org.deeplearning4j.nn.layers.convolution

Class ConvolutionLayer

java.lang.Object

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

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

org.deeplearning4j.nn.layers.convolution.ConvolutionLayer

All Implemented Interfaces:

Serializable, Cloneable, Layer, Model

Direct Known Subclasses:

Convolution1DLayer

public class ConvolutionLayer
extends BaseLayer<ConvolutionLayer>

Convolution layer

Author:

Adam Gibson (original impl), Alex Black (current version)

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 ConvolutionHelper	helper
protected org.nd4j.linalg.api.ndarray.INDArray	i2d
protected static org.slf4j.Logger	log

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

gradient, gradientsFlattened, gradientViews, optimizer, params, paramsFlattened, score, solver

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

cacheMode, conf, dropoutApplied, dropoutMask, index, input, iterationListeners, maskArray, maskState, preOutput

Constructor Summary

Constructors

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

Method Summary

Modifier and Type	Method and Description
org.nd4j.linalg.api.ndarray.INDArray	activate(boolean training) Trigger an activation with the last specified input
org.nd4j.linalg.primitives.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(boolean backpropParamsOnly) Calculate the l1 regularization term 0.0 if regularization is not used.
double	calcL2(boolean backpropParamsOnly) Calculate the l2 regularization term 0.0 if regularization is not used.
void	fit(org.nd4j.linalg.api.ndarray.INDArray input) Fit the model to the given data
boolean	isPretrainLayer() Returns true if the layer can be trained in an unsupervised/pretrain manner (VAE, RBMs etc)
void	merge(Layer layer, int batchSize) Averages the given logistic regression from a mini batch into this layer
org.nd4j.linalg.api.ndarray.INDArray	params() Returns the parameters of the neural network as a flattened row vector
org.nd4j.linalg.api.ndarray.INDArray	preOutput(boolean training)
protected org.nd4j.linalg.primitives.Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>	preOutput(boolean training, boolean forBackprop) PreOutput method that also returns the im2col2d array (if being called for backprop), as this can be re-used instead of being calculated again.
protected org.nd4j.linalg.primitives.Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>	preOutput4d(boolean training, boolean forBackprop) preOutput4d: Used so that ConvolutionLayer subclasses (such as Convolution1DLayer) can maintain their standard non-4d preOutput method, while overriding this to return 4d activations (for use in backprop) without modifying the public API
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

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

accumulateScore, activate, activate, activationMean, applyLearningRateScoreDecay, clone, computeGradientAndScore, error, fit, getGradientsViewArray, getOptimizer, getParam, gradient, initParams, iterate, layerConf, numParams, paramTable, paramTable, preOutput, score, setBackpropGradientsViewArray, setParam, setParams, setParamsViewArray, setParamTable, setScoreWithZ, toString, update, update

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

activate, activate, activate, addListeners, applyDropOutIfNecessary, applyMask, batchSize, clear, conf, derivativeActivation, feedForwardMaskArray, getIndex, getInput, getInputMiniBatchSize, getListeners, getMaskArray, gradientAndScore, init, input, layerId, numParams, preOutput, preOutput, setCacheMode, setConf, setIndex, setInput, setInputMiniBatchSize, setListeners, setListeners, setMaskArray, 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

i2d

protected org.nd4j.linalg.api.ndarray.INDArray i2d

helper

protected ConvolutionHelper helper

convolutionMode

protected ConvolutionMode convolutionMode

Constructor Detail

ConvolutionLayer

public ConvolutionLayer(NeuralNetConfiguration conf)

ConvolutionLayer

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

Method Detail

calcL2

public double calcL2(boolean backpropParamsOnly)

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<ConvolutionLayer>

Parameters:

backpropParamsOnly - If true: calculate L2 based on backprop params only. If false: calculate based on all params (including pretrain params, if any)

Returns:

the l2 regularization term for this layer.

calcL1

public double calcL1(boolean backpropParamsOnly)

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<ConvolutionLayer>

Parameters:

backpropParamsOnly - If true: calculate L1 based on backprop params only. If false: calculate based on all params (including pretrain params, if any)

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 AbstractLayer<ConvolutionLayer>

Returns:

backpropGradient

public org.nd4j.linalg.primitives.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<ConvolutionLayer>

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

preOutput4d

protected org.nd4j.linalg.primitives.Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray> preOutput4d(boolean training,
                                                                                                                                 boolean forBackprop)

preOutput4d: Used so that ConvolutionLayer subclasses (such as Convolution1DLayer) can maintain their standard non-4d preOutput method, while overriding this to return 4d activations (for use in backprop) without modifying the public API

preOutput

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

Overrides:

preOutput in class BaseLayer<ConvolutionLayer>

preOutput

protected org.nd4j.linalg.primitives.Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray> preOutput(boolean training,
                                                                                                                               boolean forBackprop)

PreOutput method that also returns the im2col2d array (if being called for backprop), as this can be re-used instead of being calculated again.

Parameters:

training - Train or test time (impacts dropout)

forBackprop - If true: return the im2col2d array for re-use during backprop. False: return null for second pair entry. Note that it may still be null in the case of CuDNN and the like.

Returns:

Pair of arrays: preOutput (activations) and optionally the im2col2d array

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<ConvolutionLayer>

Parameters:

training - training or test mode

Returns:

the activation of the last specified input

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<ConvolutionLayer>

Returns:

the transposed layer

isPretrainLayer

public boolean isPretrainLayer()

Description copied from interface: Layer

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

Returns:

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

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<ConvolutionLayer>

Parameters:

layerError - the layer error

Returns:

the gradient

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<ConvolutionLayer>

Parameters:

input - the data to fit the model to

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<ConvolutionLayer>

Parameters:

layer - the logistic regression layer to average into this layer

batchSize - the batch size

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<ConvolutionLayer>

Returns:

the parameters of the neural network

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<ConvolutionLayer>

Parameters:

params - the parameters for the model