weka.dl4j.layers

Class OutputLayer

java.lang.Object

weka.dl4j.layers.Layer<T>

weka.dl4j.layers.FeedForwardLayer<org.deeplearning4j.nn.conf.layers.OutputLayer>

weka.dl4j.layers.OutputLayer

All Implemented Interfaces:

java.io.Serializable, weka.core.OptionHandler, ApiWrapper<org.deeplearning4j.nn.conf.layers.OutputLayer>

public class OutputLayer
extends FeedForwardLayer<org.deeplearning4j.nn.conf.layers.OutputLayer>
implements weka.core.OptionHandler, java.io.Serializable

A version of DeepLearning4j's OutputLayer that implements WEKA option handling.

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
OutputLayer() Constructor for setting some defaults.

Method Summary

Modifier and Type	Method and Description
LossFunction<? extends org.nd4j.linalg.lossfunctions.ILossFunction>	getLossFn()
java.lang.String[]	getOptions() Gets the current settings of the Classifier.
java.lang.String	globalInfo() Global info.
void	initializeBackend() Initialize the DL4J backend.
java.util.Enumeration<weka.core.Option>	listOptions() Returns an enumeration describing the available options.
void	setLossFn(LossFunction<? extends org.nd4j.linalg.lossfunctions.ILossFunction> lossFn)
void	setOptions(java.lang.String[] options) Parses a given list of options.

Methods inherited from class weka.dl4j.layers.FeedForwardLayer

getActivationFunction, getNOut, setActivationFunction, setNOut

Methods inherited from class weka.dl4j.layers.Layer

create, getBackend, getLayerName, setBackend, setLayerName

Methods inherited from class java.lang.Object

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

Methods inherited from interface weka.core.OptionHandler

makeCopy

Constructor Detail

OutputLayer

public OutputLayer()

Constructor for setting some defaults.

Method Detail

initializeBackend

public void initializeBackend()

Description copied from interface: ApiWrapper

Initialize the DL4J backend.

Specified by:

initializeBackend in interface ApiWrapper<org.deeplearning4j.nn.conf.layers.OutputLayer>

globalInfo

public java.lang.String globalInfo()

Global info.

Returns:

string describing this class.

getLossFn

@OptionMetadata(displayName="loss function",
                description="The loss function to use (default = LossMCXENT).",
                commandLineParamName="lossFn",
                commandLineParamSynopsis="-lossFn <specification>",
                displayOrder=1)
public LossFunction<? extends org.nd4j.linalg.lossfunctions.ILossFunction> getLossFn()

setLossFn

public void setLossFn(LossFunction<? extends org.nd4j.linalg.lossfunctions.ILossFunction> lossFn)

listOptions

public java.util.Enumeration<weka.core.Option> listOptions()

Returns an enumeration describing the available options.

Specified by:

listOptions in interface weka.core.OptionHandler

Overrides:

listOptions in class FeedForwardLayer<org.deeplearning4j.nn.conf.layers.OutputLayer>

Returns:

an enumeration of all the available options.

getOptions

public java.lang.String[] getOptions()

Gets the current settings of the Classifier.

Specified by:

getOptions in interface weka.core.OptionHandler

Overrides:

getOptions in class FeedForwardLayer<org.deeplearning4j.nn.conf.layers.OutputLayer>

Returns:

an array of strings suitable for passing to setOptions

setOptions

public void setOptions(java.lang.String[] options)
                throws java.lang.Exception

Parses a given list of options.

Specified by:

setOptions in interface weka.core.OptionHandler

Overrides:

setOptions in class FeedForwardLayer<org.deeplearning4j.nn.conf.layers.OutputLayer>

Parameters:

options - the list of options as an array of strings

Throws:

java.lang.Exception - if an option is not supported