C# 클래스 Encog.Neural.NeuralData.Image.ImageNeuralDataSet

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.

상속: Encog.Neural.Data.Basic.BasicNeuralDataSet

파일 보기 프로젝트 열기: encog/encog-silverlight-core

공개 메소드들

메소드	설명
Add ( INeuralData data ) : void	Add the specified data, must be an ImageNeuralData class.
Add ( INeuralData inputData, INeuralData idealData ) : void	Add the specified input and ideal object to the collection.
Add ( INeuralDataPair inputData ) : void	Add input and expected output. This is used for supervised training.
Downsample ( int height, int width ) : void	Downsample all images and generate training data.
ImageNeuralDataSet ( IDownSample downsampler, bool findBounds, double hi, double lo ) : System	Construct this class with the specified downsampler.

메소드 상세

Add() 공개 메소드

Add the specified data, must be an ImageNeuralData class.

public Add ( INeuralData data ) : void
data	INeuralData	The data The object to add.
리턴	void

Add() 공개 메소드

Add the specified input and ideal object to the collection.

public Add ( INeuralData inputData, INeuralData idealData ) : void
inputData	INeuralData	The image to train with.
idealData	INeuralData	The expected otuput form this image.
리턴	void

Add() 공개 메소드

Add input and expected output. This is used for supervised training.

public Add ( INeuralDataPair inputData ) : void
inputData	INeuralDataPair	The input data to train on.
리턴	void

Downsample() 공개 메소드

Downsample all images and generate training data.

public Downsample ( int height, int width ) : void
height	int	The height to downsample to.
width	int	The width to downsample to.
리턴	void

ImageNeuralDataSet() 공개 메소드

Construct this class with the specified downsampler.

public ImageNeuralDataSet ( IDownSample downsampler, bool findBounds, double hi, double lo ) : System
downsampler	IDownSample	The downsampler to use.
findBounds	bool	Should the bounds be found and clipped.
hi	double	The high value to normalize to.
lo	double	The low value to normalize to.
리턴	System