org.encog.platformspecific.j2se.data.image
Class ImageMLDataSet

java.lang.Object
  extended by org.encog.ml.data.basic.BasicMLDataSet
      extended by org.encog.platformspecific.j2se.data.image.ImageMLDataSet
All Implemented Interfaces:
Serializable, Iterable<MLDataPair>, MLDataSet

public class ImageMLDataSet
extends BasicMLDataSet

Store a collection of images for training with a neural network. This class collects and then downsamples images for use with a neural network. This is a memory based class, so large datasets can run out of memory.

Author:
jheaton
See Also:
Serialized Form

Nested Class Summary
 
Nested classes/interfaces inherited from class org.encog.ml.data.basic.BasicMLDataSet
BasicMLDataSet.BasicMLIterator
 
Field Summary
static String MUST_USE_IMAGE
          Error message to inform the caller that only ImageNeuralData objects can be used with this collection.
 
Constructor Summary
ImageMLDataSet(Downsample theDownsampler, boolean theFindBounds, double theHi, double theLo)
          Construct this class with the specified downsampler.
 
Method Summary
 void downsample(int theHeight, int theWidth)
          Downsample all images and generate training data.
 int getHeight()
           
 int getWidth()
           
 
Methods inherited from class org.encog.ml.data.basic.BasicMLDataSet
add, add, add, clone, close, get, getData, getIdealSize, getInputSize, getRecord, getRecordCount, isSupervised, iterator, openAdditional, setData, size, toList
 
Methods inherited from class java.lang.Object
equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Field Detail

MUST_USE_IMAGE

public static final String MUST_USE_IMAGE
Error message to inform the caller that only ImageNeuralData objects can be used with this collection.

See Also:
Constant Field Values
Constructor Detail

ImageMLDataSet

public ImageMLDataSet(Downsample theDownsampler,
                      boolean theFindBounds,
                      double theHi,
                      double theLo)
Construct this class with the specified downsampler.

Parameters:
theDownsampler - The downsampler to use.
theFindBounds - Should the bounds be found and clipped.
theHi - The high value to normalize to.
theLo - The low value to normalize to.
Method Detail

downsample

public final void downsample(int theHeight,
                             int theWidth)
Downsample all images and generate training data.

Parameters:
theHeight - The height to downsample to.
theWidth - the width to downsample to.

getHeight

public final int getHeight()
Returns:
the height

getWidth

public final int getWidth()
Returns:
the width


Copyright © 2014. All Rights Reserved.