.l2(1e-5) .weightInit(WeightInit.XAVIER) .gradientNormalization(GradientNormalization.ClipElementWiseAbsoluteValue).gradientNormalizationThreshold(1.0) .list() .layer(0, new LSTM.Builder().nIn(vectorSize).nOut(256)
.weightInit(WeightInit.XAVIER) .gradientNormalization(GradientNormalization.ClipElementWiseAbsoluteValue) .gradientNormalizationThreshold(1.0).learningRate(0.0018).list() .layer(0, new GravesLSTM.Builder().nIn(inputNeurons).nOut(200)
.l2(1e-5).weightInit(WeightInit.RELU) .gradientNormalization(GradientNormalization.ClipElementWiseAbsoluteValue) .gradientNormalizationThreshold(1.0).learningRate(learningRate).list() .layer(0, new GravesLSTM.Builder().activation(Activation.TANH).nIn(featuresSize)
builder.gradientNormalization(gradientNormalization.getValue(values)); if (gradientNormalizationThreshold != null) builder.gradientNormalizationThreshold(gradientNormalizationThreshold.getValue(values)); if (adamMeanDecay != null) builder.adamMeanDecay(adamMeanDecay.getValue(values));
.weightInit(aTraits.getWeightInit()) .gradientNormalization(aTraits.getGradientNormalization()) .gradientNormalizationThreshold(aTraits.getGradientNormalizationThreshold()) .list() .layer(0, new Bidirectional(Bidirectional.Mode.ADD, new GravesLSTM.Builder()
.weightInit(aTraits.getWeightInit()) .gradientNormalization(aTraits.getGradientNormalization()) .gradientNormalizationThreshold(aTraits.getGradientNormalizationThreshold()) .list() .layer(0, new Bidirectional(Bidirectional.Mode.ADD, new GravesLSTM.Builder()
.weightInit(WeightInit.XAVIER) .gradientNormalization(GradientNormalization.ClipElementWiseAbsoluteValue) .gradientNormalizationThreshold(1.0) .list() .layer(0, new GravesLSTM.Builder()
/** * Deliver access to the internal builder * * @return NeuralNetworkConfiguration */ public org.deeplearning4j.nn.conf.NeuralNetConfiguration.Builder builder() { Builder builder = new Builder(); // Set dist to null if Disabled was chosen as dl4j backend defaults to null builder .l1(l1) .l2(l2) .optimizationAlgo(optimizationAlgo) .seed(seed) .weightInit(weightInit) .dist(dist.getBackend()) .biasInit(biasInit) .updater(updater.getBackend()) .biasUpdater(biasUpdater.getBackend()) .dropOut(dropout.getBackend()) .miniBatch(miniBatch) .minimize(minimize) .weightNoise(weightNoise.getBackend()) .gradientNormalization(gradientNormalization.getBackend()) .gradientNormalizationThreshold(gradientNormalizationThreshold) .inferenceWorkspaceMode(inferenceWorkspaceMode) .trainingWorkspaceMode(trainingWorkspaceMode); builder.setPretrain(pretrain); return builder; }