BatchNormalizationSpace

java.lang.Object
- org.deeplearning4j.arbiter.optimize.api.AbstractParameterSpace<L>
- - org.deeplearning4j.arbiter.layers.LayerSpace<L>
  - - org.deeplearning4j.arbiter.layers.BaseLayerSpace<L>
    - - org.deeplearning4j.arbiter.layers.FeedForwardLayerSpace<BatchNormalization>
      - org.deeplearning4j.arbiter.layers.BatchNormalizationSpace

All Implemented Interfaces:

ParameterSpace<BatchNormalization>
```
public class BatchNormalizationSpace
extends FeedForwardLayerSpace<BatchNormalization>
```
LayerSpace for batch normalization layers

Nested Class Summary

Nested Classes
Modifier and Type Class and Description

static class BatchNormalizationSpace.Builder

Nested Classes
Modifier and Type	Class and Description
`static class`	`BatchNormalizationSpace.Builder`

Field Summary

Fields
Modifier and Type	Field and Description
`protected ParameterSpace<java.lang.Double>`	`beta`
`protected ParameterSpace<java.util.List<LayerConstraint>>`	`constrainBeta`
`protected ParameterSpace<java.util.List<LayerConstraint>>`	`constrainGamma`
`protected ParameterSpace<java.lang.Double>`	`decay`
`protected ParameterSpace<java.lang.Double>`	`eps`
`protected ParameterSpace<java.lang.Double>`	`gamma`
`protected ParameterSpace<java.lang.Boolean>`	`isMinibatch`
`protected ParameterSpace<java.lang.Boolean>`	`lockGammaBeta`

Fields inherited from class org.deeplearning4j.arbiter.layers.FeedForwardLayerSpace
constrainAll, constrainBias, constrainWeights, nIn, nOut

Fields inherited from class org.deeplearning4j.arbiter.layers.BaseLayerSpace
activationFunction, biasInit, biasUpdater, dist, gradientNormalization, gradientNormalizationThreshold, l1, l1Bias, l2, l2Bias, numParameters, updater, weightInit, weightNoise

Fields inherited from class org.deeplearning4j.arbiter.layers.LayerSpace
dropOut

Method Summary

All Methods Instance Methods Concrete Methods
Modifier and Type	Method and Description
`BatchNormalization`	`getValue(double[] parameterValues)` Generate a candidate given a set of values.
`protected void`	`setLayerOptionsBuilder(BatchNormalization.Builder builder, double[] values)`
`java.lang.String`	`toString()`
`java.lang.String`	`toString(java.lang.String delim)`

Methods inherited from class org.deeplearning4j.arbiter.layers.FeedForwardLayerSpace
setLayerOptionsBuilder

Methods inherited from class org.deeplearning4j.arbiter.layers.BaseLayerSpace
isLeaf, numParameters, setIndices, setLayerOptionsBuilder

Methods inherited from class org.deeplearning4j.arbiter.layers.LayerSpace
collectLeaves, setLayerOptionsBuilder

Methods inherited from class org.deeplearning4j.arbiter.optimize.api.AbstractParameterSpace
getNestedSpaces

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

Field Detail

decay

protected ParameterSpace<java.lang.Double> decay

eps

protected ParameterSpace<java.lang.Double> eps

isMinibatch

protected ParameterSpace<java.lang.Boolean> isMinibatch

lockGammaBeta

protected ParameterSpace<java.lang.Boolean> lockGammaBeta

gamma

protected ParameterSpace<java.lang.Double> gamma

beta

protected ParameterSpace<java.lang.Double> beta

constrainBeta

protected ParameterSpace<java.util.List<LayerConstraint>> constrainBeta

constrainGamma

protected ParameterSpace<java.util.List<LayerConstraint>> constrainGamma

Method Detail
- getValue
```
public BatchNormalization getValue(double[] parameterValues)
```
  Description copied from interface: ParameterSpace
  
  Generate a candidate given a set of values. These values are then mapped to a specific candidate, using some mapping function (such as the prior probability distribution)
  
  Parameters:
  
  parameterValues - A set of values, each in the range [0,1], of length ParameterSpace.numParameters()
- setLayerOptionsBuilder
```
protected void setLayerOptionsBuilder(BatchNormalization.Builder builder,
                                      double[] values)
```
- toString
```
public java.lang.String toString()
```
  Overrides:
  
  toString in class FeedForwardLayerSpace<BatchNormalization>
- toString
```
public java.lang.String toString(java.lang.String delim)
```
  Overrides:
  
  toString in class FeedForwardLayerSpace<BatchNormalization>

Class BatchNormalizationSpace

Nested Class Summary

Field Summary

Fields inherited from class org.deeplearning4j.arbiter.layers.FeedForwardLayerSpace

Fields inherited from class org.deeplearning4j.arbiter.layers.BaseLayerSpace

Fields inherited from class org.deeplearning4j.arbiter.layers.LayerSpace

Method Summary

Methods inherited from class org.deeplearning4j.arbiter.layers.FeedForwardLayerSpace

Methods inherited from class org.deeplearning4j.arbiter.layers.BaseLayerSpace

Methods inherited from class org.deeplearning4j.arbiter.layers.LayerSpace

Methods inherited from class org.deeplearning4j.arbiter.optimize.api.AbstractParameterSpace

Methods inherited from class java.lang.Object

Field Detail

decay

eps

isMinibatch

lockGammaBeta

gamma

beta

constrainBeta

constrainGamma

Method Detail

getValue

setLayerOptionsBuilder

toString

toString