A class for holding data for inference. More...

Public Member Functions
TrainingSetPlain (int batchSize)

void loadFromH5 (const std::string &sampleFile, const std::string &sampleWeights, const std::string &labelFile, const std::string &labelWeights)

void loadFromH5 (const std::string &sampleFile, const std::string &sampleWeights)

const DoubleMatrixArray & getSamples (int batch) const

const DoubleMatrixArray & getLabels (int batch) const

DoubleMatrixArray getAllSamples () const

DoubleMatrixArray getAllLabels () const

int getNumBatches () const

int getBatchSize () const

const DoubleMatrix & getSample (int batch, int i) const

const DoubleMatrix & getLabel (int batch, int i) const

int getNumSamples () const

int getNumLabels () const

int getNumClasses () const

Detailed Description

A class for holding data for inference.

It may hold just the inputs, or both inputs and expected outputs (usually refered to as labels, or ground truth).

If it contains both it can be used for training, or for estimating the accuracy of a given model. Otherwise it can only be used for inference.

It loads the data from an h5 file, and divides it to batches according to a specified batch size.

The documentation for this class was generated from the following files:

Public Member Functions