org.deeplearning4j.nn.layers.convolution.subsampling

Class SubsamplingLayer

java.lang.Object

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

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

All Implemented Interfaces:

Serializable, Cloneable, Layer, Model

public class SubsamplingLayer
extends BaseLayer<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 static org.slf4j.Logger	log

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

conf, dropoutApplied, dropoutMask, gradient, gradientsFlattened, gradientViews, index, input, iterationListeners, maskArray, optimizer, params, paramsFlattened, score, solver

Constructor Summary

Constructors

Constructor and Description
SubsamplingLayer(NeuralNetConfiguration conf)
SubsamplingLayer(NeuralNetConfiguration conf, org.nd4j.linalg.api.ndarray.INDArray input)

Method Summary

Modifier and Type	Method and Description
void	accumulateScore(double accum) Sets a rolling tally for the score.
org.nd4j.linalg.api.ndarray.INDArray	activate(boolean training) Trigger an activation with the last specified input
org.nd4j.linalg.api.ndarray.INDArray	activationMean() Calculate the mean representation for the activation for this layer
Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon) Calculate the gradient relative to the error in the next layer
Gradient	calcGradient(Gradient layerError, org.nd4j.linalg.api.ndarray.INDArray indArray) Calculate the gradient
double	calcL1() Calculate the l1 regularization term 0.0 if regularization is not used.
double	calcL2() Calculate the l2 regularization term 0.0 if regularization is not used.
void	computeGradientAndScore() Update the score
Gradient	error(org.nd4j.linalg.api.ndarray.INDArray input) Calculate error with respect to the current layer.
void	fit() All models have a fit method
void	fit(org.nd4j.linalg.api.ndarray.INDArray input) Fit the model to the given data
org.nd4j.linalg.api.ndarray.INDArray	getParam(String param) Get the parameter
void	iterate(org.nd4j.linalg.api.ndarray.INDArray input) iterate one iteration of the network
void	merge(Layer layer, int batchSize) Averages the given logistic regression from a mini batch into this layer
int	numParams() The number of parameters for the model
org.nd4j.linalg.api.ndarray.INDArray	params() Returns the parameters of the neural network as a flattened row vector
double	score() Objective function: the specified objective
void	setParams(org.nd4j.linalg.api.ndarray.INDArray params) Set the parameters for this model.
Layer	transpose() Return a transposed copy of the weights/bias (this means reverse the number of inputs and outputs on the weights)
Layer.Type	type() Returns the layer type
void	update(org.nd4j.linalg.api.ndarray.INDArray gradient, String paramType) Perform one update applying the gradient

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

activate, activate, activate, activate, activate, applyDropOutIfNecessary, applyLearningRateScoreDecay, batchSize, clear, clone, conf, createGradient, derivativeActivation, getIndex, getInput, getInputMiniBatchSize, getListeners, getOptimizer, gradient, gradientAndScore, initParams, input, layerConf, numParams, paramTable, preOutput, preOutput, preOutput, preOutput, setBackpropGradientsViewArray, setConf, setIndex, setInput, setInputMiniBatchSize, setListeners, setListeners, setMaskArray, setParam, setParams, setParamsViewArray, setParamTable, setScoreWithZ, toString, update, validateInput

Methods inherited from class java.lang.Object

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

Field Detail

log

protected static final org.slf4j.Logger log

Constructor Detail

SubsamplingLayer

public SubsamplingLayer(NeuralNetConfiguration conf)

SubsamplingLayer

public SubsamplingLayer(NeuralNetConfiguration conf,
                        org.nd4j.linalg.api.ndarray.INDArray input)

Method Detail

calcL2

public double calcL2()

Description copied from interface: Layer

Calculate the l2 regularization term
0.0 if regularization is not used. Or 0.5 * l2Coeff * l2Magnitude otherwise.
Note that this does not divide by mini-batch size

Specified by:

calcL2 in interface Layer

Overrides:

calcL2 in class BaseLayer<SubsamplingLayer>

Returns:

the l2 regularization term for this layer.

calcL1

public double calcL1()

Description copied from interface: Layer

Calculate the l1 regularization term
0.0 if regularization is not used. Or l1Coeff * l1Magnitude otherwise.
Note that this does not divide by mini-batch size

Specified by:

calcL1 in interface Layer

Overrides:

calcL1 in class BaseLayer<SubsamplingLayer>

Returns:

the l1 regularization term for this layer.

type

public Layer.Type type()

Description copied from interface: Layer

Returns the layer type

Specified by:

type in interface Layer

Overrides:

type in class BaseLayer<SubsamplingLayer>

Returns:

backpropGradient

public Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray> backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon)

Description copied from interface: Layer

Calculate the gradient relative to the error in the next layer

Specified by:

backpropGradient in interface Layer

Overrides:

backpropGradient in class BaseLayer<SubsamplingLayer>

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.

Returns:

Pair where Gradient is gradient for this layer, INDArray is epsilon 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() == (w^(L)*(delta^(L))^T)^T

activate

public org.nd4j.linalg.api.ndarray.INDArray activate(boolean training)

Description copied from interface: Layer

Trigger an activation with the last specified input

Specified by:

activate in interface Layer

Overrides:

activate in class BaseLayer<SubsamplingLayer>

Parameters:

training - training or test mode

Returns:

the activation of the last specified input

error

public Gradient error(org.nd4j.linalg.api.ndarray.INDArray input)

Description copied from interface: Layer

Calculate error with respect to the current layer. This gradient will contain the error signal

Specified by:

error in interface Layer

Overrides:

error in class BaseLayer<SubsamplingLayer>

Parameters:

input - the gradient for the forward layer If this is the final layer, it will start with the error from the output. This is on the user to initialize.

Returns:

the gradient wrt the parameters on the current layer

calcGradient

public Gradient calcGradient(Gradient layerError,
                             org.nd4j.linalg.api.ndarray.INDArray indArray)

Description copied from interface: Layer

Calculate the gradient

Specified by:

calcGradient in interface Layer

Overrides:

calcGradient in class BaseLayer<SubsamplingLayer>

Parameters:

layerError - the layer error

Returns:

the gradient

merge

public void merge(Layer layer,
                  int batchSize)

Description copied from class: BaseLayer

Averages the given logistic regression from a mini batch into this layer

Specified by:

merge in interface Layer

Overrides:

merge in class BaseLayer<SubsamplingLayer>

Parameters:

layer - the logistic regression layer to average into this layer

batchSize - the batch size

activationMean

public org.nd4j.linalg.api.ndarray.INDArray activationMean()

Description copied from interface: Layer

Calculate the mean representation for the activation for this layer

Specified by:

activationMean in interface Layer

Overrides:

activationMean in class BaseLayer<SubsamplingLayer>

Returns:

the activation mean for this layer

transpose

public Layer transpose()

Description copied from interface: Layer

Return a transposed copy of the weights/bias (this means reverse the number of inputs and outputs on the weights)

Specified by:

transpose in interface Layer

Overrides:

transpose in class BaseLayer<SubsamplingLayer>

Returns:

the transposed layer

iterate

public void iterate(org.nd4j.linalg.api.ndarray.INDArray input)

Description copied from class: BaseLayer

iterate one iteration of the network

Specified by:

iterate in interface Model

Overrides:

iterate in class BaseLayer<SubsamplingLayer>

Parameters:

input - the input to iterate on

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 BaseLayer<SubsamplingLayer>

numParams

public int numParams()

Description copied from class: BaseLayer

The number of parameters for the model

Specified by:

numParams in interface Model

Overrides:

numParams in class BaseLayer<SubsamplingLayer>

Returns:

the number of parameters for the model

fit

public void fit(org.nd4j.linalg.api.ndarray.INDArray input)

Description copied from interface: Model

Fit the model to the given data

Specified by:

fit in interface Model

Overrides:

fit in class BaseLayer<SubsamplingLayer>

Parameters:

input - the data to fit the model to

computeGradientAndScore

public void computeGradientAndScore()

Description copied from interface: Model

Update the score

Specified by:

computeGradientAndScore in interface Model

Overrides:

computeGradientAndScore in class BaseLayer<SubsamplingLayer>

score

public double score()

Description copied from class: BaseLayer

Objective function: the specified objective

Specified by:

score in interface Model

Overrides:

score in class BaseLayer<SubsamplingLayer>

Returns:

the score for the objective

accumulateScore

public void accumulateScore(double accum)

Description copied from interface: Model

Sets a rolling tally for the score. This is useful for mini batch learning when you are accumulating error across a dataset.

Specified by:

accumulateScore in interface Model

Overrides:

accumulateScore in class BaseLayer<SubsamplingLayer>

Parameters:

accum - the amount to accum

update

public void update(org.nd4j.linalg.api.ndarray.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 BaseLayer<SubsamplingLayer>

Parameters:

gradient - the gradient to apply

params

public org.nd4j.linalg.api.ndarray.INDArray params()

Description copied from class: BaseLayer

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

Specified by:

params in interface Model

Overrides:

params in class BaseLayer<SubsamplingLayer>

Returns:

the parameters of the neural network

getParam

public org.nd4j.linalg.api.ndarray.INDArray getParam(String param)

Description copied from interface: Model

Get the parameter

Specified by:

getParam in interface Model

Overrides:

getParam in class BaseLayer<SubsamplingLayer>

Parameters:

param - the key of the parameter

Returns:

the parameter vector/matrix with that particular key

setParams

public void setParams(org.nd4j.linalg.api.ndarray.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 BaseLayer<SubsamplingLayer>

Parameters:

params - the parameters for the model