org.deeplearning4j.nn.conf.layers

Class BasePretrainNetwork

java.lang.Object

org.deeplearning4j.nn.conf.layers.Layer

org.deeplearning4j.nn.conf.layers.BaseLayer

org.deeplearning4j.nn.conf.layers.FeedForwardLayer

org.deeplearning4j.nn.conf.layers.BasePretrainNetwork

All Implemented Interfaces:

Serializable, Cloneable

Direct Known Subclasses:

AutoEncoder, VariationalAutoencoder

public abstract class BasePretrainNetwork
extends FeedForwardLayer

See Also:

Serialized Form

Nested Class Summary

Nested Classes

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

Field Summary

Fields

Modifier and Type	Field and Description
protected org.nd4j.linalg.lossfunctions.LossFunctions.LossFunction	lossFunction
protected double	visibleBiasInit

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

nIn, nOut

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

activationFn, biasInit, biasUpdater, dist, gradientNormalization, gradientNormalizationThreshold, iUpdater, l1, l1Bias, l2, l2Bias, weightInit, weightNoise

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

constraints, iDropout, layerName

Constructor Summary

Constructors

Constructor and Description
BasePretrainNetwork(BasePretrainNetwork.Builder builder)

Method Summary

Modifier and Type	Method and Description
double	getL1ByParam(String paramName) Get the L1 coefficient for the given parameter.
double	getL2ByParam(String paramName) Get the L2 coefficient for the given parameter.
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.

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

getOutputType, getPreProcessorForInputType, setNIn

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

clone, getUpdaterByParam, resetLayerDefaultConfig

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

getMemoryReport, initializeConstraints, initializer, instantiate

Methods inherited from class java.lang.Object

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

Field Detail

lossFunction

protected org.nd4j.linalg.lossfunctions.LossFunctions.LossFunction lossFunction

visibleBiasInit

protected double visibleBiasInit

Constructor Detail

BasePretrainNetwork

public BasePretrainNetwork(BasePretrainNetwork.Builder builder)

Method Detail

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

Overrides:

getL1ByParam in class FeedForwardLayer

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

Overrides:

getL2ByParam in class FeedForwardLayer

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.

Overrides:

isPretrainParam in class FeedForwardLayer

Parameters:

paramName - Parameter name/key

Returns:

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