.activation(Activation.LEAKYRELU) .weightInit(WeightInit.XAVIER) .updater(new Nesterovs(0.1))// To configure: .updater(Nesterovs.builder().momentum(0.9).build())
.seed(12345) .activation(Activation.LEAKYRELU) .weightInit(WeightInit.XAVIER) .updater(new Nesterovs(0.02))// To configure: .updater(Nesterovs.builder().momentum(0.9).build())
.activation(Activation.LEAKYRELU) .updater(Updater.ADADELTA) .convolutionMode(ConvolutionMode.Same)
new NeuralNetConfiguration.Builder() .optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT) .updater(Updater.NESTEROVS).activation(Activation.RELU) .trainingWorkspaceMode(workspaceMode).inferenceWorkspaceMode(workspaceMode) .list()
new NeuralNetConfiguration.Builder() .optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT) .updater(Updater.NESTEROVS).activation(Activation.RELU) .trainingWorkspaceMode(workspaceMode).inferenceWorkspaceMode(workspaceMode) .list()
new NeuralNetConfiguration.Builder().trainingWorkspaceMode(workspaceMode) .inferenceWorkspaceMode(workspaceMode).seed(seed).iterations(iterations) .activation(Activation.IDENTITY).weightInit(WeightInit.RELU) .optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT) .updater(new AdaDelta()).regularization(false)
MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder() .activation(Activation.RELU) .weightInit(WeightInit.XAVIER) .updater(new Nesterovs(rate, 0.98))
.seed(seed) .iterations(iterations) .activation(Activation.TANH) .weightInit(WeightInit.XAVIER) .learningRate(0.01)
.activation(Activation.RELU).optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT) .updater(Updater.NESTEROVS).learningRate(1e-2).biasLearningRate(1e-2 * 2).regularization(true) .convolutionMode(ConvolutionMode.Same)
public ComputationGraphConfiguration.GraphBuilder graphBuilder() { .iterations(iterations).activation(Activation.IDENTITY) .optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT) .updater(new RmsProp(0.1, 0.96, 0.001)).weightInit(WeightInit.DISTRIBUTION)
public ComputationGraphConfiguration conf() { GraphBuilder graph = new NeuralNetConfiguration.Builder().seed(seed).iterations(iterations) .activation(Activation.RELU).optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT) .learningRate(1e-2).biasLearningRate(2 * 1e-2).learningRateDecayPolicy(LearningRatePolicy.Step) .lrPolicyDecayRate(0.96).lrPolicySteps(320000).updater(new Nesterovs(1e-2, 0.9))
.weightInit(WeightInit.DISTRIBUTION) .dist(new NormalDistribution(0.0, 0.01)) .activation(Activation.RELU) .updater(new Nesterovs(new StepSchedule(ScheduleType.ITERATION, 0.1, 0.1, 100000), 0.9)) .biasUpdater(new Nesterovs(new StepSchedule(ScheduleType.ITERATION, 0.2, 0.1, 100000), 0.9))
.activation(Activation.RELU) .weightInit(WeightInit.XAVIER)
public void buildModel() { if (model == null) { int iterations = 1000; long seed = 6; MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder() .seed(seed) .iterations(iterations) .activation(Activation.TANH) .weightInit(WeightInit.XAVIER) .learningRate(0.1) .regularization(true).l2(1e-4) .list() .layer(0, new DenseLayer.Builder().nIn(numInputs).nOut(3) .build()) .layer(1, new DenseLayer.Builder().nIn(3).nOut(3) .build()) .layer(2, new OutputLayer.Builder(LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD) .activation(Activation.SOFTMAX) .nIn(3).nOut(numClasses).build()) .backprop(true).pretrain(false) .build(); //run the model model = new MultiLayerNetwork(conf); model.init(); model.setListeners(iterationListener); } }
public void buildModel() { if (model == null) { int iterations = 1000; long seed = 6; MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder() .seed(seed) .iterations(iterations) .activation(Activation.TANH) .weightInit(WeightInit.XAVIER) .learningRate(0.1) .regularization(true).l2(1e-4) .list() .layer(0, new DenseLayer.Builder().nIn(numInputs).nOut(3) .build()) .layer(1, new DenseLayer.Builder().nIn(3).nOut(3) .build()) .layer(2, new OutputLayer.Builder(LossFunctions.LossFunction.MEAN_SQUARED_LOGARITHMIC_ERROR) .activation(Activation.SOFTMAX) .nIn(3).nOut(numClasses).build()) .backprop(true).pretrain(false) .build(); //run the model model = new MultiLayerNetwork(conf); model.init(); model.setListeners(iterationListener); } }
public MultiLayerConfiguration conf() { MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder().trainingWorkspaceMode(workspaceMode) .inferenceWorkspaceMode(workspaceMode).seed(seed).iterations(iterations) .activation(Activation.IDENTITY).weightInit(WeightInit.XAVIER) .optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT).updater(new AdaDelta()) .regularization(false).convolutionMode(ConvolutionMode.Same).list() // block 1 .layer(0, new ConvolutionLayer.Builder(new int[] {5, 5}, new int[] {1, 1}).name("cnn1") .nIn(inputShape[0]).nOut(20).activation(Activation.RELU).build()) .layer(1, new SubsamplingLayer.Builder(SubsamplingLayer.PoolingType.MAX, new int[] {2, 2}, new int[] {2, 2}).name("maxpool1").build()) // block 2 .layer(2, new ConvolutionLayer.Builder(new int[] {5, 5}, new int[] {1, 1}).name("cnn2").nOut(50) .activation(Activation.RELU).build()) .layer(3, new SubsamplingLayer.Builder(SubsamplingLayer.PoolingType.MAX, new int[] {2, 2}, new int[] {2, 2}).name("maxpool2").build()) // fully connected .layer(4, new DenseLayer.Builder().name("ffn1").activation(Activation.RELU).nOut(500).build()) // output .layer(5, new OutputLayer.Builder(LossFunctions.LossFunction.MCXENT).name("output") .nOut(numLabels).activation(Activation.SOFTMAX) // radial basis function required .build()) .setInputType(InputType.convolutionalFlat(inputShape[2], inputShape[1], inputShape[0])) .backprop(true).pretrain(false).build(); return conf; }
/** * Activation function / neuron non-linearity */ public Builder activation(Activation activation) { return activation(activation.getActivationFunction()); }
/** * Activation function / neuron non-linearity * Typical values include:<br> * "relu" (rectified linear), "tanh", "sigmoid", "softmax", * "hardtanh", "leakyrelu", "maxout", "softsign", "softplus" * * @deprecated Use {@link #activation(Activation)} or * {@link @activation(IActivation)} */ @Deprecated public Builder activation(String activationFunction) { return activation(Activation.fromString(activationFunction).getActivationFunction()); }
public static MultiLayerNetwork lenetModel() { /** * Revisde Lenet Model approach developed by ramgo2 achieves slightly above random * Reference: https://gist.github.com/ramgo2/833f12e92359a2da9e5c2fb6333351c5 **/ MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder() .seed(seed) .l2(0.005) // tried 0.0001, 0.0005 .activation(Activation.RELU) .weightInit(WeightInit.XAVIER) .optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT) .updater(new Nesterovs(0.0001,0.9)) .list() .layer(0, new ConvolutionLayer.Builder(new int[]{5, 5}, new int[]{1, 1}, new int[]{0, 0}).name("cnn1") .nIn(channels).nOut(50).biasInit(0).build()) .layer(1, new SubsamplingLayer.Builder(new int[]{2,2}, new int[]{2,2}).name("maxpool1").build()) .layer(2, new ConvolutionLayer.Builder(new int[]{5,5}, new int[]{5, 5}, new int[]{1, 1}).name("cnn2") .nOut(100).biasInit(0).build()) .layer(3, new SubsamplingLayer.Builder(new int[]{2,2}, new int[]{2,2}).name("maxpool2").build()) .layer(4, new DenseLayer.Builder().nOut(500).build()) .layer(5, new OutputLayer.Builder(LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD) .nOut(4) .activation(Activation.SOFTMAX) .build()) .backprop(true).pretrain(false) .setInputType(InputType.convolutional(height, width, channels)) .build(); return new MultiLayerNetwork(conf); }
public static MultiLayerConfiguration lenetModelConf() { MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder() .seed(seed) .l2(0.005) .activation(Activation.RELU) .weightInit(WeightInit.XAVIER) .optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT) .updater(new Nesterovs(0.0001, 0.9)) .list() .layer(0, new ConvolutionLayer.Builder(new int[]{5, 5}, new int[]{1, 1}, new int[]{0, 0}).name("cnn1") .nIn(channels).nOut(50).biasInit(0).build()) .layer(1, new SubsamplingLayer.Builder(new int[]{2,2}, new int[]{2,2}).name("maxpool1").build()) .layer(2, new ConvolutionLayer.Builder(new int[]{5,5}, new int[]{5, 5}, new int[]{1, 1}).name("cnn2") .nOut(100).biasInit(0).build()) .layer(3, new SubsamplingLayer.Builder(new int[]{2,2}, new int[]{2,2}).name("maxpool2").build()) .layer(4, new DenseLayer.Builder().nOut(500).build()) .layer(5, new OutputLayer.Builder(LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD) .nOut(4) .activation(Activation.SOFTMAX) .build()) .backprop(true).pretrain(false) .setInputType(InputType.convolutional(height, width, channels)) .build(); return conf; } public static void saveModel(FileSystem fs, Model model ) throws Exception{