SubsamplingLayer.BaseSubsamplingBuilder (deeplearning4j-nn 1.0.0-beta7 API)

java.lang.Object
- org.deeplearning4j.nn.conf.layers.Layer.Builder<T>
- - org.deeplearning4j.nn.conf.layers.SubsamplingLayer.BaseSubsamplingBuilder<T>

Direct Known Subclasses:: Subsampling1DLayer.Builder, SubsamplingLayer.Builder

Enclosing class:: SubsamplingLayer

protected abstract static class SubsamplingLayer.BaseSubsamplingBuilder<T extends SubsamplingLayer.BaseSubsamplingBuilder<T>>
extends Layer.Builder<T>

Field Summary

Fields
Modifier and Type	Field and Description
`protected boolean`	`avgPoolIncludePadInDivisor`
`protected ConvolutionMode`	`convolutionMode` Set the convolution mode for the Convolution layer.
`protected boolean`	`cudnnAllowFallback` When using CuDNN and an error is encountered, should fallback to the non-CuDNN implementatation be allowed? If set to false, an exception in CuDNN will be propagated back to the user.
`protected double`	`eps`
`protected int[]`	`kernelSize`
`protected int[]`	`padding`
`protected int`	`pnorm`
`protected PoolingType`	`poolingType`
`protected int[]`	`stride`

Fields inherited from class org.deeplearning4j.nn.conf.layers.Layer.Builder
allParamConstraints, biasConstraints, iDropout, layerName, weightConstraints

Constructor Summary

Constructors
Modifier	Constructor and Description
`protected`	`BaseSubsamplingBuilder(int... kernelSize)`
`protected`	`BaseSubsamplingBuilder(int[] kernelSize, int[] stride)`
`protected`	`BaseSubsamplingBuilder(int[] kernelSize, int[] stride, int[] padding)`
`protected`	`BaseSubsamplingBuilder(PoolingType poolingType)`
`protected`	`BaseSubsamplingBuilder(PoolingType poolingType, int[] kernelSize)`
`protected`	`BaseSubsamplingBuilder(PoolingType poolingType, int[] kernelSize, int[] stride, int[] padding)`
`protected`	`BaseSubsamplingBuilder(SubsamplingLayer.PoolingType poolingType)`
`protected`	`BaseSubsamplingBuilder(SubsamplingLayer.PoolingType poolingType, int[] kernelSize)`
`protected`	`BaseSubsamplingBuilder(SubsamplingLayer.PoolingType poolingType, int[] kernelSize, int[] stride)`
`protected`	`BaseSubsamplingBuilder(SubsamplingLayer.PoolingType poolingType, int[] kernelSize, int[] stride, int[] padding)`

Method Summary

All Methods Instance Methods Abstract Methods Concrete Methods Deprecated Methods
Modifier and Type	Method and Description
`protected abstract boolean`	`allowCausal()`
`T`	`avgPoolIncludePadInDivisor(boolean avgPoolIncludePadInDivisor)` When doing average pooling, should the padding values be included in the divisor or not? Not applicable for max and p-norm pooling. Users should not usually set this - instead, leave it as the default (false).
`T`	`convolutionMode(ConvolutionMode convolutionMode)` Set the convolution mode for the Convolution layer.
`T`	`cudnnAllowFallback(boolean allowFallback)` Deprecated. Use `helperAllowFallback(boolean)`
`T`	`eps(double eps)`
`T`	`helperAllowFallback(boolean allowFallback)` When using CuDNN or MKLDNN and an error is encountered, should fallback to the non-helper implementation be allowed? If set to false, an exception in the helper will be propagated back to the user.
`T`	`pnorm(int pnorm)`
`T`	`poolingType(PoolingType poolingType)`
`T`	`poolingType(SubsamplingLayer.PoolingType poolingType)`
`void`	`setConvolutionMode(ConvolutionMode convolutionMode)`
`void`	`setEps(double eps)`
`void`	`setPnorm(int pnorm)`

Methods inherited from class org.deeplearning4j.nn.conf.layers.Layer.Builder
build, constrainAllParameters, constrainBias, constrainWeights, dropOut, dropOut, name

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

- Field Detail
  - poolingType
```
protected PoolingType poolingType
```
  - kernelSize
```
protected int[] kernelSize
```
  - stride
```
protected int[] stride
```
  - padding
```
protected int[] padding
```
  - convolutionMode
```
protected ConvolutionMode convolutionMode
```
    Set the convolution mode for the Convolution layer. See ConvolutionMode for more details Convolution mode for layer
  - pnorm
```
protected int pnorm
```
  - eps
```
protected double eps
```
  - cudnnAllowFallback
```
protected boolean cudnnAllowFallback
```
    When using CuDNN and an error is encountered, should fallback to the non-CuDNN implementatation be allowed? If set to false, an exception in CuDNN will be propagated back to the user. If false, the built-in (non-CuDNN) implementation for ConvolutionLayer will be used Whether fallback to non-CuDNN implementation should be used
  - avgPoolIncludePadInDivisor
```
protected boolean avgPoolIncludePadInDivisor
```
- Constructor Detail
  - BaseSubsamplingBuilder
```
protected BaseSubsamplingBuilder(SubsamplingLayer.PoolingType poolingType,
                                 int[] kernelSize,
                                 int[] stride)
```
  - BaseSubsamplingBuilder
```
protected BaseSubsamplingBuilder(SubsamplingLayer.PoolingType poolingType,
                                 int[] kernelSize)
```
  - BaseSubsamplingBuilder
```
protected BaseSubsamplingBuilder(SubsamplingLayer.PoolingType poolingType,
                                 int[] kernelSize,
                                 int[] stride,
                                 int[] padding)
```
  - BaseSubsamplingBuilder
```
protected BaseSubsamplingBuilder(PoolingType poolingType,
                                 int[] kernelSize)
```
  - BaseSubsamplingBuilder
```
protected BaseSubsamplingBuilder(PoolingType poolingType,
                                 int[] kernelSize,
                                 int[] stride,
                                 int[] padding)
```
  - BaseSubsamplingBuilder
```
protected BaseSubsamplingBuilder(int[] kernelSize,
                                 int[] stride,
                                 int[] padding)
```
  - BaseSubsamplingBuilder
```
protected BaseSubsamplingBuilder(int[] kernelSize,
                                 int[] stride)
```
  - BaseSubsamplingBuilder
```
protected BaseSubsamplingBuilder(int... kernelSize)
```
  - BaseSubsamplingBuilder
```
protected BaseSubsamplingBuilder(SubsamplingLayer.PoolingType poolingType)
```
  - BaseSubsamplingBuilder
```
protected BaseSubsamplingBuilder(PoolingType poolingType)
```
- Method Detail
  - setPnorm
```
public void setPnorm(int pnorm)
```
  - setEps
```
public void setEps(double eps)
```
  - allowCausal
```
protected abstract boolean allowCausal()
```
  - setConvolutionMode
```
public void setConvolutionMode(ConvolutionMode convolutionMode)
```
  - convolutionMode
```
public T convolutionMode(ConvolutionMode convolutionMode)
```
    Set the convolution mode for the Convolution layer. See ConvolutionMode for more details
    
    Parameters:
    
    convolutionMode - Convolution mode for layer
  - poolingType
```
public T poolingType(SubsamplingLayer.PoolingType poolingType)
```
  - poolingType
```
public T poolingType(PoolingType poolingType)
```
  - pnorm
```
public T pnorm(int pnorm)
```
  - eps
```
public T eps(double eps)
```
  - cudnnAllowFallback
```
@Deprecated
public T cudnnAllowFallback(boolean allowFallback)
```
    Deprecated. Use helperAllowFallback(boolean)
    
    When using CuDNN or MKLDNN and an error is encountered, should fallback to the non-helper implementation be allowed? If set to false, an exception in the helper will be propagated back to the user. If true, the built-in (non-MKL/CuDNN) implementation for ConvolutionLayer will be used
    
    Parameters:
    
    allowFallback - Whether fallback to non-CuDNN implementation should be used
  - helperAllowFallback
```
public T helperAllowFallback(boolean allowFallback)
```
    When using CuDNN or MKLDNN and an error is encountered, should fallback to the non-helper implementation be allowed? If set to false, an exception in the helper will be propagated back to the user. If true, the built-in (non-MKL/CuDNN) implementation for SubsamplingLayer will be used
    
    Parameters:
    
    allowFallback - Whether fallback to non-CuDNN implementation should be used
  - avgPoolIncludePadInDivisor
```
public T avgPoolIncludePadInDivisor(boolean avgPoolIncludePadInDivisor)
```
    When doing average pooling, should the padding values be included in the divisor or not?
    Not applicable for max and p-norm pooling.
    Users should not usually set this - instead, leave it as the default (false). It is included mainly for backward compatibility of older models
    Consider the following 2x2 segment along the right side of the image:
```
 [A, P]
 [B, P]
 
```
    Where A and B are actual values, and P is padding (0).
    With avgPoolIncludePadInDivisor = true, we have: out = (A+B+0+0)/4
    With avgPoolIncludePadInDivisor = false, we have: out = (A+B+0+0)/2
    
    Earlier versions of DL4J originally included padding in the count, newer versions exclude it.
    Parameters:
    
    avgPoolIncludePadInDivisor - Whether the divisor should include or exclude padding for average pooling

Class SubsamplingLayer.BaseSubsamplingBuilder<T extends SubsamplingLayer.BaseSubsamplingBuilder<T>>

Field Summary

Fields inherited from class org.deeplearning4j.nn.conf.layers.Layer.Builder

Constructor Summary

Method Summary

Methods inherited from class org.deeplearning4j.nn.conf.layers.Layer.Builder

Methods inherited from class java.lang.Object

Field Detail

poolingType

kernelSize

stride

padding

convolutionMode

pnorm

eps

cudnnAllowFallback

avgPoolIncludePadInDivisor

Constructor Detail

BaseSubsamplingBuilder

BaseSubsamplingBuilder

BaseSubsamplingBuilder

BaseSubsamplingBuilder

BaseSubsamplingBuilder

BaseSubsamplingBuilder

BaseSubsamplingBuilder

BaseSubsamplingBuilder

BaseSubsamplingBuilder

BaseSubsamplingBuilder

Method Detail

setPnorm

setEps

allowCausal

setConvolutionMode

convolutionMode

poolingType

poolingType

pnorm

eps

cudnnAllowFallback

helperAllowFallback

avgPoolIncludePadInDivisor