org.deeplearning4j.nn.conf.layers

Class DropoutLayer.Builder

java.lang.Object

org.deeplearning4j.nn.conf.layers.Layer.Builder<T>

org.deeplearning4j.nn.conf.layers.BaseLayer.Builder<T>

org.deeplearning4j.nn.conf.layers.FeedForwardLayer.Builder<DropoutLayer.Builder>

org.deeplearning4j.nn.conf.layers.DropoutLayer.Builder

Enclosing class:

DropoutLayer

public static class DropoutLayer.Builder
extends FeedForwardLayer.Builder<DropoutLayer.Builder>

Field Summary

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

nIn, nOut

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

activationFn, biasInit, biasUpdater, gainInit, gradientNormalization, gradientNormalizationThreshold, iupdater, regularization, regularizationBias, weightInitFn, weightNoise

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

allParamConstraints, biasConstraints, iDropout, layerName, weightConstraints

Constructor Summary

Constructors

Constructor and Description
Builder(double dropout) Create a dropout layer with standard Dropout, with the specified probability of retaining the input activation.
Builder(IDropout dropout)

Method Summary

Modifier and Type	Method and Description
DropoutLayer	build()

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

nIn, nIn, nOut, nOut, units

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

activation, activation, biasInit, biasUpdater, dist, gainInit, gradientNormalization, gradientNormalizationThreshold, l1, l1Bias, l2, l2Bias, regularization, regularizationBias, updater, updater, weightDecay, weightDecay, weightDecayBias, weightDecayBias, weightInit, weightInit, weightInit, weightNoise

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

constrainAllParameters, constrainBias, constrainWeights, dropOut, dropOut, name

Methods inherited from class java.lang.Object

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

Constructor Detail

Builder

public Builder(double dropout)

Create a dropout layer with standard Dropout, with the specified probability of retaining the input activation. See Dropout for the full details

Parameters:

dropout - Activation retain probability.

Builder

public Builder(IDropout dropout)

Parameters:

dropout - Specified IDropout instance for the dropout layer

Method Detail

build

public DropoutLayer build()

Specified by:

build in class Layer.Builder<DropoutLayer.Builder>