org.deeplearning4j.nn.conf

Class MultiLayerConfiguration

java.lang.Object

org.deeplearning4j.nn.conf.MultiLayerConfiguration

All Implemented Interfaces:

Serializable

public class MultiLayerConfiguration
extends Object
implements Serializable

Configuration for a multi layer network

Author:

Adam Gibson

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	MultiLayerConfiguration.Builder

Field Summary

Fields

Modifier and Type	Field and Description
protected boolean	pretrain

Method Summary

Modifier and Type	Method and Description
boolean	equals(Object o)
static MultiLayerConfiguration	fromJson(String json) Create a neural net configuration from json
NeuralNetConfiguration	getConf(int i)
List<NeuralNetConfiguration>	getConfs()
double	getDampingFactor()
int[]	getHiddenLayerSizes()
OutputPreProcessor	getPreProcessor(int layer)
int	hashCode()
boolean	isPretrain()
boolean	isUseDropConnect()
boolean	isUseGaussNewtonVectorProductBackProp()
boolean	isUseRBMPropUpAsActivations()
void	setConfs(List<NeuralNetConfiguration> confs)
void	setDampingFactor(double dampingFactor)
void	setHiddenLayerSizes(int[] hiddenLayerSizes)
void	setPretrain(boolean pretrain)
void	setUseDropConnect(boolean useDropConnect)
void	setUseGaussNewtonVectorProductBackProp(boolean useGaussNewtonVectorProductBackProp)
void	setUseRBMPropUpAsActivations(boolean useRBMPropUpAsActivations)
String	toJson()

Methods inherited from class java.lang.Object

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

Field Detail

pretrain

protected boolean pretrain

Method Detail

getConf

public NeuralNetConfiguration getConf(int i)

getPreProcessor

public OutputPreProcessor getPreProcessor(int layer)

getDampingFactor

public double getDampingFactor()

setDampingFactor

public void setDampingFactor(double dampingFactor)

isUseRBMPropUpAsActivations

public boolean isUseRBMPropUpAsActivations()

setUseRBMPropUpAsActivations

public void setUseRBMPropUpAsActivations(boolean useRBMPropUpAsActivations)

isUseDropConnect

public boolean isUseDropConnect()

setUseDropConnect

public void setUseDropConnect(boolean useDropConnect)

isUseGaussNewtonVectorProductBackProp

public boolean isUseGaussNewtonVectorProductBackProp()

setUseGaussNewtonVectorProductBackProp

public void setUseGaussNewtonVectorProductBackProp(boolean useGaussNewtonVectorProductBackProp)

isPretrain

public boolean isPretrain()

setPretrain

public void setPretrain(boolean pretrain)

getHiddenLayerSizes

public int[] getHiddenLayerSizes()

setHiddenLayerSizes

public void setHiddenLayerSizes(int[] hiddenLayerSizes)

getConfs

public List<NeuralNetConfiguration> getConfs()

setConfs

public void setConfs(List<NeuralNetConfiguration> confs)

toJson

public String toJson()

Returns:

fromJson

public static MultiLayerConfiguration fromJson(String json)

Create a neural net configuration from json

Parameters:

json - the neural net configuration from json

Returns:

equals

public boolean equals(Object o)

Overrides:

equals in class Object

hashCode

public int hashCode()

Overrides:

hashCode in class Object