org.deeplearning4j.nn.layers

Class FrozenLayer<LayerT extends Layer>

java.lang.Object

org.deeplearning4j.nn.layers.FrozenLayer<LayerT>

All Implemented Interfaces:

java.io.Serializable, java.lang.Cloneable, Layer, Model

public class FrozenLayer<LayerT extends Layer>
extends java.lang.Object
implements Layer

For purposes of transfer learning A frozen layers wraps another dl4j layer within it. The params of the layer within it are "frozen" or in other words held constant During the forward pass the frozen layer behaves as the layer within it would during test regardless of the training/test mode the network is in. Backprop is skipped since parameters are not be updated.

See Also:

Serialized Form

Nested Class Summary

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

Layer.TrainingMode, Layer.Type

Constructor Summary

Constructors

Constructor and Description
FrozenLayer(LayerT insideLayer)

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() Trigger an activation with the last specified input
org.nd4j.linalg.api.ndarray.INDArray	activate(boolean training) Trigger an activation with the last specified input
org.nd4j.linalg.api.ndarray.INDArray	activate(org.nd4j.linalg.api.ndarray.INDArray input) Initialize the layer with the given input and return the activation for this layer given this input
org.nd4j.linalg.api.ndarray.INDArray	activate(org.nd4j.linalg.api.ndarray.INDArray input, boolean training) Initialize the layer with the given input and return the activation for this layer given this input
org.nd4j.linalg.api.ndarray.INDArray	activate(org.nd4j.linalg.api.ndarray.INDArray input, Layer.TrainingMode training) Initialize the layer with the given input and return the activation for this layer given this input
org.nd4j.linalg.api.ndarray.INDArray	activate(Layer.TrainingMode 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
void	applyLearningRateScoreDecay() Update learningRate using for this model.
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
int	batchSize() The current inputs batch size
Gradient	calcGradient(Gradient layerError, org.nd4j.linalg.api.ndarray.INDArray indArray) Calculate the gradient
double	calcL1(boolean backpropOnlyParams) Calculate the l1 regularization term 0.0 if regularization is not used.
double	calcL2(boolean backpropOnlyParams) Calculate the l2 regularization term 0.0 if regularization is not used.
void	clear() Clear input
Layer	clone() Clone the layer
void	computeGradientAndScore() Update the score
NeuralNetConfiguration	conf() The configuration for the neural network
org.nd4j.linalg.api.ndarray.INDArray	derivativeActivation(org.nd4j.linalg.api.ndarray.INDArray input) Take the derivative of the given input based on the activation
Gradient	error(org.nd4j.linalg.api.ndarray.INDArray input) Calculate error with respect to the current layer.
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>	feedForwardMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray, MaskState currentMaskState, int minibatchSize) Feed forward the input mask array, setting in in the layer as appropriate.
void	fit() All models have a fit method
void	fit(org.nd4j.linalg.api.ndarray.INDArray data) Fit the model to the given data
int	getIndex() Get the layer index.
int	getInputMiniBatchSize() Get current/last input mini-batch size, as set by setInputMiniBatchSize(int)
LayerT	getInsideLayer()
java.util.Collection<IterationListener>	getListeners() Get the iteration listeners for this layer.
org.nd4j.linalg.api.ndarray.INDArray	getMaskArray()
ConvexOptimizer	getOptimizer() Returns this models optimizer
org.nd4j.linalg.api.ndarray.INDArray	getParam(java.lang.String param) Get the parameter
Gradient	gradient() Calculate a gradient
Pair<Gradient,java.lang.Double>	gradientAndScore() Get the gradient and score
void	init() Init the model
void	initParams() Initialize the parameters
org.nd4j.linalg.api.ndarray.INDArray	input() The input/feature matrix for the model
boolean	isPretrainLayer() Returns true if the layer can be trained in an unsupervised/pretrain manner (VAE, RBMs etc)
void	iterate(org.nd4j.linalg.api.ndarray.INDArray input) Run one iteration
void	logTestMode(boolean training)
void	logTestMode(Layer.TrainingMode training)
void	merge(Layer layer, int batchSize) Parameter averaging
int	numParams() the number of parameters for the model
int	numParams(boolean backwards) the number of parameters for the model
org.nd4j.linalg.api.ndarray.INDArray	params() Parameters of the model (if any)
java.util.Map<java.lang.String,org.nd4j.linalg.api.ndarray.INDArray>	paramTable() The param table
java.util.Map<java.lang.String,org.nd4j.linalg.api.ndarray.INDArray>	paramTable(boolean backpropParamsOnly) Table of parameters by key, for backprop For many models (dense layers, etc) - all parameters are backprop parameters
org.nd4j.linalg.api.ndarray.INDArray	preOutput(org.nd4j.linalg.api.ndarray.INDArray x) Raw activations
org.nd4j.linalg.api.ndarray.INDArray	preOutput(org.nd4j.linalg.api.ndarray.INDArray x, boolean training) Raw activations
org.nd4j.linalg.api.ndarray.INDArray	preOutput(org.nd4j.linalg.api.ndarray.INDArray x, Layer.TrainingMode training) Raw activations
double	score() The score for the model
void	setBackpropGradientsViewArray(org.nd4j.linalg.api.ndarray.INDArray gradients) Set the gradients array as a view of the full (backprop) network parameters NOTE: this is intended to be used internally in MultiLayerNetwork and ComputationGraph, not by users.
void	setConf(NeuralNetConfiguration conf) Setter for the configuration
void	setIndex(int index) Set the layer index.
void	setInput(org.nd4j.linalg.api.ndarray.INDArray input) Get the layer input.
void	setInputMiniBatchSize(int size) Set current/last input mini-batch size. Used for score and gradient calculations.
void	setListeners(java.util.Collection<IterationListener> listeners) Set the iteration listeners for this layer.
void	setListeners(IterationListener... listeners) Set the iteration listeners for this layer.
void	setMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray) Set the mask array.
void	setParam(java.lang.String key, org.nd4j.linalg.api.ndarray.INDArray val) Set the parameter with a new ndarray
void	setParams(org.nd4j.linalg.api.ndarray.INDArray params) Set the parameters for this model.
void	setParamsViewArray(org.nd4j.linalg.api.ndarray.INDArray params) Set the initial parameters array as a view of the full (backprop) network parameters NOTE: this is intended to be used internally in MultiLayerNetwork and ComputationGraph, not by users.
void	setParamTable(java.util.Map<java.lang.String,org.nd4j.linalg.api.ndarray.INDArray> paramTable) Setter for the param table
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(Gradient gradient) Update layer weights and biases with gradient change
void	update(org.nd4j.linalg.api.ndarray.INDArray gradient, java.lang.String paramType) Perform one update applying the gradient
void	validateInput() Validate the input

Methods inherited from class java.lang.Object

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

Constructor Detail

FrozenLayer

public FrozenLayer(LayerT insideLayer)

Method Detail

calcL2

public double calcL2(boolean backpropOnlyParams)

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

Parameters:

backpropOnlyParams - 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 backpropOnlyParams)

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

Parameters:

backpropOnlyParams - 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

Returns:

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

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

derivativeActivation

public org.nd4j.linalg.api.ndarray.INDArray derivativeActivation(org.nd4j.linalg.api.ndarray.INDArray input)

Description copied from interface: Layer

Take the derivative of the given input based on the activation

Specified by:

derivativeActivation in interface Layer

Parameters:

input - the input to take the derivative of

Returns:

the derivative of the action

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

Parameters:

layerError - the layer error

Returns:

the gradient

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

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

merge

public void merge(Layer layer,
                  int batchSize)

Description copied from interface: Layer

Parameter averaging

Specified by:

merge in interface Layer

Parameters:

layer - the layer to merge

batchSize - the batch size to merge on

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

Returns:

the activation mean for this layer

preOutput

public org.nd4j.linalg.api.ndarray.INDArray preOutput(org.nd4j.linalg.api.ndarray.INDArray x)

Description copied from interface: Layer

Raw activations

Specified by:

preOutput in interface Layer

Parameters:

x - the input to transform

Returns:

the raw activation for this layer

preOutput

public org.nd4j.linalg.api.ndarray.INDArray preOutput(org.nd4j.linalg.api.ndarray.INDArray x,
                                                      Layer.TrainingMode training)

Description copied from interface: Layer

Raw activations

Specified by:

preOutput in interface Layer

Parameters:

x - the input to transform

Returns:

the raw activation for this layer

activate

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

Description copied from interface: Layer

Trigger an activation with the last specified input

Specified by:

activate in interface Layer

Parameters:

training - training or test mode

Returns:

the activation of the last specified input

activate

public org.nd4j.linalg.api.ndarray.INDArray activate(org.nd4j.linalg.api.ndarray.INDArray input,
                                                     Layer.TrainingMode training)

Description copied from interface: Layer

Initialize the layer with the given input and return the activation for this layer given this input

Specified by:

activate in interface Layer

Parameters:

input - the input to use

training - train or test mode

Returns:

preOutput

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

Description copied from interface: Layer

Raw activations

Specified by:

preOutput in interface Layer

Parameters:

x - the input to transform

Returns:

the raw activation for this layer

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

Parameters:

training - training or test mode

Returns:

the activation of the last specified input

activate

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

Description copied from interface: Layer

Initialize the layer with the given input and return the activation for this layer given this input

Specified by:

activate in interface Layer

Parameters:

input - the input to use

training - train or test mode

Returns:

activate

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

Description copied from interface: Layer

Trigger an activation with the last specified input

Specified by:

activate in interface Layer

Returns:

the activation of the last specified input

activate

public org.nd4j.linalg.api.ndarray.INDArray activate(org.nd4j.linalg.api.ndarray.INDArray input)

Description copied from interface: Layer

Initialize the layer with the given input and return the activation for this layer given this input

Specified by:

activate in interface Layer

Parameters:

input - the input to use

Returns:

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

Returns:

the transposed layer

clone

public Layer clone()

Description copied from interface: Layer

Clone the layer

Specified by:

clone in interface Layer

Overrides:

clone in class java.lang.Object

Returns:

getListeners

public java.util.Collection<IterationListener> getListeners()

Description copied from interface: Layer

Get the iteration listeners for this layer.

Specified by:

getListeners in interface Layer

setListeners

public void setListeners(IterationListener... listeners)

Description copied from interface: Layer

Set the iteration listeners for this layer.

Specified by:

setListeners in interface Layer

Specified by:

setListeners in interface Model

fit

public void fit()

Description copied from interface: Model

All models have a fit method

Specified by:

fit in interface Model

update

public void update(Gradient gradient)

Description copied from interface: Model

Update layer weights and biases with gradient change

Specified by:

update in interface Model

update

public void update(org.nd4j.linalg.api.ndarray.INDArray gradient,
                   java.lang.String paramType)

Description copied from interface: Model

Perform one update applying the gradient

Specified by:

update in interface Model

Parameters:

gradient - the gradient to apply

score

public double score()

Description copied from interface: Model

The score for the model

Specified by:

score in interface Model

Returns:

the score for the model

computeGradientAndScore

public void computeGradientAndScore()

Description copied from interface: Model

Update the score

Specified by:

computeGradientAndScore in interface 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

Parameters:

accum - the amount to accum

params

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

Description copied from interface: Model

Parameters of the model (if any)

Specified by:

params in interface Model

Returns:

the parameters of the model

numParams

public int numParams()

Description copied from interface: Model

the number of parameters for the model

Specified by:

numParams in interface Model

Returns:

the number of parameters for the model

numParams

public int numParams(boolean backwards)

Description copied from interface: Model

the number of parameters for the model

Specified by:

numParams in interface Model

Returns:

the number of parameters for the model

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

Parameters:

params - the parameters for the model

setParamsViewArray

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

Description copied from interface: Model

Set the initial parameters array as a view of the full (backprop) network parameters NOTE: this is intended to be used internally in MultiLayerNetwork and ComputationGraph, not by users.

Specified by:

setParamsViewArray in interface Model

Parameters:

params - a 1 x nParams row vector that is a view of the larger (MLN/CG) parameters array

setBackpropGradientsViewArray

public void setBackpropGradientsViewArray(org.nd4j.linalg.api.ndarray.INDArray gradients)

Description copied from interface: Model

Set the gradients array as a view of the full (backprop) network parameters NOTE: this is intended to be used internally in MultiLayerNetwork and ComputationGraph, not by users.

Specified by:

setBackpropGradientsViewArray in interface Model

Parameters:

gradients - a 1 x nParams row vector that is a view of the larger (MLN/CG) gradients array

applyLearningRateScoreDecay

public void applyLearningRateScoreDecay()

Description copied from interface: Model

Update learningRate using for this model. Use the learningRateScoreBasedDecay to adapt the score if the Eps termination condition is met

Specified by:

applyLearningRateScoreDecay in interface Model

fit

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

Description copied from interface: Model

Fit the model to the given data

Specified by:

fit in interface Model

Parameters:

data - the data to fit the model to

iterate

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

Description copied from interface: Model

Run one iteration

Specified by:

iterate in interface Model

Parameters:

input - the input to iterate on

gradient

public Gradient gradient()

Description copied from interface: Model

Calculate a gradient

Specified by:

gradient in interface Model

Returns:

the gradient for this model

gradientAndScore

public Pair<Gradient,java.lang.Double> gradientAndScore()

Description copied from interface: Model

Get the gradient and score

Specified by:

gradientAndScore in interface Model

Returns:

the gradient and score

batchSize

public int batchSize()

Description copied from interface: Model

The current inputs batch size

Specified by:

batchSize in interface Model

Returns:

the current inputs batch size

conf

public NeuralNetConfiguration conf()

Description copied from interface: Model

The configuration for the neural network

Specified by:

conf in interface Model

Returns:

the configuration for the neural network

setConf

public void setConf(NeuralNetConfiguration conf)

Description copied from interface: Model

Setter for the configuration

Specified by:

setConf in interface Model

input

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

Description copied from interface: Model

The input/feature matrix for the model

Specified by:

input in interface Model

Returns:

the input/feature matrix for the model

validateInput

public void validateInput()

Description copied from interface: Model

Validate the input

Specified by:

validateInput in interface Model

getOptimizer

public ConvexOptimizer getOptimizer()

Description copied from interface: Model

Returns this models optimizer

Specified by:

getOptimizer in interface Model

Returns:

this models optimizer

getParam

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

Description copied from interface: Model

Get the parameter

Specified by:

getParam in interface Model

Parameters:

param - the key of the parameter

Returns:

the parameter vector/matrix with that particular key

initParams

public void initParams()

Description copied from interface: Model

Initialize the parameters

Specified by:

initParams in interface Model

paramTable

public java.util.Map<java.lang.String,org.nd4j.linalg.api.ndarray.INDArray> paramTable()

Description copied from interface: Model

The param table

Specified by:

paramTable in interface Model

Returns:

paramTable

public java.util.Map<java.lang.String,org.nd4j.linalg.api.ndarray.INDArray> paramTable(boolean backpropParamsOnly)

Description copied from interface: Model

Table of parameters by key, for backprop For many models (dense layers, etc) - all parameters are backprop parameters

Specified by:

paramTable in interface Model

Parameters:

backpropParamsOnly - If true, return backprop params only. If false: return all params (equivalent to paramsTable())

setParamTable

public void setParamTable(java.util.Map<java.lang.String,org.nd4j.linalg.api.ndarray.INDArray> paramTable)

Description copied from interface: Model

Setter for the param table

Specified by:

setParamTable in interface Model

setParam

public void setParam(java.lang.String key,
                     org.nd4j.linalg.api.ndarray.INDArray val)

Description copied from interface: Model

Set the parameter with a new ndarray

Specified by:

setParam in interface Model

Parameters:

key - the key to se t

val - the new ndarray

clear

public void clear()

Description copied from interface: Model

Clear input

Specified by:

clear in interface Model

init

public void init()

Init the model

Specified by:

init in interface Model

setListeners

public void setListeners(java.util.Collection<IterationListener> listeners)

Description copied from interface: Layer

Set the iteration listeners for this layer.

Specified by:

setListeners in interface Layer

Specified by:

setListeners in interface Model

setIndex

public void setIndex(int index)

Description copied from interface: Layer

Set the layer index.

Specified by:

setIndex in interface Layer

getIndex

public int getIndex()

Description copied from interface: Layer

Get the layer index.

Specified by:

getIndex in interface Layer

setInput

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

Description copied from interface: Layer

Get the layer input.

Specified by:

setInput in interface Layer

setInputMiniBatchSize

public void setInputMiniBatchSize(int size)

Description copied from interface: Layer

Set current/last input mini-batch size.
Used for score and gradient calculations. Mini batch size may be different from getInput().size(0) due to reshaping operations - for example, when using RNNs with DenseLayer and OutputLayer. Called automatically during forward pass.

Specified by:

setInputMiniBatchSize in interface Layer

getInputMiniBatchSize

public int getInputMiniBatchSize()

Description copied from interface: Layer

Get current/last input mini-batch size, as set by setInputMiniBatchSize(int)

Specified by:

getInputMiniBatchSize in interface Layer

See Also:

Layer.setInputMiniBatchSize(int)

setMaskArray

public void setMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray)

Description copied from interface: Layer

Set the mask array. Note: In general, Layer.feedForwardMaskArray(INDArray, MaskState, int) should be used in preference to this.

Specified by:

setMaskArray in interface Layer

Parameters:

maskArray - Mask array to set

getMaskArray

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

Specified by:

getMaskArray in interface 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)

Specified by:

isPretrainLayer in interface Layer

Returns:

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

feedForwardMaskArray

public Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState> feedForwardMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray,
                                                                                 MaskState currentMaskState,
                                                                                 int minibatchSize)

Description copied from interface: Layer

Feed forward the input mask array, setting in 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

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.

logTestMode

public void logTestMode(boolean training)

logTestMode

public void logTestMode(Layer.TrainingMode training)

getInsideLayer

public LayerT getInsideLayer()