org.deeplearning4j.nn.conf.layers.recurrent

Class Bidirectional

java.lang.Object

org.deeplearning4j.nn.conf.layers.Layer

org.deeplearning4j.nn.conf.layers.recurrent.Bidirectional

All Implemented Interfaces:

Serializable, Cloneable, TrainingConfig

public class Bidirectional
extends Layer

Bidirectional is a "wrapper" layer: it wraps any uni-directional RNN layer to make it bidirectional.
Note that multiple different modes are supported - these specify how the activations should be combined from the forward and backward RNN networks. See Bidirectional.Mode javadoc for more details.
Parameters are not shared here - there are 2 separate copies of the wrapped RNN layer, each with separate parameters.
Usage: .layer(new Bidirectional(new LSTM.Builder()....build())

Author:

Alex Black

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	Bidirectional.Builder
static class	Bidirectional.Mode This Mode enumeration defines how the activations for the forward and backward networks should be combined. ADD: out = forward + backward (elementwise addition) MUL: out = forward * backward (elementwise multiplication) AVERAGE: out = 0.5 * (forward + backward) CONCAT: Concatenate the activations. Where 'forward' is the activations for the forward RNN, and 'backward' is the activations for the backward RNN.

Field Summary

Fields inherited from class org.deeplearning4j.nn.conf.layers.Layer

constraints, iDropout, layerName

Constructor Summary

Constructors

Constructor and Description
Bidirectional(Bidirectional.Mode mode, Layer layer) Create a Bidirectional wrapper for the specified layer
Bidirectional(Layer layer) Create a Bidirectional wrapper, with the default Mode (CONCAT) for the specified layer

Method Summary

Modifier and Type	Method and Description
GradientNormalization	getGradientNormalization()
double	getGradientNormalizationThreshold()
LayerMemoryReport	getMemoryReport(InputType inputType) This is a report of the estimated memory consumption for the given layer
long	getNIn()
long	getNOut()
InputType	getOutputType(int layerIndex, InputType inputType) For a given type of input to this layer, what is the type of the output?
InputPreProcessor	getPreProcessorForInputType(InputType inputType) For the given type of input to this layer, what preprocessor (if any) is required? Returns null if no preprocessor is required, otherwise returns an appropriate InputPreProcessor for this layer, such as a CnnToFeedForwardPreProcessor
List<Regularization>	getRegularizationByParam(String paramName) Get the regularization types (l1/l2/weight decay) for the given parameter.
IUpdater	getUpdaterByParam(String paramName) Get the updater for the given parameter.
ParamInitializer	initializer()
Layer	instantiate(NeuralNetConfiguration conf, Collection<TrainingListener> trainingListeners, int layerIndex, INDArray layerParamsView, boolean initializeParams, org.nd4j.linalg.api.buffer.DataType networkDataType)
boolean	isPretrainParam(String paramName) Is the specified parameter a layerwise pretraining only parameter? For example, visible bias params in an autoencoder (or, decoder params in a variational autoencoder) aren't used during supervised backprop. Layers (like DenseLayer, etc) with no pretrainable parameters will return false for all (valid) inputs.
void	setLayerName(String layerName)
void	setNIn(InputType inputType, boolean override) Set the nIn value (number of inputs, or input channels for CNNs) based on the given input type

Methods inherited from class org.deeplearning4j.nn.conf.layers.Layer

clone, initializeConstraints, resetLayerDefaultConfig, setDataType

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.TrainingConfig

getLayerName

Constructor Detail

Bidirectional

public Bidirectional(@NonNull
                     Layer layer)

Create a Bidirectional wrapper, with the default Mode (CONCAT) for the specified layer

Parameters:

layer - layer to wrap

Bidirectional

public Bidirectional(@NonNull
                     Bidirectional.Mode mode,
                     @NonNull
                     Layer layer)

Create a Bidirectional wrapper for the specified layer

Parameters:

mode - Mode to use to combine activations. See Bidirectional.Mode for details

layer - layer to wrap

Method Detail

getNOut

public long getNOut()

getNIn

public long getNIn()

instantiate

public Layer instantiate(NeuralNetConfiguration conf,
                         Collection<TrainingListener> trainingListeners,
                         int layerIndex,
                         INDArray layerParamsView,
                         boolean initializeParams,
                         org.nd4j.linalg.api.buffer.DataType networkDataType)

Specified by:

instantiate in class Layer

initializer

public ParamInitializer initializer()

Specified by:

initializer in class Layer

Returns:

The parameter initializer for this model

getOutputType

public InputType getOutputType(int layerIndex,
                               InputType inputType)

Description copied from class: Layer

For a given type of input to this layer, what is the type of the output?

Specified by:

getOutputType in class Layer

Parameters:

layerIndex - Index of the layer

inputType - Type of input for the layer

Returns:

Type of output from the layer

setNIn

public void setNIn(InputType inputType,
                   boolean override)

Description copied from class: Layer

Set the nIn value (number of inputs, or input channels for CNNs) based on the given input type

Specified by:

setNIn in class Layer

Parameters:

inputType - Input type for this layer

override - If false: only set the nIn value if it's not already set. If true: set it regardless of whether it's already set or not.

getPreProcessorForInputType

public InputPreProcessor getPreProcessorForInputType(InputType inputType)

Description copied from class: Layer

For the given type of input to this layer, what preprocessor (if any) is required?
Returns null if no preprocessor is required, otherwise returns an appropriate InputPreProcessor for this layer, such as a CnnToFeedForwardPreProcessor

Specified by:

getPreProcessorForInputType in class Layer

Parameters:

inputType - InputType to this layer

Returns:

Null if no preprocessor is required, otherwise the type of preprocessor necessary for this layer/input combination

getRegularizationByParam

public List<Regularization> getRegularizationByParam(String paramName)

Description copied from class: Layer

Get the regularization types (l1/l2/weight decay) for the given parameter. Different parameters may have different regularization types.

Specified by:

getRegularizationByParam in interface TrainingConfig

Specified by:

getRegularizationByParam in class Layer

Parameters:

paramName - Parameter name ("W", "b" etc)

Returns:

Regularization types (if any) for the specified parameter

isPretrainParam

public boolean isPretrainParam(String paramName)

Description copied from class: Layer

Is the specified parameter a layerwise pretraining only parameter?
For example, visible bias params in an autoencoder (or, decoder params in a variational autoencoder) aren't used during supervised backprop.
Layers (like DenseLayer, etc) with no pretrainable parameters will return false for all (valid) inputs.

Specified by:

isPretrainParam in interface TrainingConfig

Specified by:

isPretrainParam in class Layer

Parameters:

paramName - Parameter name/key

Returns:

True if the parameter is for layerwise pretraining only, false otherwise

getUpdaterByParam

public IUpdater getUpdaterByParam(String paramName)

Get the updater for the given parameter. Typically the same updater will be used for all updaters, but this is not necessarily the case

Specified by:

getUpdaterByParam in interface TrainingConfig

Overrides:

getUpdaterByParam in class Layer

Parameters:

paramName - Parameter name

Returns:

IUpdater for the parameter

getGradientNormalization

public GradientNormalization getGradientNormalization()

Returns:

The gradient normalization configuration

getGradientNormalizationThreshold

public double getGradientNormalizationThreshold()

Returns:

The gradient normalization threshold

setLayerName

public void setLayerName(String layerName)

getMemoryReport

public LayerMemoryReport getMemoryReport(InputType inputType)

Description copied from class: Layer

This is a report of the estimated memory consumption for the given layer

Specified by:

getMemoryReport in class Layer

Parameters:

inputType - Input type to the layer. Memory consumption is often a function of the input type

Returns:

Memory report for the layer