org.deeplearning4j.nn.conf

Class NeuralNetConfiguration.ListBuilder

java.lang.Object

org.deeplearning4j.nn.conf.MultiLayerConfiguration.Builder

org.deeplearning4j.nn.conf.NeuralNetConfiguration.ListBuilder

Enclosing class:

NeuralNetConfiguration

public static class NeuralNetConfiguration.ListBuilder
extends MultiLayerConfiguration.Builder

Fluent interface for building a list of configurations

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
class	NeuralNetConfiguration.ListBuilder.InputTypeBuilder Helper class for setting input types

Field Summary

Fields inherited from class org.deeplearning4j.nn.conf.MultiLayerConfiguration.Builder

backprop, backpropType, cacheMode, confs, dampingFactor, inferenceWorkspaceMode, inputPreProcessors, inputType, pretrain, tbpttBackLength, tbpttFwdLength, trainingWorkspaceMode

Constructor Summary

Constructors

Constructor and Description
ListBuilder(NeuralNetConfiguration.Builder globalConfig)
ListBuilder(NeuralNetConfiguration.Builder globalConfig, Map<Integer,NeuralNetConfiguration.Builder> layerMap)

Method Summary

Modifier and Type	Method and Description
NeuralNetConfiguration.ListBuilder	backprop(boolean backprop) Whether to do back prop or not
MultiLayerConfiguration	build() Build the multi layer network based on this neural network and overr ridden parameters
List<InputType>	getLayerActivationTypes() For the (perhaps partially constructed) network configuration, return a list of activation sizes for each layer in the network. Note: To use this method, the network input type must have been set using setInputType(InputType) first
Map<Integer,NeuralNetConfiguration.Builder>	getLayerwise()
NeuralNetConfiguration.ListBuilder.InputTypeBuilder	inputType() A convenience method for setting input types: note that for example .inputType().convolutional(h,w,d) is equivalent to .setInputType(InputType.convolutional(h,w,d))
NeuralNetConfiguration.ListBuilder	layer(int ind, Layer layer)
NeuralNetConfiguration.ListBuilder	layer(Layer layer)
NeuralNetConfiguration.ListBuilder	pretrain(boolean pretrain) Whether to do pre train or not
NeuralNetConfiguration.ListBuilder	setInputType(InputType inputType)

Methods inherited from class org.deeplearning4j.nn.conf.MultiLayerConfiguration.Builder

backpropType, cacheMode, confs, inferenceWorkspaceMode, inputPreProcessor, inputPreProcessors, tBPTTBackwardLength, tBPTTForwardLength, tBPTTLength, trainingWorkspaceMode

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

ListBuilder

public ListBuilder(NeuralNetConfiguration.Builder globalConfig,
                   Map<Integer,NeuralNetConfiguration.Builder> layerMap)

ListBuilder

public ListBuilder(NeuralNetConfiguration.Builder globalConfig)

Method Detail

backprop

public NeuralNetConfiguration.ListBuilder backprop(boolean backprop)

Description copied from class: MultiLayerConfiguration.Builder

Whether to do back prop or not

Overrides:

backprop in class MultiLayerConfiguration.Builder

Parameters:

backprop - whether to do back prop or not

Returns:

pretrain

public NeuralNetConfiguration.ListBuilder pretrain(boolean pretrain)

Description copied from class: MultiLayerConfiguration.Builder

Whether to do pre train or not

Overrides:

pretrain in class MultiLayerConfiguration.Builder

Parameters:

pretrain - whether to do pre train or not

Returns:

builder pattern

layer

public NeuralNetConfiguration.ListBuilder layer(int ind,
                                                @NonNull
                                                Layer layer)

layer

public NeuralNetConfiguration.ListBuilder layer(Layer layer)

getLayerwise

public Map<Integer,NeuralNetConfiguration.Builder> getLayerwise()

setInputType

public NeuralNetConfiguration.ListBuilder setInputType(InputType inputType)

Overrides:

setInputType in class MultiLayerConfiguration.Builder

inputType

public NeuralNetConfiguration.ListBuilder.InputTypeBuilder inputType()

A convenience method for setting input types: note that for example .inputType().convolutional(h,w,d) is equivalent to .setInputType(InputType.convolutional(h,w,d))

getLayerActivationTypes

public List<InputType> getLayerActivationTypes()

For the (perhaps partially constructed) network configuration, return a list of activation sizes for each layer in the network.
Note: To use this method, the network input type must have been set using setInputType(InputType) first

Returns:

A list of activation types for the network, indexed by layer number

build

public MultiLayerConfiguration build()

Build the multi layer network based on this neural network and overr ridden parameters

Overrides:

build in class MultiLayerConfiguration.Builder

Returns:

the configuration to build