org.deeplearning4j.nn.layers.convolution.subsampling

Class SubsamplingLayer

java.lang.Object

org.deeplearning4j.nn.layers.AbstractLayer<SubsamplingLayer>

org.deeplearning4j.nn.layers.convolution.subsampling.SubsamplingLayer

All Implemented Interfaces:

Serializable, Cloneable, Layer, Model, Trainable

Direct Known Subclasses:

Subsampling1DLayer

public class SubsamplingLayer
extends AbstractLayer<SubsamplingLayer>

Subsampling layer. Used for downsampling a convolution

Author:

Adam Gibson

See Also:

Serialized Form

Nested Class Summary

Nested classes/interfaces inherited from interface org.deeplearning4j.nn.api.Layer

Layer.TrainingMode, Layer.Type

Field Summary

Fields

Modifier and Type	Field and Description
protected ConvolutionMode	convolutionMode
protected SubsamplingHelper	helper
protected int	helperCountFail

Fields inherited from class org.deeplearning4j.nn.layers.AbstractLayer

cacheMode, conf, dataType, dropoutApplied, epochCount, index, input, inputModificationAllowed, iterationCount, maskArray, maskState, preOutput, trainingListeners

Constructor Summary

Constructors

Constructor and Description
SubsamplingLayer(NeuralNetConfiguration conf, org.nd4j.linalg.api.buffer.DataType dataType)

Method Summary

Modifier and Type	Method and Description
INDArray	activate(boolean training, LayerWorkspaceMgr workspaceMgr) Perform forward pass and return the activations array with the last set input
Pair<Gradient,INDArray>	backpropGradient(INDArray epsilon, LayerWorkspaceMgr workspaceMgr) Calculate the gradient relative to the error in the next layer
double	calcRegularizationScore(boolean backpropOnlyParams) Calculate the regularization component of the score, for the parameters in this layer For example, the L1, L2 and/or weight decay components of the loss function
void	clearNoiseWeightParams()
Pair<INDArray,MaskState>	feedForwardMaskArray(INDArray maskArray, MaskState currentMaskState, int minibatchSize) Feed forward the input mask array, setting in the layer as appropriate.
void	fit() All models have a fit method
void	fit(INDArray input, LayerWorkspaceMgr workspaceMgr) Fit the model to the given data
LayerHelper	getHelper()
INDArray	getParam(String param) Get the parameter
Gradient	gradient() Get the gradient.
boolean	isPretrainLayer() Returns true if the layer can be trained in an unsupervised/pretrain manner (AE, VAE, etc)
long	numParams() The number of parameters for the model
INDArray	params() Returns the parameters of the neural network as a flattened row vector
double	score() The score for the model
void	setParams(INDArray params) Set the parameters for this model.
Layer.Type	type() Returns the layer type
void	update(INDArray gradient, String paramType) Perform one update applying the gradient

Methods inherited from class org.deeplearning4j.nn.layers.AbstractLayer

activate, addListeners, allowInputModification, applyConstraints, applyDropOutIfNecessary, applyMask, assertInputSet, backpropDropOutIfPresent, batchSize, clear, computeGradientAndScore, conf, getConfig, getEpochCount, getGradientsViewArray, getIndex, getInput, getInputMiniBatchSize, getListeners, getMaskArray, getOptimizer, gradientAndScore, init, input, layerConf, layerId, numParams, paramTable, paramTable, setBackpropGradientsViewArray, setCacheMode, setConf, setEpochCount, setIndex, setInput, setInputMiniBatchSize, setListeners, setListeners, setMaskArray, setParam, setParams, setParamsViewArray, setParamTable, update, updaterDivideByMinibatch

Methods inherited from class java.lang.Object

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

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

getIterationCount, setIterationCount

Field Detail

helper

protected SubsamplingHelper helper

helperCountFail

protected int helperCountFail

convolutionMode

protected ConvolutionMode convolutionMode

Constructor Detail

SubsamplingLayer

public SubsamplingLayer(NeuralNetConfiguration conf,
                        org.nd4j.linalg.api.buffer.DataType dataType)

Method Detail

calcRegularizationScore

public double calcRegularizationScore(boolean backpropOnlyParams)

Description copied from interface: Layer

Calculate the regularization component of the score, for the parameters in this layer
For example, the L1, L2 and/or weight decay components of the loss function

Specified by:

calcRegularizationScore in interface Layer

Overrides:

calcRegularizationScore in class AbstractLayer<SubsamplingLayer>

Parameters:

backpropOnlyParams - If true: calculate regularization score based on backprop params only. If false: calculate based on all params (including pretrain params, if any)

Returns:

the regularization score of

type

public Layer.Type type()

Description copied from interface: Layer

Returns the layer type

Specified by:

type in interface Layer

Overrides:

type in class AbstractLayer<SubsamplingLayer>

Returns:

backpropGradient

public Pair<Gradient,INDArray> backpropGradient(INDArray epsilon,
                                                LayerWorkspaceMgr workspaceMgr)

Description copied from interface: Layer

Calculate the gradient relative to the error in the next layer

Parameters:

epsilon - w^(L+1)*delta^(L+1). Or, equiv: dC/da, i.e., (dC/dz)*(dz/da) = dC/da, where C is cost function a=sigma(z) is activation.

workspaceMgr - Workspace manager

Returns:

Pair where Gradient is gradient for this layer, INDArray is epsilon (activation gradient) needed by next layer, but before element-wise multiply by sigmaPrime(z). So for standard feed-forward layer, if this layer is L, then return.getSecond() == dL/dIn = (w^(L)*(delta^(L))^T)^T. Note that the returned array should be placed in the ArrayType.ACTIVATION_GRAD workspace via the workspace manager

activate

public INDArray activate(boolean training,
                         LayerWorkspaceMgr workspaceMgr)

Description copied from interface: Layer

Perform forward pass and return the activations array with the last set input

Parameters:

training - training or test mode

workspaceMgr - Workspace manager

Returns:

the activation (layer output) of the last specified input. Note that the returned array should be placed in the ArrayType.ACTIVATIONS workspace via the workspace manager

isPretrainLayer

public boolean isPretrainLayer()

Description copied from interface: Layer

Returns true if the layer can be trained in an unsupervised/pretrain manner (AE, VAE, etc)

Returns:

true if the layer can be pretrained (using fit(INDArray), false otherwise

clearNoiseWeightParams

public void clearNoiseWeightParams()

getHelper

public LayerHelper getHelper()

Specified by:

getHelper in interface Layer

Overrides:

getHelper in class AbstractLayer<SubsamplingLayer>

Returns:

Get the layer helper, if any

gradient

public Gradient gradient()

Description copied from interface: Model

Get the gradient. Note that this method will not calculate the gradient, it will rather return the gradient that has been computed before. For calculating the gradient, see Model.computeGradientAndScore(LayerWorkspaceMgr) } .

Specified by:

gradient in interface Model

Overrides:

gradient in class AbstractLayer<SubsamplingLayer>

Returns:

the gradient for this model, as calculated before

fit

public void fit()

Description copied from interface: Model

All models have a fit method

Specified by:

fit in interface Model

Overrides:

fit in class AbstractLayer<SubsamplingLayer>

numParams

public long numParams()

Description copied from class: AbstractLayer

The number of parameters for the model

Specified by:

numParams in interface Model

Specified by:

numParams in interface Trainable

Overrides:

numParams in class AbstractLayer<SubsamplingLayer>

Returns:

the number of parameters for the model

fit

public void fit(INDArray input,
                LayerWorkspaceMgr workspaceMgr)

Description copied from interface: Model

Fit the model to the given data

Specified by:

fit in interface Model

Overrides:

fit in class AbstractLayer<SubsamplingLayer>

Parameters:

input - the data to fit the model to

score

public double score()

Description copied from interface: Model

The score for the model

Specified by:

score in interface Model

Overrides:

score in class AbstractLayer<SubsamplingLayer>

Returns:

the score for the model

update

public void update(INDArray gradient,
                   String paramType)

Description copied from interface: Model

Perform one update applying the gradient

Specified by:

update in interface Model

Overrides:

update in class AbstractLayer<SubsamplingLayer>

Parameters:

gradient - the gradient to apply

params

public INDArray params()

Description copied from class: AbstractLayer

Returns the parameters of the neural network as a flattened row vector

Specified by:

params in interface Model

Specified by:

params in interface Trainable

Overrides:

params in class AbstractLayer<SubsamplingLayer>

Returns:

the parameters of the neural network

getParam

public INDArray getParam(String param)

Description copied from interface: Model

Get the parameter

Specified by:

getParam in interface Model

Overrides:

getParam in class AbstractLayer<SubsamplingLayer>

Parameters:

param - the key of the parameter

Returns:

the parameter vector/matrix with that particular key

setParams

public void setParams(INDArray params)

Description copied from interface: Model

Set the parameters for this model. This expects a linear ndarray which then be unpacked internally relative to the expected ordering of the model

Specified by:

setParams in interface Model

Overrides:

setParams in class AbstractLayer<SubsamplingLayer>

Parameters:

params - the parameters for the model

feedForwardMaskArray

public Pair<INDArray,MaskState> feedForwardMaskArray(INDArray maskArray,
                                                     MaskState currentMaskState,
                                                     int minibatchSize)

Description copied from interface: Layer

Feed forward the input mask array, setting in the layer as appropriate. This allows different layers to handle masks differently - for example, bidirectional RNNs and normal RNNs operate differently with masks (the former sets activations to 0 outside of the data present region (and keeps the mask active for future layers like dense layers), whereas normal RNNs don't zero out the activations/errors )instead relying on backpropagated error arrays to handle the variable length case.
This is also used for example for networks that contain global pooling layers, arbitrary preprocessors, etc.

Specified by:

feedForwardMaskArray in interface Layer

Overrides:

feedForwardMaskArray in class AbstractLayer<SubsamplingLayer>

Parameters:

maskArray - Mask array to set

currentMaskState - Current state of the mask - see MaskState

minibatchSize - Current minibatch size. Needs to be known as it cannot always be inferred from the activations array due to reshaping (such as a DenseLayer within a recurrent neural network)

Returns:

New mask array after this layer, along with the new mask state.