GClasses
GClasses::GContext Class Referenceabstract

Detailed Description

The base class for the buffers that a thread needs to use (train or predict with) a neural network component.

#include <GBlock.h>

Inheritance diagram for GClasses::GContext:
GClasses::GContextLayer GClasses::GContextNeuralNet GClasses::GContextRecurrent GClasses::GContextRecurrentInstance GClasses::GContextGRU GClasses::GContextLSTM

Public Member Functions

 GContext (GRand &rand)
 
virtual ~GContext ()
 
virtual void resetState ()=0
 Resets the state of all recurrent blocks. (This is called whenever a recurrent neural network begins with a new sequence, either for training or testing.) More...
 

Public Attributes

GRandm_rand
 

Constructor & Destructor Documentation

GClasses::GContext::GContext ( GRand rand)
inline
virtual GClasses::GContext::~GContext ( )
inlinevirtual

Member Function Documentation

virtual void GClasses::GContext::resetState ( )
pure virtual

Resets the state of all recurrent blocks. (This is called whenever a recurrent neural network begins with a new sequence, either for training or testing.)

Implemented in GClasses::GContextGRU, GClasses::GContextLSTM, GClasses::GContextRecurrent, GClasses::GContextNeuralNet, and GClasses::GContextLayer.

Member Data Documentation

GRand& GClasses::GContext::m_rand