org.deeplearning4j.nn.conf.layers

Class SeparableConvolution2D.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<SeparableConvolution2D.Builder>

org.deeplearning4j.nn.conf.layers.SeparableConvolution2D.Builder

Enclosing class:

SeparableConvolution2D

public static class SeparableConvolution2D.Builder
extends ConvolutionLayer.BaseConvBuilder<SeparableConvolution2D.Builder>

Field Summary

Fields

Modifier and Type	Field and Description
int	depthMultiplier
protected List<LayerConstraint>	pointWiseConstraints

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, dist, gradientNormalization, gradientNormalizationThreshold, iupdater, l1, l1Bias, l2, l2Bias, weightInit, 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)

Method Summary

Modifier and Type	Method and Description
SeparableConvolution2D	build()
SeparableConvolution2D.Builder	constrainPointWise(LayerConstraint... constraints) Set constraints to be applied to the point-wise convolution weight parameters of this layer.
SeparableConvolution2D.Builder	depthMultiplier(int depthMultiplier) Set channels multiplier of channels-wise step in separable convolution
SeparableConvolution2D.Builder	kernelSize(int... kernelSize) Size of the convolution rows/columns
SeparableConvolution2D.Builder	padding(int... padding)
SeparableConvolution2D.Builder	stride(int... stride)

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

convolutionMode, cudnnAlgoMode, cudnnAllowFallback, cudnnBwdDataMode, cudnnBwdFilterMode, cudnnFwdMode, dilation, hasBias

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

nIn, nOut, units

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

activation, activation, biasInit, biasUpdater, dist, gradientNormalization, gradientNormalizationThreshold, l1, l1Bias, l2, l2Bias, updater, updater, 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

Field Detail

depthMultiplier

public int depthMultiplier

pointWiseConstraints

protected List<LayerConstraint> pointWiseConstraints

Constructor Detail

Builder

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

Builder

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

Builder

public Builder(int... kernelSize)

Builder

public Builder()

Method Detail

depthMultiplier

public SeparableConvolution2D.Builder depthMultiplier(int depthMultiplier)

Set channels multiplier of channels-wise step in separable convolution

Parameters:

depthMultiplier - integer value, for each input map we get depthMultipler outputs in channels-wise step.

Returns:

Builder

constrainPointWise

public SeparableConvolution2D.Builder constrainPointWise(LayerConstraint... constraints)

Set constraints to be applied to the point-wise convolution weight parameters of this layer. Default: no constraints.
Constraints can be used to enforce certain conditions (non-negativity of parameters, max-norm regularization, etc). These constraints are applied at each iteration, after the parameters have been updated.

Parameters:

constraints - Constraints to apply to the point-wise convolution parameters of this layer

kernelSize

public SeparableConvolution2D.Builder kernelSize(int... kernelSize)

Size of the convolution rows/columns

Parameters:

kernelSize - the height and width of the kernel

Returns:

stride

public SeparableConvolution2D.Builder stride(int... stride)

padding

public SeparableConvolution2D.Builder padding(int... padding)

build

public SeparableConvolution2D build()

Specified by:

build in class Layer.Builder<SeparableConvolution2D.Builder>