org.deeplearning4j.nn.conf.layers.misc

Class FrozenLayerWithBackprop

java.lang.Object

org.deeplearning4j.nn.conf.layers.Layer

org.deeplearning4j.nn.conf.layers.wrapper.BaseWrapperLayer

org.deeplearning4j.nn.conf.layers.misc.FrozenLayerWithBackprop

All Implemented Interfaces:

Serializable, Cloneable, TrainingConfig

public class FrozenLayerWithBackprop
extends BaseWrapperLayer

Frozen layer freezes parameters of the layer it wraps, but allows the backpropagation to continue.

Author:

Ugljesa Jovanovic ([email protected]) on 06/05/2018.

See Also:

FrozenLayer, Serialized Form

Nested Class Summary

Nested classes/interfaces inherited from class org.deeplearning4j.nn.conf.layers.Layer

Layer.Builder<T extends Layer.Builder<T>>

Field Summary

Fields inherited from class org.deeplearning4j.nn.conf.layers.wrapper.BaseWrapperLayer

underlying

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

constraints, iDropout, layerName

Constructor Summary

Constructors

Constructor and Description
FrozenLayerWithBackprop(Layer layer)

Method Summary

Modifier and Type	Method and Description
Layer	clone()
NeuralNetConfiguration	getInnerConf(NeuralNetConfiguration conf)
double	getL1ByParam(String paramName) Get the L1 coefficient for the given parameter.
double	getL2ByParam(String paramName) Get the L2 coefficient 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)
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	setConstraints(List<LayerConstraint> constraints)
void	setLayerName(String layerName)

Methods inherited from class org.deeplearning4j.nn.conf.layers.wrapper.BaseWrapperLayer

getGradientNormalization, getGradientNormalizationThreshold, getMemoryReport, getOutputType, getPreProcessorForInputType, isPretrain, setNIn

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

initializeConstraints, resetLayerDefaultConfig, setPretrain

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

FrozenLayerWithBackprop

public FrozenLayerWithBackprop(Layer layer)

Method Detail

getInnerConf

public NeuralNetConfiguration getInnerConf(NeuralNetConfiguration conf)

clone

public Layer clone()

Overrides:

clone in class Layer

instantiate

public Layer instantiate(NeuralNetConfiguration conf,
                         Collection<TrainingListener> trainingListeners,
                         int layerIndex,
                         INDArray layerParamsView,
                         boolean initializeParams)

Specified by:

instantiate in class Layer

initializer

public ParamInitializer initializer()

Overrides:

initializer in class BaseWrapperLayer

Returns:

The parameter initializer for this model

getL1ByParam

public double getL1ByParam(String paramName)

Description copied from class: Layer

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

Overrides:

getL1ByParam in class BaseWrapperLayer

Parameters:

paramName - Parameter name

Returns:

L1 value for that parameter

getL2ByParam

public double getL2ByParam(String paramName)

Description copied from class: Layer

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

Overrides:

getL2ByParam in class BaseWrapperLayer

Parameters:

paramName - Parameter name

Returns:

L2 value for that 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

Overrides:

isPretrainParam in class BaseWrapperLayer

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 class: Layer

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

setLayerName

public void setLayerName(String layerName)

Overrides:

setLayerName in class BaseWrapperLayer

setConstraints

public void setConstraints(List<LayerConstraint> constraints)