org.deeplearning4j.nn.conf.layers

Class BaseLayer

java.lang.Object

org.deeplearning4j.nn.conf.layers.Layer

org.deeplearning4j.nn.conf.layers.BaseLayer

All Implemented Interfaces:

Serializable, Cloneable, TrainingConfig

Direct Known Subclasses:

FeedForwardLayer, PReLULayer

public abstract class BaseLayer
extends Layer
implements Serializable, Cloneable

A neural network layer.

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	BaseLayer.Builder<T extends BaseLayer.Builder<T>>

Field Summary

Fields

Modifier and Type	Field and Description
protected IActivation	activationFn
protected double	biasInit
protected IUpdater	biasUpdater
protected double	gainInit
protected GradientNormalization	gradientNormalization
protected double	gradientNormalizationThreshold
protected IUpdater	iUpdater
protected List<Regularization>	regularization
protected List<Regularization>	regularizationBias
protected IWeightInit	weightInitFn
protected IWeightNoise	weightNoise

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

constraints, iDropout, layerName

Constructor Summary

Constructors

Constructor and Description
BaseLayer(BaseLayer.Builder builder)

Method Summary

Modifier and Type	Method and Description
BaseLayer	clone()
GradientNormalization	getGradientNormalization()
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.
void	resetLayerDefaultConfig() Reset the learning related configs of the layer to default.

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

getMemoryReport, getOutputType, getPreProcessorForInputType, initializeConstraints, initializer, instantiate, isPretrainParam, setDataType, setNIn

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

getGradientNormalizationThreshold, getLayerName

Field Detail

activationFn

protected IActivation activationFn

weightInitFn

protected IWeightInit weightInitFn

biasInit

protected double biasInit

gainInit

protected double gainInit

regularization

protected List<Regularization> regularization

regularizationBias

protected List<Regularization> regularizationBias

iUpdater

protected IUpdater iUpdater

biasUpdater

protected IUpdater biasUpdater

weightNoise

protected IWeightNoise weightNoise

gradientNormalization

protected GradientNormalization gradientNormalization

gradientNormalizationThreshold

protected double gradientNormalizationThreshold

Constructor Detail

BaseLayer

public BaseLayer(BaseLayer.Builder builder)

Method Detail

resetLayerDefaultConfig

public void resetLayerDefaultConfig()

Reset the learning related configs of the layer to default. When instantiated with a global neural network configuration the parameters specified in the neural network configuration will be used. For internal use with the transfer learning API. Users should not have to call this method directly.

Overrides:

resetLayerDefaultConfig in class Layer

clone

public BaseLayer clone()

Overrides:

clone in class Layer

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()

Specified by:

getGradientNormalization in interface TrainingConfig

Returns:

The gradient normalization configuration

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