org.deeplearning4j.nn.layers.convolution

Class SpaceToBatch

java.lang.Object

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

org.deeplearning4j.nn.layers.convolution.SpaceToBatch

All Implemented Interfaces:

Serializable, Cloneable, Layer, Model

public class SpaceToBatch
extends AbstractLayer<SpaceToBatchLayer>

Space to batch utility layer for convolutional input types.

Does a 2-dimensional space to batch operation, i.e. ransforms data from a tensor from 2 spatial dimensions into batch dimension according to the "blocks" specified (a vector of length 2). Afterwards the spatial dimensions are optionally padded, as specified in "padding", a tensor of dim (2, 2), denoting the padding range.

Example: input: [[[[1], [2]], [[3], [4]]]] input shape: [1, 2, 2, 1] blocks: [2, 2] padding: [[0, 0], [0, 0]]

output: [[[[1]]], [[[2]]], [[[3]]], [[[4]]]] output shape: [4, 1, 1, 1]

Author:

Max Pumperla

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

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

Constructor Summary

Constructors

Constructor and Description
SpaceToBatch(NeuralNetConfiguration conf)
SpaceToBatch(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, LayerWorkspaceMgr workspaceMgr) Perform forward pass and return the activations array with the last set input
org.nd4j.linalg.primitives.Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>	backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon, LayerWorkspaceMgr workspaceMgr) Calculate the gradient relative to the error in the next layer
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	clearNoiseWeightParams()
Layer	clone() Clone the layer
org.nd4j.linalg.api.ndarray.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)
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
protected org.nd4j.linalg.api.ndarray.INDArray	preOutput(boolean training, boolean forBackprop, LayerWorkspaceMgr workspaceMgr)
double	score() The score for the model
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.AbstractLayer

activate, addListeners, applyConstraints, applyDropOutIfNecessary, applyMask, assertInputSet, batchSize, clear, computeGradientAndScore, conf, feedForwardMaskArray, fit, fit, getGradientsViewArray, getIndex, getInput, getInputMiniBatchSize, getListeners, getMaskArray, getOptimizer, gradientAndScore, init, initParams, input, layerConf, layerId, numParams, paramTable, paramTable, setBackpropGradientsViewArray, setCacheMode, setConf, setIndex, setInput, setInputMiniBatchSize, setListeners, setListeners, setMaskArray, setParam, setParams, setParamsViewArray, setParamTable, update, validateInput

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.Layer

getEpochCount, getIterationCount, setEpochCount, setIterationCount

Constructor Detail

SpaceToBatch

public SpaceToBatch(NeuralNetConfiguration conf)

SpaceToBatch

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

Method Detail

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<SpaceToBatchLayer>

Returns:

backpropGradient

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

preOutput

protected org.nd4j.linalg.api.ndarray.INDArray preOutput(boolean training,
                                                         boolean forBackprop,
                                                         LayerWorkspaceMgr workspaceMgr)

activate

public org.nd4j.linalg.api.ndarray.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

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 AbstractLayer<SpaceToBatchLayer>

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 AbstractLayer<SpaceToBatchLayer>

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.

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 AbstractLayer<SpaceToBatchLayer>

Returns:

the transposed layer

clone

public Layer clone()

Description copied from interface: Layer

Clone the layer

Specified by:

clone in interface Layer

Specified by:

clone in class AbstractLayer<SpaceToBatchLayer>

Returns:

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()

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() .

Specified by:

gradient in interface Model

Overrides:

gradient in class AbstractLayer<SpaceToBatchLayer>

Returns:

the gradient for this model, as calculated before

numParams

public int numParams()

Description copied from class: AbstractLayer

The number of parameters for the model

Specified by:

numParams in interface Model

Overrides:

numParams in class AbstractLayer<SpaceToBatchLayer>

Returns:

the number of parameters for the model

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<SpaceToBatchLayer>

Returns:

the score for the model

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 AbstractLayer<SpaceToBatchLayer>

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 AbstractLayer<SpaceToBatchLayer>

Parameters:

gradient - the gradient to apply

params

public org.nd4j.linalg.api.ndarray.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

Overrides:

params in class AbstractLayer<SpaceToBatchLayer>

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 AbstractLayer<SpaceToBatchLayer>

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 AbstractLayer<SpaceToBatchLayer>

Parameters:

params - the parameters for the model