nSteps; j++) {
int startTimeRange = j * inLength;
int endTimeRange = startTimeRange + inLength;
INDArray inputSubset;
if (inLength == 1) {
//Workaround to nd4j bug
int[] sizes = new int[] { input.size(0), input.size(1), 1 };
inputSubset = Nd4j.create(sizes);
inputSubset.tensorAlongDimension(0, 1, 0).assign(input.get(NDArrayIndex.all(), NDArrayIndex.all(), NDArrayIndex.point(startTimeRange)));
} else {
inputSubset = input.get(NDArrayIndex.all(), NDArrayIndex.all(), NDArrayIndex.interval(startTimeRange, endTimeRange));
}
if (inLength > 1)
assertTrue(inputSubset.size(2) == inLength);
INDArray out = mln.rnnTimeStep(inputSubset);
INDArray expOutSubset;
if (inLength == 1) {
int[] sizes = new int[] { fullOutL3.size(0), fullOutL3.size(1), 1 };
expOutSubset = Nd4j.create(sizes);
expOutSubset.tensorAlongDimension(0, 1, 0).assign(fullOutL3.get(NDArrayIndex.all(), NDArrayIndex.all(), NDArrayIndex.point(startTimeRange)));
} else {
expOutSubset = fullOutL3.get(NDArrayIndex.all(), NDArrayIndex.all(), NDArrayIndex.interval(startTimeRange, endTimeRange));
}
assertEquals(expOutSubset, out);
Map<String, INDArray> currL0State = mln.rnnGetPreviousState(0);
Map<String, INDArray> currL1State = mln.rnnGetPreviousState(1);
INDArray lastActL0 = currL0State.get(GravesLSTM.STATE_KEY_PREV_ACTIVATION);
INDArray lastActL1 = currL1State.get(GravesLSTM.STATE_KEY_PREV_ACTIVATION);
INDArray expLastActL0 = fullOutL0.tensorAlongDimension(endTimeRange - 1, 1, 0);
INDArray expLastActL1 = fullOutL1.tensorAlongDimension(endTimeRange - 1, 1, 0);
assertEquals(expLastActL0, lastActL0);
assertEquals(expLastActL1, lastActL1);
}
}
}
Aggregations