org.deeplearning4j.nn.conf.layers

Class Convolution3D.Builder

java.lang.Object

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

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

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

org.deeplearning4j.nn.conf.layers.ConvolutionLayer.BaseConvBuilder<Convolution3D.Builder>

org.deeplearning4j.nn.conf.layers.Convolution3D.Builder

Enclosing class:

Convolution3D

public static class Convolution3D.Builder
extends ConvolutionLayer.BaseConvBuilder<Convolution3D.Builder>

Field Summary

Fields inherited from class org.deeplearning4j.nn.conf.layers.ConvolutionLayer.BaseConvBuilder

convolutionDim, convolutionMode, cudnnAlgoMode, cudnnAllowFallback, cudnnBwdDataAlgo, cudnnBwdFilterAlgo, cudnnFwdAlgo, dilation, hasBias, kernelSize, padding, stride

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

nIn, nOut

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

activationFn, biasInit, biasUpdater, gainInit, gradientNormalization, gradientNormalizationThreshold, iupdater, regularization, regularizationBias, weightInitFn, weightNoise

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

allParamConstraints, biasConstraints, iDropout, layerName, weightConstraints

Constructor Summary

Constructors

Constructor and Description
Builder()
Builder(int... kernelSize)
Builder(int[] kernelSize, int[] stride)
Builder(int[] kernelSize, int[] stride, int[] padding)
Builder(int[] kernelSize, int[] stride, int[] padding, int[] dilation)

Method Summary

Modifier and Type	Method and Description
protected boolean	allowCausal()
Convolution3D	build()
Convolution3D.Builder	convolutionMode(ConvolutionMode mode) Set the convolution mode for the Convolution layer.
Convolution3D.Builder	dataFormat(Convolution3D.DataFormat dataFormat) The data format for input and output activations. NCDHW: activations (in/out) should have shape [minibatch, channels, depth, height, width] NDHWC: activations (in/out) should have shape [minibatch, depth, height, width, channels]
Convolution3D.Builder	dilation(int... dilation) Set dilation size for 3D convolutions in (depth, height, width) order
Convolution3D.Builder	kernelSize(int... kernelSize) Set kernel size for 3D convolutions in (depth, height, width) order
Convolution3D.Builder	padding(int... padding) Set padding size for 3D convolutions in (depth, height, width) order
void	setDilation(int... dilation) Set dilation size for 3D convolutions in (depth, height, width) order
void	setKernelSize(int... kernelSize) Set kernel size for 3D convolutions in (depth, height, width) order
void	setPadding(int... padding) Set padding size for 3D convolutions in (depth, height, width) order
void	setStride(int... stride) Set stride size for 3D convolutions in (depth, height, width) order
Convolution3D.Builder	stride(int... stride) Set stride size for 3D convolutions in (depth, height, width) order

Methods inherited from class org.deeplearning4j.nn.conf.layers.ConvolutionLayer.BaseConvBuilder

cudnnAlgoMode, cudnnAllowFallback, cudnnBwdDataMode, cudnnBwdFilterMode, cudnnFwdMode, hasBias, helperAllowFallback, setConvolutionMode

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

nIn, nIn, nOut, nOut, units

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

activation, activation, biasInit, biasUpdater, dist, gainInit, gradientNormalization, gradientNormalizationThreshold, l1, l1Bias, l2, l2Bias, regularization, regularizationBias, updater, updater, weightDecay, weightDecay, weightDecayBias, weightDecayBias, weightInit, weightInit, weightInit, weightNoise

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

constrainAllParameters, constrainBias, constrainWeights, dropOut, dropOut, name

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

Builder

public Builder()

Builder

public Builder(int[] kernelSize,
               int[] stride,
               int[] padding,
               int[] dilation)

Builder

public Builder(int[] kernelSize,
               int[] stride,
               int[] padding)

Builder

public Builder(int[] kernelSize,
               int[] stride)

Builder

public Builder(int... kernelSize)

Method Detail

allowCausal

protected boolean allowCausal()

Specified by:

allowCausal in class ConvolutionLayer.BaseConvBuilder<Convolution3D.Builder>

kernelSize

public Convolution3D.Builder kernelSize(int... kernelSize)

Set kernel size for 3D convolutions in (depth, height, width) order

Overrides:

kernelSize in class ConvolutionLayer.BaseConvBuilder<Convolution3D.Builder>

Parameters:

kernelSize - kernel size

Returns:

3D convolution layer builder

stride

public Convolution3D.Builder stride(int... stride)

Set stride size for 3D convolutions in (depth, height, width) order

Overrides:

stride in class ConvolutionLayer.BaseConvBuilder<Convolution3D.Builder>

Parameters:

stride - kernel size

Returns:

3D convolution layer builder

padding

public Convolution3D.Builder padding(int... padding)

Set padding size for 3D convolutions in (depth, height, width) order

Overrides:

padding in class ConvolutionLayer.BaseConvBuilder<Convolution3D.Builder>

Parameters:

padding - kernel size

Returns:

3D convolution layer builder

dilation

public Convolution3D.Builder dilation(int... dilation)

Set dilation size for 3D convolutions in (depth, height, width) order

Overrides:

dilation in class ConvolutionLayer.BaseConvBuilder<Convolution3D.Builder>

Parameters:

dilation - kernel size

Returns:

3D convolution layer builder

convolutionMode

public Convolution3D.Builder convolutionMode(ConvolutionMode mode)

Description copied from class: ConvolutionLayer.BaseConvBuilder

Set the convolution mode for the Convolution layer. See ConvolutionMode for more details

Overrides:

convolutionMode in class ConvolutionLayer.BaseConvBuilder<Convolution3D.Builder>

Parameters:

mode - Convolution mode for layer

dataFormat

public Convolution3D.Builder dataFormat(Convolution3D.DataFormat dataFormat)

The data format for input and output activations.
NCDHW: activations (in/out) should have shape [minibatch, channels, depth, height, width]
NDHWC: activations (in/out) should have shape [minibatch, depth, height, width, channels]

Parameters:

dataFormat - Data format to use for activations

setKernelSize

public void setKernelSize(int... kernelSize)

Set kernel size for 3D convolutions in (depth, height, width) order

Parameters:

kernelSize - kernel size

setStride

public void setStride(int... stride)

Set stride size for 3D convolutions in (depth, height, width) order

Parameters:

stride - kernel size

setPadding

public void setPadding(int... padding)

Set padding size for 3D convolutions in (depth, height, width) order

Parameters:

padding - kernel size

setDilation

public void setDilation(int... dilation)

Set dilation size for 3D convolutions in (depth, height, width) order

Parameters:

dilation - kernel size

build

public Convolution3D build()

Specified by:

build in class Layer.Builder<Convolution3D.Builder>