weka.dl4j.iterators

Class ImageDataSetIterator

java.lang.Object

weka.dl4j.iterators.AbstractDataSetIterator

weka.dl4j.iterators.ImageDataSetIterator

All Implemented Interfaces:

java.io.Serializable, OptionHandler

public class ImageDataSetIterator
extends AbstractDataSetIterator

An iterator that loads images.

Version:

$Revision: 11711 $

Author:

Christopher Beckham, Eibe Frank

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
ImageDataSetIterator()

Method Summary

Modifier and Type	Method and Description
int	getHeight()
java.io.File	getImagesLocation()
org.nd4j.linalg.dataset.api.iterator.DataSetIterator	getIterator(Instances data, int seed, int batchSize) This method returns the iterator.
int	getNumAttributes(Instances data) This just returns the number of channels.
int	getNumChannels()
int	getTrainBatchSize() Getting the training batch size
int	getWidth()
void	setHeight(int height)
void	setImagesLocation(java.io.File imagesLocation)
void	setNumChannels(int numChannels)
void	setTrainBatchSize(int trainBatchSize) Setting the training batch size
void	setWidth(int width)
void	validate(Instances data) Validates the input dataset

Methods inherited from class weka.dl4j.iterators.AbstractDataSetIterator

getIterator, getOptions, listOptions, setOptions

Methods inherited from class java.lang.Object

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

Constructor Detail

ImageDataSetIterator

public ImageDataSetIterator()

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

getImagesLocation

@OptionMetadata(displayName="directory of images",
                description="The directory containing the images (default = user home).",
                commandLineParamName="imagesLocation",
                commandLineParamSynopsis="-imagesLocation <string>",
                displayOrder=1)
public java.io.File getImagesLocation()

setImagesLocation

public void setImagesLocation(java.io.File imagesLocation)

getWidth

@OptionMetadata(displayName="desired width",
                description="The desired width of the images (default = 28).",
                commandLineParamName="width",
                commandLineParamSynopsis="-width <int>",
                displayOrder=2)
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=3)
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=4)
public int getNumChannels()

setNumChannels

public void setNumChannels(int numChannels)

validate

public void validate(Instances data)
              throws java.lang.Exception

Validates the input dataset

Parameters:

data - the input dataset

Throws:

java.lang.Exception - if validation is unsuccessful

getNumAttributes

public int getNumAttributes(Instances data)

This just returns the number of channels.

Specified by:

getNumAttributes in class AbstractDataSetIterator

Parameters:

data - the dataset to compute the number of attributes from

Returns:

the number of channels

getIterator

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

This method returns the iterator. Scales all intensity values: it divides them by 255. Shuffles the data before the iterator is created.

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 iterator

Throws:

java.lang.Exception