Simd Library Documentation.

Home | Release Notes | Download | Documentation | Issues | GitHub | SourceForge
Network Class Reference

Network class. More...

Public Member Functions

 Network ()
 Creates a new object of Network class. More...
 
void Clear ()
 Clears all layers of the neural network.
 
bool Empty () const
 Returns true if the neural network is empty.
 
bool Add (Layer *layer)
 Adds new Layer to the neural network. More...
 
const IndexInputIndex () const
 Gets dimensions of input data. More...
 
const IndexOutputIndex () const
 Gets dimensions of output data. More...
 
template<class Logger >
bool Train (const Vectors &src, const Labels &dst, const TrainOptions &options, Logger logger)
 Trains the neural network. More...
 
template<class Logger >
bool Train (const Vectors &src, const Vectors &dst, const TrainOptions &options, Logger logger)
 Trains the neural network. More...
 
SIMD_INLINE const VectorPredict (const Vector &x, Layer::Method method=Layer::Fast)
 Classifies given sample. More...
 
bool Load (const void *data, size_t size, bool train=false)
 Loads the weights of neural network from an external buffer. More...
 
bool Load (std::istream &is, bool train=false)
 Loads the weights of neural network from file stream. More...
 
bool Load (const std::string &path, bool train=false)
 Loads the weights of neural network from file. More...
 
bool Save (void *data, size_t *size, bool train=false) const
 Saves the weights of neural network into external buffer. More...
 
bool Save (std::ostream &os, bool train=false) const
 Saves the weights of neural network to file stream. More...
 
bool Save (const std::string &path, bool train=false) const
 Saves the weights of neural network to file. More...
 
void Convert (const Labels &src, Vectors &dst) const
 Converts format of classification results. More...
 

Detailed Description

Network class.

Class Network provides functionality for construction, loading, saving, prediction and training of convolutional neural network.

Constructor & Destructor Documentation

◆ Network()

Network ( )

Creates a new object of Network class.

Creates empty network without any layers.

Member Function Documentation

◆ Add()

bool Add ( Layer layer)

Adds new Layer to the neural network.

Parameters
[in]layer- a pointer to the new layer. You can add ConvolutionalLayer, MaxPoolingLayer and FullyConnectedLayer.
Returns
a result of addition. If added layer is not compatible with previous layer the result might be negative.

◆ InputIndex()

const Index& InputIndex ( ) const

Gets dimensions of input data.

Returns
a dimensions of input data.

◆ OutputIndex()

const Index& OutputIndex ( ) const

Gets dimensions of output data.

Returns
a dimensions of output data.

◆ Train() [1/2]

bool Train ( const Vectors src,
const Labels dst,
const TrainOptions options,
Logger  logger 
)

Trains the neural network.

Parameters
[in]src- a set of input training samples.
[in]dst- a set of classification results.
[in]options- an options of training process.
[in]logger- a functor to log training process.
Returns
a result of the training.

◆ Train() [2/2]

bool Train ( const Vectors src,
const Vectors dst,
const TrainOptions options,
Logger  logger 
)

Trains the neural network.

Parameters
[in]src- a set of input training samples.
[in]dst- a set of classification results.
[in]options- an options of training process.
[in]logger- a functor to log training process.
Returns
a result of the training.

◆ Predict()

SIMD_INLINE const Vector& Predict ( const Vector x,
Layer::Method  method = Layer::Fast 
)

Classifies given sample.

Parameters
[in]x- an input sample.
[in]method- a method of prediction. By default it is equal to Layer::Fast.
Returns
a result of classification (vector with predicted probabilities).

◆ Load() [1/3]

bool Load ( const void *  data,
size_t  size,
bool  train = false 
)

Loads the weights of neural network from an external buffer.

Note
The network has to be created previously with using of methods Clear/Add.
Parameters
[in]data- a pointer to the external buffer.
[in]size- a size of the external buffer.
[in]train- a boolean flag (True - if we need to load temporary training data, False - otherwise). By default it is equal to False.
Returns
a result of loading.

◆ Load() [2/3]

bool Load ( std::istream &  is,
bool  train = false 
)

Loads the weights of neural network from file stream.

Note
The network has to be created previously with using of methods Clear/Add.
Parameters
[in]is- a input stream.
[in]train- a boolean flag (True - if we need to load temporary training data, False - otherwise). By default it is equal to False.
Returns
a result of loading.

◆ Load() [3/3]

bool Load ( const std::string &  path,
bool  train = false 
)

Loads the weights of neural network from file.

Note
The network has to be created previously with using of methods Clear/Add.
Parameters
[in]path- a path to input file.
[in]train- a boolean flag (True - if we need to load temporary training data, False - otherwise). By default it is equal to False.
Returns
a result of loading.

◆ Save() [1/3]

bool Save ( void *  data,
size_t *  size,
bool  train = false 
) const

Saves the weights of neural network into external buffer.

Parameters
[out]data- a pointer to the external buffer.
[in,out]size- a pointer to the size of external buffer. Returns requred buffer size.
[in]train- a boolean flag (True - if we need to save temporary training data, False - otherwise). By default it is equal to False.
Returns
a result of saving.

◆ Save() [2/3]

bool Save ( std::ostream &  os,
bool  train = false 
) const

Saves the weights of neural network to file stream.

Parameters
[out]os- a output stream.
[in]train- a boolean flag (True - if we need to save temporary training data, False - otherwise). By default it is equal to False.
Returns
a result of saving.

◆ Save() [3/3]

bool Save ( const std::string &  path,
bool  train = false 
) const

Saves the weights of neural network to file.

Parameters
[in]path- a path to output file.
[in]train- a boolean flag (True - if we need to save temporary training data, False - otherwise). By default it is equal to False.
Returns
a result of saving.

◆ Convert()

void Convert ( const Labels src,
Vectors dst 
) const

Converts format of classification results.

Parameters
[in]src- a set of class indexes.
[out]dst- a set of vectors with predicted probabilities.