DataGeneratorBase
-
class DataGeneratorBase
Subclassed by DataGeneratorClassification, DataGeneratorRegression
Public Functions
-
DataGeneratorBase(Config *settings)
Class constructor. Generates training data for neural network approaches using spherical harmonics and an entropy functional and the quadrature specified by the options file.
- Parameters:
settings – config class with global information
-
virtual void ComputeTrainingData() = 0
computes the training data set. Realizable set is sampled uniformly. Prototype: 1D, u in [0,100]
Public Static Functions
-
static DataGeneratorBase *Create(Config *settings)
Create a datagenerator (1D or 3D)
- Parameters:
settings – Pointer to the config file
- Returns:
Pointer to the createt basis class
Protected Functions
-
virtual void SampleMultiplierAlpha()
Sample Lagrange multipliers alpha.
-
void ComputeRealizableSolution()
make u the realizable moment to alpha, since Newton has roundoff errors.
-
virtual void PrintTrainingData() = 0
: Print computed training data to csv file and screen
-
void PrintLoadScreen()
Print screen IO.
-
virtual void ComputeMoments() = 0
Pre-Compute Moments at all quadrature points.
-
bool ComputeEVRejection(unsigned idx_set)
Evalute rejection criterion based on the smallest Eigenvalue of the Hessian corresponding to alpha[idx_set].
-
bool ComputeReducedEVRejection(VectorVector &redMomentBasis, Vector &redAlpha)
Evalute rejection criterion based on the smallest Eigenvalue of the reduced Hessian corresponding to alpha[idx_set].
Protected Attributes
-
VectorVector _uSol
vector with moments. Size: (setSize,basisSize)
-
VectorVector _alpha
vector with Lagrange multipliers. Size: (setSize,basisSize)
-
unsigned long _setSize
Size of the whole training Set.
-
unsigned short _maxPolyDegree
Max Order of Spherical Harmonics.
-
unsigned _nTotalEntries
Total number of equations in the system.
-
QuadratureBase *_quadrature
quadrature to create members below
-
unsigned _nq
number of quadrature points
-
VectorVector _quadPoints
quadrature points, dim(_quadPoints) = (_nq,spatialDim)
-
Vector _weights
quadrature weights, dim(_weights) = (_nq)
-
VectorVector _quadPointsSphere
(my,phi), dim(_quadPoints) = (_nq,2)
-
SphericalBase *_basisGenerator
Class to compute and store current spherical harmonics basis.
-
VectorVector _momentBasis
Moment Vector pre-computed at each quadrature point: dim= _nq x _nTotalEntries.
-
NewtonOptimizer *_optimizer
Class to solve minimal entropy problem.
-
EntropyBase *_entropy
Class to handle entropy functional evaluations.
-
bool _reducedSampling
Flag to show if the reduced optimizer is used.
-
DataGeneratorBase(Config *settings)