Modifier and Type | Method and Description |
---|---|
protected NeuralNetConfiguration.Builder |
BaseNetworkSpace.randomGlobalConf(double[] values) |
Modifier and Type | Field and Description |
---|---|
protected NeuralNetConfiguration.Builder |
ComputationGraphConfiguration.GraphBuilder.globalConfiguration |
Modifier and Type | Method and Description |
---|---|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.activation(Activation activation)
Activation function / neuron non-linearity
Note: values set by this method will be applied to all applicable layers in the network, unless a different value is explicitly set on a given layer. |
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.activation(IActivation activationFunction)
Activation function / neuron non-linearity
Note: values set by this method will be applied to all applicable layers in the network, unless a different value is explicitly set on a given layer. |
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.biasInit(double biasInit)
Constant for bias initialization.
|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.biasUpdater(IUpdater updater)
Gradient updater configuration, for the biases only.
|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.cacheMode(@NonNull CacheMode cacheMode)
This method defines how/if preOutput cache is handled:
NONE: cache disabled (default value)
HOST: Host memory will be used
DEVICE: GPU memory will be used (on CPU backends effect will be the same as for HOST)
|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.clone() |
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.constrainAllParameters(LayerConstraint... constraints)
Set constraints to be applied to all layers.
|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.constrainBias(LayerConstraint... constraints)
Set constraints to be applied to all layers.
|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.constrainWeights(LayerConstraint... constraints)
Set constraints to be applied to all layers.
|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.convolutionMode(ConvolutionMode convolutionMode)
Sets the convolution mode for convolutional layers, which impacts padding and output sizes.
|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.cudnnAlgoMode(ConvolutionLayer.AlgoMode cudnnAlgoMode)
Sets the cuDNN algo mode for convolutional layers, which impacts performance and memory usage of cuDNN.
|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.dataType(@NonNull DataType dataType)
Set the DataType for the network parameters and activations.
|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.dist(Distribution dist)
Deprecated.
|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.dropOut(double inputRetainProbability)
Dropout probability.
|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.dropOut(IDropout dropout)
Set the dropout for all layers in this network
Note: values set by this method will be applied to all applicable layers in the network, unless a different value is explicitly set on a given layer. |
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.gradientNormalization(GradientNormalization gradientNormalization)
Gradient normalization strategy.
|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.gradientNormalizationThreshold(double threshold)
Threshold for gradient normalization, only used for GradientNormalization.ClipL2PerLayer,
GradientNormalization.ClipL2PerParamType, and GradientNormalization.ClipElementWiseAbsoluteValue
Not used otherwise. |
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.inferenceWorkspaceMode(@NonNull WorkspaceMode workspaceMode)
This method defines Workspace mode being used during inference:
NONE: workspace won't be used ENABLED: workspaces will be used for inference (reduced memory and better performance) |
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.l1(double l1)
L1 regularization coefficient for the weights (excluding biases).
|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.l1Bias(double l1Bias)
L1 regularization coefficient for the bias.
|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.l2(double l2)
L2 regularization coefficient for the weights (excluding biases).
|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.l2Bias(double l2Bias)
L2 regularization coefficient for the bias.
|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.layer(Layer layer)
Layer class.
|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.maxNumLineSearchIterations(int maxNumLineSearchIterations)
Maximum number of line search iterations.
|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.miniBatch(boolean miniBatch)
Process input as minibatch vs full dataset.
|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.minimize(boolean minimize)
Objective function to minimize or maximize cost function
Default set to minimize true.
|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.optimizationAlgo(OptimizationAlgorithm optimizationAlgo)
Optimization algorithm to use.
|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.regularization(List<Regularization> regularization)
Set the regularization for the parameters (excluding biases) - for example
WeightDecay Note: values set by this method will be applied to all applicable layers in the network, unless a different value is explicitly set on a given layer. |
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.regularizationBias(List<Regularization> regularizationBias)
Set the regularization for the biases only - for example
WeightDecay Note: values set by this method will be applied to all applicable layers in the network, unless a different value is explicitly set on a given layer. |
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.seed(long seed)
Random number generator seed.
|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.stepFunction(StepFunction stepFunction)
Deprecated.
|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.trainingWorkspaceMode(@NonNull WorkspaceMode workspaceMode)
This method defines Workspace mode being used during training:
NONE: workspace won't be used ENABLED: workspaces will be used for training (reduced memory and better performance) |
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.updater(IUpdater updater)
Gradient updater configuration.
|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.updater(Updater updater)
Deprecated.
|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.weightDecay(double coefficient)
Add weight decay regularization for the network parameters (excluding biases).
|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.weightDecay(double coefficient,
boolean applyLR)
Add weight decay regularization for the network parameters (excluding biases).
|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.weightDecayBias(double coefficient)
Weight decay for the biases only - see
weightDecay(double) for more details. |
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.weightDecayBias(double coefficient,
boolean applyLR)
Weight decay for the biases only - see
weightDecay(double) for more detailsNote: values set by this method will be applied to all applicable layers in the network, unless a different value is explicitly set on a given layer. |
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.weightInit(Distribution distribution)
Set weight initialization scheme to random sampling via the specified distribution.
|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.weightInit(IWeightInit weightInit)
Weight initialization scheme to use, for initial weight values
Note: values set by this method will be applied to all applicable layers in the network, unless a different
value is explicitly set on a given layer.
|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.weightInit(WeightInit weightInit)
Weight initialization scheme to use, for initial weight values
Note: values set by this method will be applied to all applicable layers in the network, unless a different
value is explicitly set on a given layer.
|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.weightNoise(IWeightNoise weightNoise)
Set the weight noise (such as
DropConnect and
WeightNoise ) for the layers in this network. |
Modifier and Type | Method and Description |
---|---|
Map<Integer,NeuralNetConfiguration.Builder> |
NeuralNetConfiguration.ListBuilder.getLayerwise() |
Constructor and Description |
---|
GraphBuilder(ComputationGraphConfiguration newConf,
NeuralNetConfiguration.Builder globalConfiguration) |
GraphBuilder(NeuralNetConfiguration.Builder globalConfiguration) |
ListBuilder(NeuralNetConfiguration.Builder globalConfig) |
ListBuilder(NeuralNetConfiguration.Builder globalConfig,
Map<Integer,NeuralNetConfiguration.Builder> layerMap) |
Constructor and Description |
---|
ListBuilder(NeuralNetConfiguration.Builder globalConfig,
Map<Integer,NeuralNetConfiguration.Builder> layerMap) |
Modifier and Type | Method and Description |
---|---|
void |
LocallyConnected1D.applyGlobalConfigToLayer(NeuralNetConfiguration.Builder globalConfig) |
void |
LocallyConnected2D.applyGlobalConfigToLayer(NeuralNetConfiguration.Builder globalConfig) |
void |
RecurrentAttentionLayer.applyGlobalConfigToLayer(NeuralNetConfiguration.Builder globalConfig) |
Modifier and Type | Method and Description |
---|---|
void |
AbstractSameDiffLayer.applyGlobalConfig(NeuralNetConfiguration.Builder b) |
void |
SameDiffVertex.applyGlobalConfig(NeuralNetConfiguration.Builder b) |
void |
AbstractSameDiffLayer.applyGlobalConfigToLayer(NeuralNetConfiguration.Builder globalConfig) |
void |
SameDiffVertex.applyGlobalConfigToLayer(NeuralNetConfiguration.Builder globalConfig) |
Modifier and Type | Method and Description |
---|---|
NeuralNetConfiguration.Builder |
FineTuneConfiguration.appliedNeuralNetConfigurationBuilder() |
Copyright © 2020. All rights reserved.