Package org.deeplearning4j.datasets.iterator.impl

Class TinyImageNetDataSetIterator

java.lang.Object

org.deeplearning4j.datasets.datavec.RecordReaderDataSetIterator

org.deeplearning4j.datasets.iterator.impl.TinyImageNetDataSetIterator

All Implemented Interfaces:

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

public class TinyImageNetDataSetIterator
extends RecordReaderDataSetIterator

See Also:

Serialized Form

Nested Class Summary

Nested classes/interfaces inherited from class org.deeplearning4j.datasets.datavec.RecordReaderDataSetIterator

RecordReaderDataSetIterator.Builder

Field Summary

Fields

Modifier and Type	Field	Description
protected org.nd4j.linalg.dataset.api.DataSetPreProcessor	preProcessor

Fields inherited from class org.deeplearning4j.datasets.datavec.RecordReaderDataSetIterator

batchNum, batchSize, converter, labelIndex, labelIndexTo, last, maxNumBatches, numPossibleLabels, recordReader, regression, sequenceIter, useCurrent

Constructor Summary

Constructors

Constructor	Description
TinyImageNetDataSetIterator(int batchSize)	Create an iterator for the training set, with random iteration order (RNG seed fixed to 123)
TinyImageNetDataSetIterator(int batchSize, int[] imgDim, DataSetType set)	Get the Tiny ImageNet iterator with specified train/test set, with random iteration order (RNG seed fixed to 123)
TinyImageNetDataSetIterator(int batchSize, int[] imgDim, DataSetType set, ImageTransform imageTransform, long rngSeed)	Get the Tiny ImageNet iterator with specified train/test set and (optional) custom transform.
TinyImageNetDataSetIterator(int batchSize, DataSetType set)	* Create an iterator for the training or test set, with random iteration order (RNG seed fixed to 123)

Method Summary

Modifier and Type	Method	Description
static List<String>	getLabels(boolean categories)	Get the labels - either in "categories" (imagenet synsets format, "n01910747" or similar) or human-readable format, such as "jellyfish"

Methods inherited from class org.deeplearning4j.datasets.datavec.RecordReaderDataSetIterator

asyncSupported, batch, getLabels, getPreProcessor, getRecordReader, hasNext, inputColumns, isCollectMetaData, loadFromMetaData, loadFromMetaData, next, next, remove, reset, resetSupported, setCollectMetaData, setPreProcessor, 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

preProcessor

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

Constructor Detail

TinyImageNetDataSetIterator

public TinyImageNetDataSetIterator(int batchSize)

Create an iterator for the training set, with random iteration order (RNG seed fixed to 123)

Parameters:

batchSize - Minibatch size for the iterator

TinyImageNetDataSetIterator

public TinyImageNetDataSetIterator(int batchSize,
                                   DataSetType set)

* Create an iterator for the training or test set, with random iteration order (RNG seed fixed to 123)

Parameters:

batchSize - Minibatch size for the iterator

set - The dataset (train or test)

TinyImageNetDataSetIterator

public TinyImageNetDataSetIterator(int batchSize,
                                   int[] imgDim,
                                   DataSetType set)

Get the Tiny ImageNet iterator with specified train/test set, with random iteration order (RNG seed fixed to 123)

Parameters:

batchSize - Size of each patch

imgDim - Dimensions of desired output - for example, {64, 64}

set - Train, test, or validation

TinyImageNetDataSetIterator

public TinyImageNetDataSetIterator(int batchSize,
                                   int[] imgDim,
                                   DataSetType set,
                                   ImageTransform imageTransform,
                                   long rngSeed)

Get the Tiny ImageNet iterator with specified train/test set and (optional) custom transform.

Parameters:

batchSize - Size of each patch

imgDim - Dimensions of desired output - for example, {64, 64}

set - Train, test, or validation

imageTransform - Additional image transform for output

rngSeed - random number generator seed to use when shuffling examples

Method Detail

getLabels

public static List<String> getLabels(boolean categories)

Get the labels - either in "categories" (imagenet synsets format, "n01910747" or similar) or human-readable format, such as "jellyfish"

Parameters:

categories - If true: return category/synset format; false: return "human readable" label format

Returns:

Labels