weka.dl4j.iterators

Class ConvolutionalInstancesIterator

java.lang.Object

weka.dl4j.iterators.AbstractDataSetIterator

weka.dl4j.iterators.ConvolutionalInstancesIterator

All Implemented Interfaces:

java.io.Serializable, OptionHandler

public class ConvolutionalInstancesIterator
extends AbstractDataSetIterator

Converts the given Instances object into a DataSet and then constructs and returns a ShufflingDataSetIterator. This iterator is designed for training convolutional networks on data that is represented as standard WEKA instances. It enables specification of filter width and height, and number of channels.

Version:

$Revision: 11711 $

Author:

Christopher Beckham, Eibe Frank

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
ConvolutionalInstancesIterator()

Method Summary

Modifier and Type	Method and Description
int	getHeight()
org.nd4j.linalg.dataset.api.iterator.DataSetIterator	getIterator(Instances data, int seed, int batchSize) Returns the actual iterator.
int	getNumAttributes(Instances data) Returns the number of predictor attributes for this dataset.
int	getNumChannels()
java.lang.String[]	getOptions() Gets the current settings of the Classifier.
int	getTrainBatchSize() Getting the training batch size
int	getWidth()
java.util.Enumeration<Option>	listOptions() Returns an enumeration describing the available options.
void	setHeight(int height)
void	setNumChannels(int numChannels)
void	setOptions(java.lang.String[] options) Parses a given list of options.
void	setTrainBatchSize(int trainBatchSize) Setting the training batch size
void	setWidth(int width)

Methods inherited from class weka.dl4j.iterators.AbstractDataSetIterator

getIterator

Methods inherited from class java.lang.Object

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

Constructor Detail

ConvolutionalInstancesIterator

public ConvolutionalInstancesIterator()

Method Detail

setTrainBatchSize

@OptionMetadata(displayName="size of mini batch",
                description="The mini batch size to use in the iterator (default = 1).",
                commandLineParamName="bs",
                commandLineParamSynopsis="-bs <int>",
                displayOrder=0)
public void setTrainBatchSize(int trainBatchSize)

Description copied from class: AbstractDataSetIterator

Setting the training batch size

Overrides:

setTrainBatchSize in class AbstractDataSetIterator

Parameters:

trainBatchSize - the batch size

getTrainBatchSize

public int getTrainBatchSize()

Description copied from class: AbstractDataSetIterator

Getting the training batch size

Overrides:

getTrainBatchSize in class AbstractDataSetIterator

Returns:

the batch size

getWidth

@OptionMetadata(displayName="desired width",
                description="The desired width of the images (default = 28).",
                commandLineParamName="width",
                commandLineParamSynopsis="-width <int>",
                displayOrder=1)
public int getWidth()

setWidth

public void setWidth(int width)

getHeight

@OptionMetadata(displayName="desired height",
                description="The desired height of the images (default = 28).",
                commandLineParamName="height",
                commandLineParamSynopsis="-height <int>",
                displayOrder=2)
public int getHeight()

setHeight

public void setHeight(int height)

getNumChannels

@OptionMetadata(displayName="desired number of channels",
                description="The desired number of channels (default = 1).",
                commandLineParamName="numChannels",
                commandLineParamSynopsis="-numChannels <int>",
                displayOrder=3)
public int getNumChannels()

setNumChannels

public void setNumChannels(int numChannels)

getNumAttributes

public int getNumAttributes(Instances data)

Returns the number of predictor attributes for this dataset.

Specified by:

getNumAttributes in class AbstractDataSetIterator

Parameters:

data - the dataset to compute the number of attributes from

Returns:

the number of attributes in the Instances object minus one

getIterator

public org.nd4j.linalg.dataset.api.iterator.DataSetIterator getIterator(Instances data,
                                                                        int seed,
                                                                        int batchSize)

Returns the actual iterator.

Specified by:

getIterator in class AbstractDataSetIterator

Parameters:

data - the dataset to use

seed - the seed for the random number generator

batchSize - the batch size to use

Returns:

the DataSetIterator

listOptions

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

Returns an enumeration describing the available options.

Specified by:

listOptions in interface OptionHandler

Overrides:

listOptions in class AbstractDataSetIterator

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 OptionHandler

Overrides:

getOptions in class AbstractDataSetIterator

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 OptionHandler

Overrides:

setOptions in class AbstractDataSetIterator

Parameters:

options - the list of options as an array of strings

Throws:

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