org.deeplearning4j.nn.conf.layers

Class Subsampling3DLayer.BaseSubsamplingBuilder<T extends Subsampling3DLayer.BaseSubsamplingBuilder<T>>

java.lang.Object

org.deeplearning4j.nn.conf.layers.Layer.Builder<T>

org.deeplearning4j.nn.conf.layers.Subsampling3DLayer.BaseSubsamplingBuilder<T>

Direct Known Subclasses:

Subsampling3DLayer.Builder

Enclosing class:

Subsampling3DLayer

protected abstract static class Subsampling3DLayer.BaseSubsamplingBuilder<T extends Subsampling3DLayer.BaseSubsamplingBuilder<T>>
extends Layer.Builder<T>

Field Summary

Fields

Modifier and Type	Field and Description
protected ConvolutionMode	convolutionMode
protected boolean	cudnnAllowFallback
protected int[]	kernelSize
protected int[]	padding
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(Subsampling3DLayer.PoolingType poolingType)
protected	BaseSubsamplingBuilder(Subsampling3DLayer.PoolingType poolingType, int[] kernelSize)
protected	BaseSubsamplingBuilder(Subsampling3DLayer.PoolingType poolingType, int[] kernelSize, int[] stride)
protected	BaseSubsamplingBuilder(Subsampling3DLayer.PoolingType poolingType, int[] kernelSize, int[] stride, int[] padding)

Method Summary

Modifier and Type	Method and Description
T	convolutionMode(ConvolutionMode convolutionMode) Set the convolution mode for the Convolution layer.
T	cudnnAllowFallback(boolean allowFallback) 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.
T	poolingType(Subsampling3DLayer.PoolingType poolingType)

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

cudnnAllowFallback

protected boolean cudnnAllowFallback

Constructor Detail

BaseSubsamplingBuilder

protected BaseSubsamplingBuilder(Subsampling3DLayer.PoolingType poolingType,
                                 int[] kernelSize,
                                 int[] stride)

BaseSubsamplingBuilder

protected BaseSubsamplingBuilder(Subsampling3DLayer.PoolingType poolingType,
                                 int[] kernelSize)

BaseSubsamplingBuilder

protected BaseSubsamplingBuilder(Subsampling3DLayer.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(Subsampling3DLayer.PoolingType poolingType)

BaseSubsamplingBuilder

protected BaseSubsamplingBuilder(PoolingType poolingType)

Method Detail

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(Subsampling3DLayer.PoolingType poolingType)

cudnnAllowFallback

public T cudnnAllowFallback(boolean allowFallback)

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

Parameters:

allowFallback - Whether fallback to non-CuDNN implementation should be used