//Reads the corpus file, the output folder, the minimum and the maximum number of clusters and runs the EM algorithm.
int main(int argc, char **argv) {
const char* info = "printinfo";
if(strcmp(argv[2],info) == 0){
Corpus *c = new Corpus(argv[1]);
cout << "Corpus Loaded - Unique Terms = " << c->vocsize << endl;
cout << "Total Terms = " << c->terms << endl;
cout << "Total Articles = " << c->size() << endl;
double avg = (double)c->terms/(double)c->size();
cout << "avg = " << avg << endl;
std::tr1::unordered_map<string,int>::iterator it;
string outfile = "Vocabulary.txt";
ofstream out;
out.open(outfile.c_str());
for(it=c->id2word.begin(); it != c->id2word.end(); it++){
if(c->df[it->second] > 3){
out << it->first << endl;
}
}
out.close();
return 0;
}
long pi = 3.141592653589793;
if(argc < 6)
cout << "Usage: ./em Cropus_File Output_Folder min_number_of_clusters max_number_of_clusters max_em_iterations" << endl;
int key=15;
long double likelihood=0.0,L=0;
Corpus *c = new Corpus(argv[1]);
int minC = atoi(argv[3]);
int maxC = atoi(argv[4]);
int MaxIter = atoi(argv[5]);
long double likelihoods[maxC+1];
cout << "Corpus Loaded - Unique Terms = " << c->vocsize << endl;
//OMPED Iterations in order to accelerate the process
#pragma omp parallel for
for(unsigned j=minC; j <= maxC; j++){
EM *em = new EM(j,c,MaxIter,string(argv[2]));
likelihoods[j] = em->run();
em->~EM();
}
string outfile = string(argv[2])+"/likelihoods.txt";
ofstream out;
out.open(outfile.c_str());
for(unsigned i = minC; i <= maxC; i++){
double d = (i*(c->vocsize-1))+(i-1);
long double penalty = (d/2.0)*log2(c->terms);
long double dr = ((d/2.0)*(2*pi));
long double bic = -likelihoods[i] + penalty;
cout << i << " " << -likelihoods[i] << " " << penalty << " " << bic << endl;
out << i << " " << -likelihoods[i] << " " << penalty << " " << bic << endl;
}
out.close();
return 0;
}
void Classifier::SaveClassifierToFile(string fileName)
{
if (em_model.isTrained() == false)
return;
FileStorage fs = FileStorage(fileName, FileStorage::WRITE);
em_model.write(fs);
fs.release();
}
static void flux_jacobian_eigen_structure(const MODEL::Properties& p,
const GV& direction,
EM& Rv,
EM& Lv,
EV& Dv)
{
Rv.setIdentity();
Lv.setIdentity();
Dv = p.v * direction;
}
int train(float* src,char *filename,int N)
{
EM* myGMM = new EM(5);
FileStorage tmp(filename,cv::FileStorage::WRITE);
Mat train_32F(N,3,CV_32FC1,src);
train_32F.convertTo(train_32F,CV_32F,1/255.);
myGMM->train(train_32F);
tmp<<"model";
myGMM->write(tmp);
tmp.release();
return 0;
}
//Learn classifier
bool Classifier::Train(Mat sample)
{
cout << "Training classfication model...";
clock_t startTime_train = clock();
em_model.train(sample);
clock_t endTime_train = clock();
double timeSec_train = (endTime_train - startTime_train) / static_cast<double>(CLOCKS_PER_SEC);
cout << " train time = " << timeSec_train << "secs\n";
SaveClassifierToFile("em" + to_string(i) + ".xml");
i++;
return em_model.isTrained();
}
int main(int argc, char**argv) {
GetPot cl(argc, argv);
if(cl.search(2,"-h","--help")) {USAGE(); exit(0);}
string clustermodel=cl.follow("clustermodel.gz",2,"-c","--clustermodel");
string outfile=cl.follow("vector.gz",2,"-v","--vectorfile");
uint number=cl.follow(0,2,"-i","--idx");
EM em;
em.loadModel(clustermodel);
vector<double> vec=em.center(number).mean;
VectorFeature feat(vec);
feat.save(outfile);
DBG(10) << "cmdline was: "; printCmdline(argc,argv);
}
void Nieto::ExpectationMaximizationOpenCV2Features(const Mat1b &imageI, const Mat1b &imageL,
map<string, double> &i_means0, map<string, double> &i_covs0, map<string, double> &i_weights0,
map<string, double> &l_means0, map<string, double> &l_covs0, map<string, double> &l_weights0, int maxIters) {
double tempoInicio = static_cast<double>(getTickCount());
const int nFeatures = 2; // 2 features => {I, L}
const int nClusters = 4; // 4 classes => {pavement, markings, objects, unknown}
const bool aplicaResize = true;
// samples feature I
Mat1b I_imageClone = imageI.clone();
Mat1b I_trainImageClone = imageI.clone();
if (aplicaResize) resize(I_imageClone, I_trainImageClone, Size(160, 35), 0, 0, INTER_NEAREST);
Mat1d I_samples = I_trainImageClone.reshape(1, I_trainImageClone.rows * I_trainImageClone.cols);
// samples feature L
Mat1b L_imageClone = imageL.clone();
Mat1b L_trainImageClone = imageL.clone();
if (aplicaResize) resize(L_imageClone, L_trainImageClone, Size(160, 35), 0, 0, INTER_NEAREST);
Mat1d L_samples = L_trainImageClone.reshape(1, L_trainImageClone.rows * L_trainImageClone.cols);
// junta as amostras (uma em cada linha)
Mat1d samplesArray[] = { I_samples, L_samples };
Mat1d samples;
cv::hconcat(samplesArray, 2, samples);
// formata o _means0
Mat1d means0 = Mat1d(nClusters, nFeatures, CV_64FC1);
means0.at<double>(0, 0) = i_means0["pavement"];
means0.at<double>(1, 0) = i_means0["markings"];
means0.at<double>(2, 0) = i_means0["objects"];
means0.at<double>(3, 0) = 255.0 / 2.0;
means0.at<double>(0, 1) = l_means0["pavement"];
means0.at<double>(1, 1) = l_means0["markings"];
means0.at<double>(2, 1) = l_means0["objects"];
means0.at<double>(3, 1) = 255.0 / 2.0;
// formata o _covs0
Mat1d covs0_pavement = Mat1d(Size(nFeatures, nFeatures), double(0));
covs0_pavement.at<double>(0, 0) = i_covs0["pavement"];
covs0_pavement.at<double>(1, 1) = l_covs0["pavement"];
Mat1d covs0_markings = Mat1d(Size(nFeatures, nFeatures), double(0));;
covs0_markings.at<double>(0, 0) = i_covs0["markings"];
covs0_markings.at<double>(1, 1) = l_covs0["markings"];
Mat1d covs0_objects = Mat1d(Size(nFeatures, nFeatures), double(0));;
covs0_objects.at<double>(0, 0) = i_covs0["objects"];
covs0_objects.at<double>(1, 1) = l_covs0["objects"];
Mat1d covs0_unknown = Mat1d(Size(nFeatures, nFeatures), double(0));;
covs0_unknown.at<double>(0, 0) = ((255.0 / 2.0) / sqrt(3)) * ((255.0 / 2.0) / sqrt(3));
covs0_unknown.at<double>(1, 1) = ((255.0 / 2.0) / sqrt(3)) * ((255.0 / 2.0) / sqrt(3));
vector<Mat> covs0 = {
covs0_pavement,
covs0_markings,
covs0_objects,
covs0_unknown
};
// formata o _weights0
Mat1d weights0 = Mat1d(nClusters, 1, CV_64FC1);
double total_i = i_weights0["pavement"] + i_weights0["markings"] + i_weights0["objects"] + i_weights0["unknown"];
double total_l = l_weights0["pavement"] + l_weights0["markings"] + l_weights0["objects"] + l_weights0["unknown"];
double total_weights = total_i + total_l;
weights0.at<double>(0, 0) = (i_weights0["pavement"] + l_weights0["pavement"]) / total_weights;
weights0.at<double>(1, 0) = (i_weights0["markings"] + l_weights0["markings"]) / total_weights;
weights0.at<double>(2, 0) = (i_weights0["objects"] + l_weights0["objects"]) / total_weights;
weights0.at<double>(3, 0) = (i_weights0["unknown"] + l_weights0["unknown"]) / total_weights;
// cout << means0 << endl;
// condi��es do EM
// dims => samples.cols
// if (!(&means0) || (!means0.empty() && means0.rows == nClusters && means0.cols == samples.cols && means0.channels() == 1)) cout << "means - ok!" << endl;
EM em = EM(nClusters, EM::COV_MAT_DIAGONAL);
em.set("maxIters", maxIters);
em.trainE(samples, means0, covs0, weights0);
// calcula o tempo de execu��o
double tempoFim = static_cast<double>(getTickCount());
double tempoExecutando = ((tempoFim - tempoInicio) / getTickFrequency()) * 1000;
// exibe as sa�das definidas (texto e/ou imagem)
if (verbose) cout << "- em opencv (2 features): " << tempoExecutando << " ms" << endl;
if (display) {
// predict
Mat1b predictedImage = Mat1b(I_imageClone.size(), uchar(0));
for (int j = 0; j < predictedImage.rows; ++j) {
unsigned char *ptRowI = I_imageClone.ptr<uchar>(j);
unsigned char *ptRowL = L_imageClone.ptr<uchar>(j);
unsigned char *ptRowDst = predictedImage.ptr<uchar>(j);
for (int i = 0; i < predictedImage.cols; ++i) {
Mat1d elementPredict = Mat1d(Size(2, 1), CV_64FC1);
elementPredict.at<double>(0) = ptRowL[i];
elementPredict.at<double>(1) = ptRowI[i];
Vec2d emPredicted = em.predict(elementPredict);
switch ((int)emPredicted[1]) {
case 0: ptRowDst[i] = 160; break;
case 1: ptRowDst[i] = 255; break;
case 2: ptRowDst[i] = 80; break;
case 3: ptRowDst[i] = 0; break;
}
}
}
imshow("EM OpenCV - 2 Features", predictedImage);
}
}
void Nieto::ExpectationMaximizationOpenCV(const Mat1b &inGrayFrameRoi, int maxIters, map<string, double> &_means0, map<string, double> &_covs0, map<string, double> &_weights0) {
double tempoInicio = static_cast<double>(getTickCount());
const int nClusters = 4; // 4 classes => {pavement, markings, objects, unknown}
const bool aplicaResize = true;
EM em = EM(nClusters, EM::COV_MAT_DIAGONAL);
Mat1b grayFrameRoiClone = inGrayFrameRoi.clone();
Mat1b trainGrayFrameRoiClone = inGrayFrameRoi.clone();
if (aplicaResize) resize(grayFrameRoiClone, trainGrayFrameRoiClone, Size(160, 35), 0, 0, INTER_NEAREST);
Mat1d samples = trainGrayFrameRoiClone.reshape(1, trainGrayFrameRoiClone.rows * trainGrayFrameRoiClone.cols);
// formata o _means0
Mat1d means0 = Mat1d(nClusters, 1, CV_64FC1);
means0.at<double>(0) = _means0["pavement"];
means0.at<double>(1) = _means0["markings"];
means0.at<double>(2) = _means0["objects"];
means0.at<double>(3) = 255.0 / 2.0;
// formata o _covs0
vector<Mat> covs0 = {
Mat1d(1, 1, _covs0["pavement"]),
Mat1d(1, 1, _covs0["markings"]),
Mat1d(1, 1, _covs0["objects"]),
Mat1d(1, 1, ((255.0 / 2.0) / sqrt(3)) * ((255.0 / 2.0) / sqrt(3)))
};
// formata o _weights0
// Mat1d weights0 = *(Mat1f(nClusters, 1, CV_64FC1) << 0.75, 0.10, 0.10, 0.05);
Mat1d weights0 = *(Mat1f(nClusters, 1, CV_64FC1) <<
_weights0["pavement"],
_weights0["markings"],
_weights0["objects"],
_weights0["unknown"]
);
// cout << means0 << endl;
em.set("maxIters", maxIters);
em.trainE(samples, means0, covs0, weights0);
// calcula o tempo de execu��o
double tempoFim = static_cast<double>(getTickCount());
double tempoExecutando = ((tempoFim - tempoInicio) / getTickFrequency()) * 1000;
// exibe as sa�das definidas (texto e/ou imagem)
if (verbose) cout << "- em opencv (1 feature): " << tempoExecutando << " ms" << endl;
if (display) {
// predict
Mat1b predictedImage = Mat1b(grayFrameRoiClone.size(), uchar(0));
for (int j = 0; j < predictedImage.rows; ++j) {
unsigned char *ptRowSrc = grayFrameRoiClone.ptr<uchar>(j);
unsigned char *ptRowDst = predictedImage.ptr<uchar>(j);
for (int i = 0; i < predictedImage.cols; ++i) {
Vec2d emPredicted = em.predict(ptRowSrc[i]);
switch ((int)emPredicted[1]) {
case 0: ptRowDst[i] = 160; break;
case 1: ptRowDst[i] = 255; break;
case 2: ptRowDst[i] = 80; break;
case 3: ptRowDst[i] = 0; break;
}
}
}
imshow("EM OpenCV - 1 Feature", predictedImage);
}
}
