Rbm/source/poet.cpp

#include <iostream>
#include <fstream>
#include <streambuf>
#include <cstdio>
#include <cmath>
#include <string>
#include <armadillo>
#include <jsoncpp/json/json.h>
#include "Rbm.hpp"
#include "Layer.hpp"
#include "Stack.hpp"

using namespace std;
class RbmListener : public Rbm::IListener
{
	public:
	RbmListener() {}
	virtual ~RbmListener() {}
	
	bool onProgress(Rbm *pRbm, const Rbm::Status &status)
	{
		std::cout << "Progress :          " << status.progress << " %" << std::endl;
		std::cout << "error (per mini batch) = " << status.err << std::endl;
		std::cout << "error (total)          = " << status.err_total << std::endl;
		std::cout << "L1                     = " << status.L1 << std::endl;
		std::cout << "L2                     = " << status.L2 << std::endl;
		
		return true;
	}
};

arma::mat createTraining(const string &filename)
{
	FILE *pFile;

	pFile = fopen(filename.c_str(), "r");

	if (!pFile)
	{
		std::cout << "Could not open " << filename << "!" << std::endl;
		return 0;
	}

	int numTraining = 0;
	int numVisible = 26 + 10;
	
	arma::mat batch = arma::zeros(numTraining, numVisible);
	while(!feof(pFile))
	{
		char c;
		int result = fread(&c, 1, 1, pFile);
		if (result < 0)
		{
			break;
		}
		
		c = toupper(c);
		
		int index;
		if (isalpha(c))
		{
			index = (int)(c-'A');
		}
		if (isdigit(c))
		{
			index = (int)(c-'0');
		}
		arma::mat data = arma::zeros(1, numVisible);
		data[index] = 1;

		batch.insert_rows(batch.n_rows, data);
	}
	fclose(pFile);
	
	return batch;
}

int main()
{
	const string project("poet");
	
	Stack stack(".", project);

	arma::mat batch = createTraining("moby_ch1.txt");
	batch.save("poet.training.dat", arma::arma_ascii);
	
	return 0;
}