org.deeplearning4j.nn.conf.misc

Class DummyConfig

java.lang.Object

org.deeplearning4j.nn.conf.misc.DummyConfig

All Implemented Interfaces:

TrainingConfig

public class DummyConfig
extends Object
implements TrainingConfig

A 'dummy' training configuration for use in frozen layers

Author:

Alex Black

Constructor Summary

Constructors

Constructor and Description
DummyConfig()

Method Summary

Modifier and Type	Method and Description
GradientNormalization	getGradientNormalization()
double	getGradientNormalizationThreshold()
double	getL1ByParam(String paramName) Get the L1 coefficient for the given parameter.
double	getL2ByParam(String paramName) Get the L2 coefficient for the given parameter.
String	getLayerName()
IUpdater	getUpdaterByParam(String paramName) Get the updater for the given parameter.
boolean	isPretrain()
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	setPretrain(boolean pretrain)

Methods inherited from class java.lang.Object

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

Constructor Detail

DummyConfig

public DummyConfig()

Method Detail

getLayerName

public String getLayerName()

Specified by:

getLayerName in interface TrainingConfig

Returns:

Name of the layer

isPretrain

public boolean isPretrain()

Specified by:

isPretrain in interface TrainingConfig

Returns:

True if the layer is set up for layerwise pretraining

getL1ByParam

public double getL1ByParam(String paramName)

Description copied from interface: TrainingConfig

Get the L1 coefficient for the given parameter. Different parameters may have different L1 values, even for a single .l1(x) configuration. For example, biases generally aren't L1 regularized, even if weights are

Specified by:

getL1ByParam in interface TrainingConfig

Parameters:

paramName - Parameter name

Returns:

L1 value for that parameter

getL2ByParam

public double getL2ByParam(String paramName)

Description copied from interface: TrainingConfig

Get the L2 coefficient for the given parameter. Different parameters may have different L2 values, even for a single .l2(x) configuration. For example, biases generally aren't L1 regularized, even if weights are

Specified by:

getL2ByParam in interface TrainingConfig

Parameters:

paramName - Parameter name

Returns:

L2 value for that parameter

isPretrainParam

public boolean isPretrainParam(String paramName)

Description copied from interface: TrainingConfig

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

Parameters:

paramName - Parameter name/key

Returns:

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

getUpdaterByParam

public IUpdater getUpdaterByParam(String paramName)

Description copied from interface: TrainingConfig

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

Parameters:

paramName - Parameter name

Returns:

IUpdater for the parameter

getGradientNormalization

public GradientNormalization getGradientNormalization()

Specified by:

getGradientNormalization in interface TrainingConfig

Returns:

The gradient normalization configuration

getGradientNormalizationThreshold

public double getGradientNormalizationThreshold()

Specified by:

getGradientNormalizationThreshold in interface TrainingConfig

Returns:

The gradient normalization threshold

setPretrain

public void setPretrain(boolean pretrain)

Specified by:

setPretrain in interface TrainingConfig

Parameters:

pretrain - Whether the layer is currently undergoing layerwise unsupervised training, or multi-layer backprop