org.deeplearning4j.datasets.iterator.impl

Class MovingWindowDataSetFetcher

java.lang.Object

org.nd4j.linalg.dataset.api.iterator.fetcher.BaseDataFetcher

org.deeplearning4j.datasets.iterator.impl.MovingWindowDataSetFetcher

All Implemented Interfaces:

Serializable, org.nd4j.linalg.dataset.api.iterator.fetcher.DataSetFetcher

public class MovingWindowDataSetFetcher
extends org.nd4j.linalg.dataset.api.iterator.fetcher.BaseDataFetcher

Moving window data fetcher. Handles rotation of matrices in all directions to generate more examples.

Author:

Adam Gibson

See Also:

Serialized Form

Field Summary

Fields inherited from class org.nd4j.linalg.dataset.api.iterator.fetcher.BaseDataFetcher

curr, inputColumns, log, numOutcomes, totalExamples

Constructor Summary

Constructors

Constructor and Description
MovingWindowDataSetFetcher(org.nd4j.linalg.dataset.DataSet data, int windowRows, int windowColumns)

Method Summary

Modifier and Type	Method and Description
void	fetch(int numExamples) Fetches the next dataset.

Methods inherited from class org.nd4j.linalg.dataset.api.iterator.fetcher.BaseDataFetcher

createInputMatrix, createOutputMatrix, createOutputVector, cursor, hasMore, initializeCurrFromList, inputColumns, next, reset, totalExamples, totalOutcomes

Methods inherited from class java.lang.Object

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

Constructor Detail

MovingWindowDataSetFetcher

public MovingWindowDataSetFetcher(org.nd4j.linalg.dataset.DataSet data,
                                  int windowRows,
                                  int windowColumns)

Method Detail

fetch

public void fetch(int numExamples)

Fetches the next dataset. You need to call this to get a new dataset, otherwise BaseDataFetcher.next() just returns the last data applyTransformToDestination fetch

Parameters:

numExamples - the number of examples to fetch