NeuralNetConfiguration (deeplearning4j-core 0.0.3.3 API)

java.lang.Object
- org.deeplearning4j.nn.conf.NeuralNetConfiguration

All Implemented Interfaces:

Serializable, Cloneable
```
public class NeuralNetConfiguration
extends Object
implements Serializable, Cloneable
```
A Serializable configuration for neural nets that covers per layer parameters

Author:

Adam Gibson

See Also:

Serialized Form

Nested Class Summary

Nested Classes
Modifier and Type	Class and Description
`static class`	`NeuralNetConfiguration.Builder`
`static interface`	`NeuralNetConfiguration.ConfOverride` Interface for a function to override builder configurations at a particular layer
`static class`	`NeuralNetConfiguration.ListBuilder` Fluent interface for building a list of configurations

Field Summary

Fields
Modifier and Type	Field and Description
`protected org.nd4j.linalg.api.activation.ActivationFunction`	`activationFunction`
`protected boolean`	`applySparsity`
`protected int`	`batchSize`
`protected boolean`	`concatBiases`
`protected boolean`	`constrainGradientToUnitNorm`
`protected double`	`corruptionLevel`
`protected org.apache.commons.math3.distribution.RealDistribution`	`dist`
`protected double`	`dropOut`
`protected List<String>`	`gradientList`
`protected int`	`k`
`protected int`	`kernel`
`protected double`	`l2`
`protected LayerFactory`	`layerFactory`
`protected Collection<IterationListener>`	`listeners`
`protected org.nd4j.linalg.lossfunctions.LossFunctions.LossFunction`	`lossFunction`
`protected double`	`momentum`
`protected Map<Integer,Double>`	`momentumAfter`
`protected int`	`nIn`
`protected int`	`nOut`
`protected int`	`numIterations`
`protected OptimizationAlgorithm`	`optimizationAlgo`
`protected int`	`renderWeightsEveryNumEpochs`
`protected int`	`resetAdaGradIterations`
`protected org.apache.commons.math3.random.RandomGenerator`	`rng`
`protected long`	`seed`
`protected StepFunction`	`stepFunction`
`protected boolean`	`useRegularization`
`protected WeightInit`	`weightInit`

Constructor Summary

Constructors
Constructor and Description
`NeuralNetConfiguration()`
NeuralNetConfiguration(double sparsity, boolean useAdaGrad, double lr, int k, double corruptionLevel, int numIterations, double momentum, double l2, boolean useRegularization, Map<Integer,Double> momentumAfter, int resetAdaGradIterations, double dropOut, boolean applySparsity, WeightInit weightInit, OptimizationAlgorithm optimizationAlgo, org.nd4j.linalg.lossfunctions.LossFunctions.LossFunction lossFunction, int renderWeightsEveryNumEpochs, boolean concatBiases, boolean constrainGradientToUnitNorm, org.apache.commons.math3.random.RandomGenerator rng, org.apache.commons.math3.distribution.RealDistribution dist, long seed, int nIn, int nOut, org.nd4j.linalg.api.activation.ActivationFunction activationFunction, RBM.VisibleUnit visibleUnit, RBM.HiddenUnit hiddenUnit, int[] weightShape, int[] filterSize, int[] stride, int[] featureMapSize, int kernel, int batchSize, Collection<IterationListener> listeners, LayerFactory layerFactory)
`NeuralNetConfiguration(NeuralNetConfiguration neuralNetConfiguration)`

Method Summary

All Methods Static Methods Instance Methods Concrete Methods
Modifier and Type	Method and Description
`NeuralNetConfiguration`	`clone()` Creates and returns a copy of this object.
`boolean`	`equals(Object o)`
`static NeuralNetConfiguration`	`fromJson(String json)` Create a neural net configuration from json
`org.nd4j.linalg.api.activation.ActivationFunction`	`getActivationFunction()`
`int`	`getBatchSize()`
`double`	`getCorruptionLevel()`
`org.apache.commons.math3.distribution.RealDistribution`	`getDist()`
`double`	`getDropOut()`
`int[]`	`getFeatureMapSize()`
`int[]`	`getFilterSize()`
`List<String>`	`getGradientList()`
`RBM.HiddenUnit`	`getHiddenUnit()`
`int`	`getK()`
`int`	`getKernel()`
`double`	`getL2()`
`LayerFactory`	`getLayerFactory()`
`Collection<IterationListener>`	`getListeners()`
`org.nd4j.linalg.lossfunctions.LossFunctions.LossFunction`	`getLossFunction()`
`double`	`getLr()`
`double`	`getMomentum()`
`Map<Integer,Double>`	`getMomentumAfter()`
`int`	`getnIn()`
`int`	`getnOut()`
`int`	`getNumFeatureMaps()`
`int`	`getNumIterations()`
`OptimizationAlgorithm`	`getOptimizationAlgo()`
`int`	`getRenderWeightIterations()`
`int`	`getResetAdaGradIterations()`
`org.apache.commons.math3.random.RandomGenerator`	`getRng()`
`long`	`getSeed()`
`double`	`getSparsity()`
`StepFunction`	`getStepFunction()`
`int[]`	`getStride()`
`RBM.VisibleUnit`	`getVisibleUnit()`
`WeightInit`	`getWeightInit()`
`int[]`	`getWeightShape()`
`int`	`hashCode()`
`boolean`	`isApplySparsity()`
`boolean`	`isConcatBiases()`
`boolean`	`isConstrainGradientToUnitNorm()`
`boolean`	`isUseAdaGrad()`
`boolean`	`isUseRegularization()`
`static com.fasterxml.jackson.databind.ObjectMapper`	`mapper()` Object mapper for serialization of configurations
`void`	`setActivationFunction(org.nd4j.linalg.api.activation.ActivationFunction activationFunction)`
`void`	`setApplySparsity(boolean applySparsity)`
`void`	`setBatchSize(int batchSize)`
`static void`	`setClassifier(NeuralNetConfiguration conf)` Set the configuration for classification
`static void`	`setClassifier(NeuralNetConfiguration conf, boolean rows)` Set the conf for classification
`void`	`setConcatBiases(boolean concatBiases)`
`void`	`setConstrainGradientToUnitNorm(boolean constrainGradientToUnitNorm)`
`void`	`setCorruptionLevel(double corruptionLevel)`
`void`	`setDist(org.apache.commons.math3.distribution.RealDistribution dist)`
`void`	`setDropOut(double dropOut)`
`void`	`setFeatureMapSize(int[] featureMapSize)`
`void`	`setFilterSize(int[] filterSize)`
`void`	`setGradientList(List<String> gradientList)`
`void`	`setHiddenUnit(RBM.HiddenUnit hiddenUnit)`
`void`	`setK(int k)`
`void`	`setKernel(int kernel)`
`void`	`setL2(double l2)`
`void`	`setLayerFactory(LayerFactory layerFactory)`
`void`	`setListeners(Collection<IterationListener> listeners)`
`void`	`setLossFunction(org.nd4j.linalg.lossfunctions.LossFunctions.LossFunction lossFunction)`
`void`	`setLr(double lr)`
`void`	`setMomentum(double momentum)`
`void`	`setMomentumAfter(Map<Integer,Double> momentumAfter)`
`void`	`setnIn(int nIn)`
`void`	`setnOut(int nOut)`
`void`	`setNumFeatureMaps(int numFeatureMaps)`
`void`	`setNumIterations(int numIterations)`
`void`	`setOptimizationAlgo(OptimizationAlgorithm optimizationAlgo)`
`void`	`setRenderWeightIterations(int renderWeightsEveryNumEpochs)`
`void`	`setResetAdaGradIterations(int resetAdaGradIterations)`
`void`	`setRng(org.apache.commons.math3.random.RandomGenerator rng)`
`void`	`setSeed(long seed)`
`void`	`setSparsity(double sparsity)`
`void`	`setStepFunction(StepFunction stepFunction)`
`void`	`setStride(int[] stride)`
`void`	`setUseAdaGrad(boolean useAdaGrad)`
`void`	`setUseRegularization(boolean useRegularization)`
`void`	`setVisibleUnit(RBM.VisibleUnit visibleUnit)`
`void`	`setWeightInit(WeightInit weightInit)`
`void`	`setWeightShape(int[] weightShape)`
`String`	`toJson()` Return this configuration as json
`String`	`toString()`

Methods inherited from class java.lang.Object
finalize, getClass, notify, notifyAll, wait, wait, wait

Field Detail

corruptionLevel
```
protected double corruptionLevel
```

numIterations
```
protected int numIterations
```

momentum
```
protected double momentum
```

l2
```
protected double l2
```

useRegularization
```
protected boolean useRegularization
```

momentumAfter

protected Map<Integer,Double> momentumAfter

resetAdaGradIterations
```
protected int resetAdaGradIterations
```

dropOut
```
protected double dropOut
```

applySparsity
```
protected boolean applySparsity
```

weightInit
```
protected WeightInit weightInit
```

optimizationAlgo

protected OptimizationAlgorithm optimizationAlgo

lossFunction

protected org.nd4j.linalg.lossfunctions.LossFunctions.LossFunction lossFunction

renderWeightsEveryNumEpochs

protected int renderWeightsEveryNumEpochs

concatBiases
```
protected boolean concatBiases
```

constrainGradientToUnitNorm

protected boolean constrainGradientToUnitNorm

seed
```
protected long seed
```

rng

protected transient org.apache.commons.math3.random.RandomGenerator rng

dist

protected transient org.apache.commons.math3.distribution.RealDistribution dist

listeners

protected transient Collection<IterationListener> listeners

stepFunction

protected transient StepFunction stepFunction

layerFactory

protected transient LayerFactory layerFactory

gradientList
```
protected List<String> gradientList
```

nIn
```
protected int nIn
```

nOut
```
protected int nOut
```

activationFunction

protected org.nd4j.linalg.api.activation.ActivationFunction activationFunction

k
```
protected int k
```

kernel
```
protected int kernel
```

batchSize
```
protected int batchSize
```

Constructor Detail

NeuralNetConfiguration
```
public NeuralNetConfiguration()
```

NeuralNetConfiguration

public NeuralNetConfiguration(double sparsity,
                              boolean useAdaGrad,
                              double lr,
                              int k,
                              double corruptionLevel,
                              int numIterations,
                              double momentum,
                              double l2,
                              boolean useRegularization,
                              Map<Integer,Double> momentumAfter,
                              int resetAdaGradIterations,
                              double dropOut,
                              boolean applySparsity,
                              WeightInit weightInit,
                              OptimizationAlgorithm optimizationAlgo,
                              org.nd4j.linalg.lossfunctions.LossFunctions.LossFunction lossFunction,
                              int renderWeightsEveryNumEpochs,
                              boolean concatBiases,
                              boolean constrainGradientToUnitNorm,
                              org.apache.commons.math3.random.RandomGenerator rng,
                              org.apache.commons.math3.distribution.RealDistribution dist,
                              long seed,
                              int nIn,
                              int nOut,
                              org.nd4j.linalg.api.activation.ActivationFunction activationFunction,
                              RBM.VisibleUnit visibleUnit,
                              RBM.HiddenUnit hiddenUnit,
                              int[] weightShape,
                              int[] filterSize,
                              int[] stride,
                              int[] featureMapSize,
                              int kernel,
                              int batchSize,
                              Collection<IterationListener> listeners,
                              LayerFactory layerFactory)

NeuralNetConfiguration

public NeuralNetConfiguration(NeuralNetConfiguration neuralNetConfiguration)

Method Detail
- getBatchSize
```
public int getBatchSize()
```
- setBatchSize
```
public void setBatchSize(int batchSize)
```
- getKernel
```
public int getKernel()
```
- setKernel
```
public void setKernel(int kernel)
```
- getLayerFactory
```
public LayerFactory getLayerFactory()
```
- setLayerFactory
```
public void setLayerFactory(LayerFactory layerFactory)
```
- getGradientList
```
public List<String> getGradientList()
```
- setGradientList
```
public void setGradientList(List<String> gradientList)
```
- getStepFunction
```
public StepFunction getStepFunction()
```
- setStepFunction
```
public void setStepFunction(StepFunction stepFunction)
```
- getFeatureMapSize
```
public int[] getFeatureMapSize()
```
- setFeatureMapSize
```
public void setFeatureMapSize(int[] featureMapSize)
```
- getWeightShape
```
public int[] getWeightShape()
```
- setWeightShape
```
public void setWeightShape(int[] weightShape)
```
- getNumIterations
```
public int getNumIterations()
```
- setNumIterations
```
public void setNumIterations(int numIterations)
```
- getK
```
public int getK()
```
- setK
```
public void setK(int k)
```
- getCorruptionLevel
```
public double getCorruptionLevel()
```
- getHiddenUnit
```
public RBM.HiddenUnit getHiddenUnit()
```
- setHiddenUnit
```
public void setHiddenUnit(RBM.HiddenUnit hiddenUnit)
```
- getVisibleUnit
```
public RBM.VisibleUnit getVisibleUnit()
```
- setVisibleUnit
```
public void setVisibleUnit(RBM.VisibleUnit visibleUnit)
```
- getLossFunction
```
public org.nd4j.linalg.lossfunctions.LossFunctions.LossFunction getLossFunction()
```
- setLossFunction
```
public void setLossFunction(org.nd4j.linalg.lossfunctions.LossFunctions.LossFunction lossFunction)
```
- getActivationFunction
```
public org.nd4j.linalg.api.activation.ActivationFunction getActivationFunction()
```
- setActivationFunction
```
public void setActivationFunction(org.nd4j.linalg.api.activation.ActivationFunction activationFunction)
```
- getnIn
```
public int getnIn()
```
- setnIn
```
public void setnIn(int nIn)
```
- getnOut
```
public int getnOut()
```
- setnOut
```
public void setnOut(int nOut)
```
- getSparsity
```
public double getSparsity()
```
- isUseAdaGrad
```
public boolean isUseAdaGrad()
```
- setUseAdaGrad
```
public void setUseAdaGrad(boolean useAdaGrad)
```
- getLr
```
public double getLr()
```
- setLr
```
public void setLr(double lr)
```
- getMomentum
```
public double getMomentum()
```
- getL2
```
public double getL2()
```
- setL2
```
public void setL2(double l2)
```
- isUseRegularization
```
public boolean isUseRegularization()
```
- setUseRegularization
```
public void setUseRegularization(boolean useRegularization)
```
- getMomentumAfter
```
public Map<Integer,Double> getMomentumAfter()
```
- setMomentumAfter
```
public void setMomentumAfter(Map<Integer,Double> momentumAfter)
```
- getResetAdaGradIterations
```
public int getResetAdaGradIterations()
```
- setResetAdaGradIterations
```
public void setResetAdaGradIterations(int resetAdaGradIterations)
```
- getDropOut
```
public double getDropOut()
```
- isApplySparsity
```
public boolean isApplySparsity()
```
- setApplySparsity
```
public void setApplySparsity(boolean applySparsity)
```
- getWeightInit
```
public WeightInit getWeightInit()
```
- setWeightInit
```
public void setWeightInit(WeightInit weightInit)
```
- getOptimizationAlgo
```
public OptimizationAlgorithm getOptimizationAlgo()
```
- setOptimizationAlgo
```
public void setOptimizationAlgo(OptimizationAlgorithm optimizationAlgo)
```
- getRenderWeightIterations
```
public int getRenderWeightIterations()
```
- setRenderWeightIterations
```
public void setRenderWeightIterations(int renderWeightsEveryNumEpochs)
```
- isConcatBiases
```
public boolean isConcatBiases()
```
- setConcatBiases
```
public void setConcatBiases(boolean concatBiases)
```
- isConstrainGradientToUnitNorm
```
public boolean isConstrainGradientToUnitNorm()
```
- setConstrainGradientToUnitNorm
```
public void setConstrainGradientToUnitNorm(boolean constrainGradientToUnitNorm)
```
- getRng
```
public org.apache.commons.math3.random.RandomGenerator getRng()
```
- setRng
```
public void setRng(org.apache.commons.math3.random.RandomGenerator rng)
```
- getSeed
```
public long getSeed()
```
- setSeed
```
public void setSeed(long seed)
```
- getDist
```
public org.apache.commons.math3.distribution.RealDistribution getDist()
```
- setDist
```
public void setDist(org.apache.commons.math3.distribution.RealDistribution dist)
```
- getFilterSize
```
public int[] getFilterSize()
```
- setFilterSize
```
public void setFilterSize(int[] filterSize)
```
- getNumFeatureMaps
```
public int getNumFeatureMaps()
```
- setNumFeatureMaps
```
public void setNumFeatureMaps(int numFeatureMaps)
```
- getStride
```
public int[] getStride()
```
- setStride
```
public void setStride(int[] stride)
```
- equals
```
public boolean equals(Object o)
```
  Overrides:
  
  equals in class Object
- hashCode
```
public int hashCode()
```
  Overrides:
  
  hashCode in class Object
- toString
```
public String toString()
```
  Overrides:
  
  toString in class Object
- setClassifier
```
public static void setClassifier(NeuralNetConfiguration conf)
```
  Set the configuration for classification
  
  Parameters:
  
  conf - the configuration to set
- setClassifier
```
public static void setClassifier(NeuralNetConfiguration conf,
                                 boolean rows)
```
  Set the conf for classification
  
  Parameters:
  
  conf - the configuration to set
  
  rows - whether to use softmax rows or soft max columns
- clone
```
public NeuralNetConfiguration clone()
```
  Creates and returns a copy of this object. The precise meaning of "copy" may depend on the class of the object. The general intent is that, for any object x, the expression:
```
 x.clone() != x
```
  will be true, and that the expression:
```
 x.clone().getClass() == x.getClass()
```
  will be true, but these are not absolute requirements. While it is typically the case that:
```
 x.clone().equals(x)
```
  will be true, this is not an absolute requirement. By convention, the returned object should be obtained by calling super.clone. If a class and all of its superclasses (except Object) obey this convention, it will be the case that x.clone().getClass() == x.getClass(). By convention, the object returned by this method should be independent of this object (which is being cloned). To achieve this independence, it may be necessary to modify one or more fields of the object returned by super.clone before returning it. Typically, this means copying any mutable objects that comprise the internal "deep structure" of the object being cloned and replacing the references to these objects with references to the copies. If a class contains only primitive fields or references to immutable objects, then it is usually the case that no fields in the object returned by super.clone need to be modified. The method clone for class Object performs a specific cloning operation. First, if the class of this object does not implement the interface Cloneable, then a CloneNotSupportedException is thrown. Note that all arrays are considered to implement the interface Cloneable and that the return type of the clone method of an array type T[] is T[] where T is any reference or primitive type. Otherwise, this method creates a new instance of the class of this object and initializes all its fields with exactly the contents of the corresponding fields of this object, as if by assignment; the contents of the fields are not themselves cloned. Thus, this method performs a "shallow copy" of this object, not a "deep copy" operation. The class Object does not itself implement the interface Cloneable, so calling the clone method on an object whose class is Object will result in throwing an exception at run time.
  Overrides:
  
  clone in class Object
  
  Returns:
  
  a clone of this instance.
  
  Throws:
  
  CloneNotSupportedException - if the object's class does not support the Cloneable interface. Subclasses that override the clone method can also throw this exception to indicate that an instance cannot be cloned.
  
  See Also:
  
  Cloneable
- toJson
```
public String toJson()
```
  Return this configuration as json
  
  Returns:
  
  this configuration represented as json
- fromJson
```
public static NeuralNetConfiguration fromJson(String json)
```
  Create a neural net configuration from json
  
  Parameters:
  
  json - the neural net configuration from json
  
  Returns:
- setSparsity
```
public void setSparsity(double sparsity)
```
- setCorruptionLevel
```
public void setCorruptionLevel(double corruptionLevel)
```
- setMomentum
```
public void setMomentum(double momentum)
```
- setDropOut
```
public void setDropOut(double dropOut)
```
- getListeners
```
public Collection<IterationListener> getListeners()
```
- setListeners
```
public void setListeners(Collection<IterationListener> listeners)
```
- mapper
```
public static com.fasterxml.jackson.databind.ObjectMapper mapper()
```
  Object mapper for serialization of configurations
  
  Returns:

Class NeuralNetConfiguration

Nested Class Summary

Field Summary

Constructor Summary

Method Summary

Methods inherited from class java.lang.Object

Field Detail

corruptionLevel

numIterations

momentum

l2

useRegularization

momentumAfter

resetAdaGradIterations

dropOut

applySparsity

weightInit

optimizationAlgo

lossFunction

renderWeightsEveryNumEpochs

concatBiases

constrainGradientToUnitNorm

seed

rng

dist

listeners

stepFunction

layerFactory

gradientList

nIn

nOut

activationFunction

k

kernel

batchSize

Constructor Detail

NeuralNetConfiguration

NeuralNetConfiguration

NeuralNetConfiguration

Method Detail

getBatchSize

setBatchSize

getKernel

setKernel

getLayerFactory

setLayerFactory

getGradientList

setGradientList

getStepFunction

setStepFunction

getFeatureMapSize

setFeatureMapSize

getWeightShape

setWeightShape

getNumIterations

setNumIterations

getK

setK

getCorruptionLevel

getHiddenUnit

setHiddenUnit

getVisibleUnit

setVisibleUnit

getLossFunction

setLossFunction

getActivationFunction

setActivationFunction

getnIn

setnIn

getnOut

setnOut

getSparsity

isUseAdaGrad

setUseAdaGrad

getLr

setLr

getMomentum

getL2

setL2

isUseRegularization