SeparableConvolution2DLayerSpace (deeplearning4j 1.0.0-beta7 API)

Skip navigation links

All Classes

Summary:
Nested |
Field |
Constr |
Method

Detail:
Field |
Constr |
Method

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<T>
      - org.deeplearning4j.arbiter.layers.BaseConvolutionLayerSpace<SeparableConvolution2D>
        
        org.deeplearning4j.arbiter.layers.SeparableConvolution2DLayerSpace

All Implemented Interfaces:: ParameterSpace<SeparableConvolution2D>

public class SeparableConvolution2DLayerSpace
extends BaseConvolutionLayerSpace<SeparableConvolution2D>

Nested Class Summary

Nested Classes
Modifier and Type Class and Description

static class SeparableConvolution2DLayerSpace.Builder

Field Summary

Fields
Modifier and Type Field and Description

protected ParameterSpace<List<LayerConstraint>> pointWiseConstraints
- Fields inherited from class org.deeplearning4j.arbiter.layers.BaseConvolutionLayerSpace
  convolutionMode, dilation, hasBias, kernelSize, padding, stride
- 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

Constructor Summary

Constructors
Modifier Constructor and Description

protected SeparableConvolution2DLayerSpace(SeparableConvolution2DLayerSpace.Builder builder)

Method Summary

All Methods Instance Methods Concrete Methods
Modifier and Type	Method and Description
`SeparableConvolution2D`	`getValue(double[] parameterValues)` Generate a candidate given a set of values.
`protected void`	`setLayerOptionsBuilder(SeparableConvolution2D.Builder builder, double[] values)`

Methods inherited from class org.deeplearning4j.arbiter.layers.BaseConvolutionLayerSpace
setLayerOptionsBuilder, toString, toString

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
  - pointWiseConstraints
```
protected ParameterSpace<List<LayerConstraint>> pointWiseConstraints
```
- Constructor Detail
  - SeparableConvolution2DLayerSpace
```
protected SeparableConvolution2DLayerSpace(SeparableConvolution2DLayerSpace.Builder builder)
```
- Method Detail
  - getValue
```
public SeparableConvolution2D 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(SeparableConvolution2D.Builder builder,
                                      double[] values)
```

Skip navigation links

All Classes

Summary:
Nested |
Field |
Constr |
Method

Detail:
Field |
Constr |
Method

Copyright © 2020. All rights reserved.