Package org.deeplearning4j.datasets.iterator.impl

Class EmnistDataSetIterator

java.lang.Object

org.nd4j.linalg.dataset.api.iterator.BaseDatasetIterator

org.deeplearning4j.datasets.iterator.impl.EmnistDataSetIterator

All Implemented Interfaces:

Serializable, Iterator<org.nd4j.linalg.dataset.DataSet>, org.nd4j.linalg.dataset.api.iterator.DataSetIterator

public class EmnistDataSetIterator
extends org.nd4j.linalg.dataset.api.iterator.BaseDatasetIterator

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field	Description
protected int	batch
protected EMnistSet	dataSet
protected int	numExamples
protected org.nd4j.linalg.dataset.api.DataSetPreProcessor	preProcessor

Fields inherited from class org.nd4j.linalg.dataset.api.iterator.BaseDatasetIterator

fetcher, topLevelDir

Constructor Summary

Constructors

Constructor	Description
EmnistDataSetIterator(EMnistSet dataSet, int batch, boolean train)	Create an EMNIST iterator with randomly shuffled data based on a random RNG seed
EmnistDataSetIterator(EMnistSet dataSet, int batch, boolean binarize, boolean train, boolean shuffle, long rngSeed)	Get the specified number of MNIST examples (test or train set), with optional shuffling and binarization.
EmnistDataSetIterator(EMnistSet dataSet, int batch, boolean binarize, boolean train, boolean shuffle, long rngSeed, File topLevelDir)	Get the specified number of MNIST examples (test or train set), with optional shuffling and binarization.
EmnistDataSetIterator(EMnistSet dataSet, int batchSize, boolean train, long seed)	Create an EMNIST iterator with randomly shuffled data based on a specified RNG seed

Method Summary

Modifier and Type	Method	Description
List<String>	getLabels()	Get the labels as a List
static List<String>	getLabels(EMnistSet dataSet)	Get the label assignments for the given set as a List
static char[]	getLabelsArray(EMnistSet dataSet)	Get the label assignments for the given set as a character array.
char[]	getLabelsArrays()	Get the labels as a character array
static boolean	isBalanced(EMnistSet dataSet)	Are the labels balanced in the training set (that is: are the number of examples for each label equal?)
static int	numExamplesTest(EMnistSet dataSet)	Get the number of test examples for the specified subset
static int	numExamplesTrain(EMnistSet dataSet)	Get the number of training examples for the specified subset
static int	numLabels(EMnistSet dataSet)	Get the number of labels for the specified subset

Methods inherited from class org.nd4j.linalg.dataset.api.iterator.BaseDatasetIterator

asyncSupported, batch, getPreProcessor, hasNext, inputColumns, next, next, remove, reset, resetSupported, setPreProcessor, setTopLevelDir, topLevelDir, totalOutcomes

Methods inherited from class java.lang.Object

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

Methods inherited from interface java.util.Iterator

forEachRemaining

Field Detail

dataSet

protected EMnistSet dataSet

batch

protected int batch

numExamples

protected int numExamples

preProcessor

protected org.nd4j.linalg.dataset.api.DataSetPreProcessor preProcessor

Constructor Detail

EmnistDataSetIterator

public EmnistDataSetIterator(EMnistSet dataSet,
                             int batch,
                             boolean train)
                      throws IOException

Create an EMNIST iterator with randomly shuffled data based on a random RNG seed

Parameters:

dataSet - Dataset (subset) to return

batch - Batch size

train - If true: use training set. If false: use test set

Throws:

IOException - If an error occurs when loading/downloading the dataset

EmnistDataSetIterator

public EmnistDataSetIterator(EMnistSet dataSet,
                             int batchSize,
                             boolean train,
                             long seed)
                      throws IOException

Create an EMNIST iterator with randomly shuffled data based on a specified RNG seed

Parameters:

dataSet - Dataset (subset) to return

batchSize - Batch size

train - If true: use training set. If false: use test set

seed - Random number generator seed

Throws:

IOException

EmnistDataSetIterator

public EmnistDataSetIterator(EMnistSet dataSet,
                             int batch,
                             boolean binarize,
                             boolean train,
                             boolean shuffle,
                             long rngSeed,
                             File topLevelDir)
                      throws IOException

Get the specified number of MNIST examples (test or train set), with optional shuffling and binarization.

Parameters:

batch - Size of each minibatch

binarize - whether to binarize the data or not (if false: normalize in range 0 to 1)

train - Train vs. test set

shuffle - whether to shuffle the examples

rngSeed - random number generator seed to use when shuffling examples

Throws:

IOException

EmnistDataSetIterator

public EmnistDataSetIterator(EMnistSet dataSet,
                             int batch,
                             boolean binarize,
                             boolean train,
                             boolean shuffle,
                             long rngSeed)
                      throws IOException

Get the specified number of MNIST examples (test or train set), with optional shuffling and binarization.

Parameters:

batch - Size of each minibatch

binarize - whether to binarize the data or not (if false: normalize in range 0 to 1)

train - Train vs. test set

shuffle - whether to shuffle the examples

rngSeed - random number generator seed to use when shuffling examples

Throws:

IOException

Method Detail

numExamplesTrain

public static int numExamplesTrain(EMnistSet dataSet)

Get the number of training examples for the specified subset

Parameters:

dataSet - Subset to get

Returns:

Number of examples for the specified subset

numExamplesTest

public static int numExamplesTest(EMnistSet dataSet)

Get the number of test examples for the specified subset

Parameters:

dataSet - Subset to get

Returns:

Number of examples for the specified subset

numLabels

public static int numLabels(EMnistSet dataSet)

Get the number of labels for the specified subset

Parameters:

dataSet - Subset to get

Returns:

Number of labels for the specified subset

getLabelsArrays

public char[] getLabelsArrays()

Get the labels as a character array

Returns:

Labels

getLabels

public List<String> getLabels()

Get the labels as a List

Specified by:

getLabels in interface org.nd4j.linalg.dataset.api.iterator.DataSetIterator

Overrides:

getLabels in class org.nd4j.linalg.dataset.api.iterator.BaseDatasetIterator

Returns:

Labels

getLabelsArray

public static char[] getLabelsArray(EMnistSet dataSet)

Get the label assignments for the given set as a character array.

Parameters:

dataSet - DataSet to get the label assignment for

Returns:

Label assignment and given dataset

getLabels

public static List<String> getLabels(EMnistSet dataSet)

Get the label assignments for the given set as a List

Parameters:

dataSet - DataSet to get the label assignment for

Returns:

Label assignment and given dataset

isBalanced

public static boolean isBalanced(EMnistSet dataSet)

Are the labels balanced in the training set (that is: are the number of examples for each label equal?)

Parameters:

dataSet - Set to get balanced value for

Returns:

True if balanced dataset, false otherwise