org.deeplearning4j.nn.conf.layers

Class PReLULayer.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<PReLULayer.Builder>

org.deeplearning4j.nn.conf.layers.PReLULayer.Builder

Enclosing class:

PReLULayer

public static class PReLULayer.Builder
extends FeedForwardLayer.Builder<PReLULayer.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()

Method Summary

Modifier and Type	Method and Description
PReLULayer	build()
PReLULayer.Builder	inputShape(long... shape) Explicitly set input shape of incoming activations so that parameters can be initialized properly.
PReLULayer.Builder	sharedAxes(long... axes) Set the broadcasting axes of PReLU's alpha parameter.

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()

Method Detail

inputShape

public PReLULayer.Builder inputShape(long... shape)

Explicitly set input shape of incoming activations so that parameters can be initialized properly. This explicitly excludes the mini-batch dimension.

Parameters:

shape - shape of input data

sharedAxes

public PReLULayer.Builder sharedAxes(long... axes)

Set the broadcasting axes of PReLU's alpha parameter. For instance, given input data of shape [mb, channels, height, width], setting axes to [2,3] will set alpha to shape [channels, 1, 1] and broadcast alpha across height and width dimensions of each channel.

Parameters:

axes - shared/broadcasting axes

Returns:

Builder

build

public PReLULayer build()

Specified by:

build in class Layer.Builder<PReLULayer.Builder>