example_fcnn_training_load.cpp

Programa para el testeo de las funciones Fully Connected Layer.Para compilar o código example_fcnn_training_load.cpp:

g++ -static -o example_fcnn_training_load example_fcnn_training_load.cpp -lpdsramm -lpdsnnmm 

Para executar o programa:

./example_fcnn_training_load

Retornando por consola:

Test[0] Accuracy %: 98.15       MeanAbsError %: 4.14644
Test[1] Accuracy %: 98.15       MeanAbsError %: 4.14643
Test[2] Accuracy %: 98.15       MeanAbsError %: 4.14642
Test[3] Accuracy %: 98.15       MeanAbsError %: 4.14641
Test[4] Accuracy %: 98.15       MeanAbsError %: 4.1464
Test[5] Accuracy %: 98.15       MeanAbsError %: 4.14639
Test[6] Accuracy %: 98.15       MeanAbsError %: 4.14639
Test[7] Accuracy %: 98.15       MeanAbsError %: 4.14638
Test[8] Accuracy %: 98.15       MeanAbsError %: 4.14637
Test[9] Accuracy %: 98.15       MeanAbsError %: 4.14636

Datos de treinamento.

Datos despues del treinamento. Código example_fcnn_training_load.cpp:

 
#include <Pds/Ra>
#include <Pds/Nn>
 
int main(void)
{
    Pds::Matrix X(Pds::Ra::TextFormat,"../test/data_x_yinyang.txt");
    Pds::Matrix Y(Pds::Ra::TextFormat,"../test/data_y_yinyang.txt");
    Pds::Matrix Ys(Y.Size());
    
    Pds::FCNn NN0("../test/NeuralNettwork0.txt",Pds::Sigmoid,Pds::DSigmoid);
    
    for(unsigned int k=0;k<10;k++)
    {
        NN0.Training(X,Y,0.1,0.01);
        
        NN0.Evaluate(X,Ys);
        
        std::cout<<"Test["<<k<<"]\t";
        std::cout<<"Accuracy %: "    <<100.0*Pds::Accuracy(Ys.Geq(0.5),Y)<<"\t";
        std::cout<<"MeanAbsError %: "<<100.0*Pds::MeanAbsoluteError(Ys,Y)<<std::endl;
    }  
    
    NN0.Save("../test/NeuralNettwork0.txt"); 
    return 0;
}