org.deeplearning4j.nn.conf.layers

Class SeparableConvolution2D

java.lang.Object

org.deeplearning4j.nn.conf.layers.Layer

org.deeplearning4j.nn.conf.layers.BaseLayer

org.deeplearning4j.nn.conf.layers.FeedForwardLayer

org.deeplearning4j.nn.conf.layers.ConvolutionLayer

org.deeplearning4j.nn.conf.layers.SeparableConvolution2D

All Implemented Interfaces:

Serializable, Cloneable, TrainingConfig

public class SeparableConvolution2D
extends ConvolutionLayer

2D Separable convolution layer configuration. Separable convolutions split a regular convolution operation into two simpler operations, which are usually computationally more efficient. The first step in a separable convolution is a channels-wise convolution, which operates on each of the input maps separately. A channels multiplier is used to specify the number of outputs per input map in this step. This convolution is carried out with the specified kernel sizes, stride and padding values. The second step is a point-wise operation, in which the intermediary outputs of the channels-wise convolution are mapped to the desired number of feature maps, by using a 1x1 convolution. The result of chaining these two operations will result in a tensor of the same shape as that for a standard conv2d operation.

Author:

Max Pumperla

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	SeparableConvolution2D.Builder

Nested classes/interfaces inherited from class org.deeplearning4j.nn.conf.layers.ConvolutionLayer

ConvolutionLayer.AlgoMode, ConvolutionLayer.BaseConvBuilder<T extends ConvolutionLayer.BaseConvBuilder<T>>, ConvolutionLayer.BwdDataAlgo, ConvolutionLayer.BwdFilterAlgo, ConvolutionLayer.FwdAlgo

Field Summary

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

cnn2dDataFormat, convolutionMode, cudnnAlgoMode, cudnnAllowFallback, cudnnBwdDataAlgo, cudnnBwdFilterAlgo, cudnnFwdAlgo, dilation, hasBias, kernelSize, padding, stride

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

nIn, nOut, timeDistributedFormat

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

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

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

constraints, iDropout, layerName

Constructor Summary

Constructors

Modifier	Constructor and Description
protected	SeparableConvolution2D(SeparableConvolution2D.Builder builder) SeparableConvolution2D layer nIn in the input layer is the number of channels nOut is the number of filters to be used in the net or in other words the channels The builder specifies the filter/kernel size, the stride and padding The pooling layer takes the kernel size

Method Summary

Modifier and Type	Method and Description
SeparableConvolution2D	clone()
InputType	getOutputType(int layerIndex, InputType inputType) For a given type of input to this layer, what is the type of the output?
boolean	hasBias()
protected void	initializeConstraints(Layer.Builder<?> builder) Initialize the weight constraints.
ParamInitializer	initializer()
Layer	instantiate(NeuralNetConfiguration conf, Collection<TrainingListener> trainingListeners, int layerIndex, INDArray layerParamsView, boolean initializeParams, DataType networkDataType)

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

getMemoryReport, getPreProcessorForInputType, setNIn

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

isPretrainParam

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

getGradientNormalization, getRegularizationByParam, getUpdaterByParam, resetLayerDefaultConfig

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

setDataType

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.deeplearning4j.nn.api.TrainingConfig

getGradientNormalizationThreshold, getLayerName

Constructor Detail

SeparableConvolution2D

protected SeparableConvolution2D(SeparableConvolution2D.Builder builder)

SeparableConvolution2D layer nIn in the input layer is the number of channels nOut is the number of filters to be used in the net or in other words the channels The builder specifies the filter/kernel size, the stride and padding The pooling layer takes the kernel size

Method Detail

initializeConstraints

protected void initializeConstraints(Layer.Builder<?> builder)

Description copied from class: Layer

Initialize the weight constraints. Should be called last, in the outer-most constructor

Overrides:

initializeConstraints in class Layer

hasBias

public boolean hasBias()

Overrides:

hasBias in class ConvolutionLayer

clone

public SeparableConvolution2D clone()

Overrides:

clone in class ConvolutionLayer

instantiate

public Layer instantiate(NeuralNetConfiguration conf,
                         Collection<TrainingListener> trainingListeners,
                         int layerIndex,
                         INDArray layerParamsView,
                         boolean initializeParams,
                         DataType networkDataType)

Overrides:

instantiate in class ConvolutionLayer

initializer

public ParamInitializer initializer()

Overrides:

initializer in class ConvolutionLayer

Returns:

The parameter initializer for this model

getOutputType

public InputType getOutputType(int layerIndex,
                               InputType inputType)

Description copied from class: Layer

For a given type of input to this layer, what is the type of the output?

Overrides:

getOutputType in class ConvolutionLayer

Parameters:

layerIndex - Index of the layer

inputType - Type of input for the layer

Returns:

Type of output from the layer