AdaBoost::AdaBoost(const unsigned int no_of_classes, const unsigned int no_of_features)
{
this->is_modelfile_loaded_ = false;
this->number_of_features_ = no_of_features;
this->number_of_classes_ = no_of_classes;
this->boost_parameters_ = CvBoostParams(CvBoost::REAL, 100, 0.95, 5, false, 0 );
}
int main()
{
const int train_sample_count = 300;
//#define LEPIOTA
#ifdef LEPIOTA
const char* filename = "../../../OpenCV_SVN/samples/c/agaricus-lepiota.data";
#else
const char* filename = "../../../OpenCV_SVN/samples/c/waveform.data";
#endif
CvDTree dtree;
CvBoost boost;
CvRTrees rtrees;
CvERTrees ertrees;
CvMLData data;
CvTrainTestSplit spl( train_sample_count );
data.read_csv( filename );
#ifdef LEPIOTA
data.set_response_idx( 0 );
#else
data.set_response_idx( 21 );
data.change_var_type( 21, CV_VAR_CATEGORICAL );
#endif
data.set_train_test_split( &spl );
printf("======DTREE=====\n");
dtree.train( &data, CvDTreeParams( 10, 2, 0, false, 16, 0, false, false, 0 ));
print_result( dtree.calc_error( &data, CV_TRAIN_ERROR), dtree.calc_error( &data ), dtree.get_var_importance() );
#ifdef LEPIOTA
printf("======BOOST=====\n");
boost.train( &data, CvBoostParams(CvBoost::DISCRETE, 100, 0.95, 2, false, 0));
print_result( boost.calc_error( &data, CV_TRAIN_ERROR ), boost.calc_error( &data ), 0 );
#endif
printf("======RTREES=====\n");
rtrees.train( &data, CvRTParams( 10, 2, 0, false, 16, 0, true, 0, 100, 0, CV_TERMCRIT_ITER ));
print_result( rtrees.calc_error( &data, CV_TRAIN_ERROR), rtrees.calc_error( &data ), rtrees.get_var_importance() );
printf("======ERTREES=====\n");
ertrees.train( &data, CvRTParams( 10, 2, 0, false, 16, 0, true, 0, 100, 0, CV_TERMCRIT_ITER ));
print_result( ertrees.calc_error( &data, CV_TRAIN_ERROR), ertrees.calc_error( &data ), ertrees.get_var_importance() );
return 0;
}
void Test::trainedClassifier(){
/* STEP 2. Opening the file */
//1. Declare a structure to keep the data
CvMLData cvml;
//2. Read the file
cvml.read_csv("samples.csv");
//3. Indicate which column is the response
cvml.set_response_idx(0);
/* STEP 3. Splitting the samples */
//1. Select 40 for the training
CvTrainTestSplit cvtts(40, true);
//2. Assign the division to the data
cvml.set_train_test_split(&cvtts);
printf("Training ... ");
/* STEP 4. The training */
//1. Declare the classifier
CvBoost boost;
//2. Train it with 100 features
boost.train(&cvml, CvBoostParams(CvBoost::REAL, 100, 0, 1, false, 0), false);
/* STEP 5. Calculating the testing and training error */
// 1. Declare a couple of vectors to save the predictions of each sample
std::vector<float> train_responses, test_responses;
// 2. Calculate the training error
float fl1 = boost.calc_error(&cvml,CV_TRAIN_ERROR,&train_responses);
// 3. Calculate the test error
float fl2 = boost.calc_error(&cvml,CV_TEST_ERROR,&test_responses);
printf("Error train %f \n", fl1);
printf("Error test %f \n", fl2);
/* STEP 6. Save your classifier */
// Save the trained classifier
boost.save("./trained_boost.xml", "boost");
//return EXIT_SUCCESS;
}
/**
* @author JIA Pei
* @version 2009-10-04
* @brief Training
* @param data Input - input data
* @param categories Input - column vector
* @return classification time cost
*/
void CClassificationAlgs::Training(const Mat_<float>& data, const Mat_<int>& categories)
{
unsigned int NbOfSamples = data.rows;
set<int> ClassSet;
for(int i = 0; i < categories.rows; i++)
{
ClassSet.insert(categories(i, 0));
}
this->m_iNbOfCategories = ClassSet.size();
switch(this->m_iClassificationMethod)
{
case CClassificationAlgs::DecisionTree:
this->m_CVDtree.train( data,
CV_ROW_SAMPLE,
categories,
Mat(),
Mat(),
Mat(),
Mat(),
CvDTreeParams( INT_MAX, 2, 0, false, this->m_iNbOfCategories, 0, false, false, 0 ) );
break;
case CClassificationAlgs::Boost:
this->m_CVBoost.train( data,
CV_ROW_SAMPLE,
categories,
Mat(),
Mat(),
Mat(),
Mat(),
CvBoostParams(CvBoost::DISCRETE, 50, 0.95, INT_MAX, false, 0),
false );
break;
case CClassificationAlgs::RandomForest:
this->m_CVRTrees.train( data,
CV_ROW_SAMPLE,
categories,
Mat(),
Mat(),
Mat(),
Mat(),
CvRTParams( INT_MAX, 2, 0, false, this->m_iNbOfCategories, 0, true, 0, 100, 0, CV_TERMCRIT_ITER ) );
break;
case CClassificationAlgs::ExtremeRandomForest:
this->m_CVERTrees.train(data,
CV_ROW_SAMPLE,
categories,
Mat(),
Mat(),
Mat(),
Mat(),
CvRTParams( INT_MAX, 2, 0, false, this->m_iNbOfCategories, 0, true, 0, 100, 0, CV_TERMCRIT_ITER ) );
break;
case CClassificationAlgs::SVM:
this->m_CVSVM.train( data,
categories,
Mat(),
Mat(),
CvSVMParams(CvSVM::C_SVC, CvSVM::RBF,
0, 1, 0,
1, 0, 0,
NULL, cvTermCriteria(CV_TERMCRIT_ITER, 1000, 1E-6) ) );
break;
}
}
static
int build_boost_classifier( char* data_filename,
char* filename_to_save, char* filename_to_load )
{
const int class_count = 26;
CvMat* data = 0;
CvMat* responses = 0;
CvMat* var_type = 0;
CvMat* temp_sample = 0;
CvMat* weak_responses = 0;
int ok = read_num_class_data( data_filename, 16, &data, &responses );
int nsamples_all = 0, ntrain_samples = 0;
int var_count;
int i, j, k;
double train_hr = 0, test_hr = 0;
CvBoost boost;
if( !ok )
{
printf( "Could not read the database %s\n", data_filename );
return -1;
}
printf( "The database %s is loaded.\n", data_filename );
nsamples_all = data->rows;
ntrain_samples = (int)(nsamples_all*0.5);
var_count = data->cols;
// Create or load Boosted Tree classifier
if( filename_to_load )
{
// load classifier from the specified file
boost.load( filename_to_load );
ntrain_samples = 0;
if( !boost.get_weak_predictors() )
{
printf( "Could not read the classifier %s\n", filename_to_load );
return -1;
}
printf( "The classifier %s is loaded.\n", data_filename );
}
else
{
// !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
//
// As currently boosted tree classifier in MLL can only be trained
// for 2-class problems, we transform the training database by
// "unrolling" each training sample as many times as the number of
// classes (26) that we have.
//
// !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
CvMat* new_data = cvCreateMat( ntrain_samples*class_count, var_count + 1, CV_32F );
CvMat* new_responses = cvCreateMat( ntrain_samples*class_count, 1, CV_32S );
// 1. unroll the database type mask
printf( "Unrolling the database...\n");
for( i = 0; i < ntrain_samples; i++ )
{
float* data_row = (float*)(data->data.ptr + data->step*i);
for( j = 0; j < class_count; j++ )
{
float* new_data_row = (float*)(new_data->data.ptr +
new_data->step*(i*class_count+j));
for( k = 0; k < var_count; k++ )
new_data_row[k] = data_row[k];
new_data_row[var_count] = (float)j;
new_responses->data.i[i*class_count + j] = responses->data.fl[i] == j+'A';
}
}
// 2. create type mask
var_type = cvCreateMat( var_count + 2, 1, CV_8U );
cvSet( var_type, cvScalarAll(CV_VAR_ORDERED) );
// the last indicator variable, as well
// as the new (binary) response are categorical
cvSetReal1D( var_type, var_count, CV_VAR_CATEGORICAL );
cvSetReal1D( var_type, var_count+1, CV_VAR_CATEGORICAL );
// 3. train classifier
printf( "Training the classifier (may take a few minutes)...\n");
boost.train( new_data, CV_ROW_SAMPLE, new_responses, 0, 0, var_type, 0,
CvBoostParams(CvBoost::REAL, 100, 0.95, 5, false, 0 ));
cvReleaseMat( &new_data );
cvReleaseMat( &new_responses );
printf("\n");
}
temp_sample = cvCreateMat( 1, var_count + 1, CV_32F );
weak_responses = cvCreateMat( 1, boost.get_weak_predictors()->total, CV_32F );
// compute prediction error on train and test data
for( i = 0; i < nsamples_all; i++ )
{
int best_class = 0;
double max_sum = -DBL_MAX;
double r;
CvMat sample;
cvGetRow( data, &sample, i );
for( k = 0; k < var_count; k++ )
temp_sample->data.fl[k] = sample.data.fl[k];
for( j = 0; j < class_count; j++ )
{
temp_sample->data.fl[var_count] = (float)j;
boost.predict( temp_sample, 0, weak_responses );
double sum = cvSum( weak_responses ).val[0];
if( max_sum < sum )
{
max_sum = sum;
best_class = j + 'A';
}
}
r = fabs(best_class - responses->data.fl[i]) < FLT_EPSILON ? 1 : 0;
if( i < ntrain_samples )
train_hr += r;
else
test_hr += r;
}
test_hr /= (double)(nsamples_all-ntrain_samples);
train_hr /= (double)ntrain_samples;
printf( "Recognition rate: train = %.1f%%, test = %.1f%%\n",
train_hr*100., test_hr*100. );
printf( "Number of trees: %d\n", boost.get_weak_predictors()->total );
// Save classifier to file if needed
if( filename_to_save )
boost.save( filename_to_save );
cvReleaseMat( &temp_sample );
cvReleaseMat( &weak_responses );
cvReleaseMat( &var_type );
cvReleaseMat( &data );
cvReleaseMat( &responses );
return 0;
}
int main()
{
const int train_sample_count = 300;
bool is_regression = false;
const char* filename = "data/waveform.data";
int response_idx = 21;
CvMLData data;
CvTrainTestSplit spl( train_sample_count );
if(data.read_csv(filename) != 0)
{
printf("couldn't read %s\n", filename);
exit(0);
}
data.set_response_idx(response_idx);
data.change_var_type(response_idx, CV_VAR_CATEGORICAL);
data.set_train_test_split( &spl );
const CvMat* values = data.get_values();
const CvMat* response = data.get_responses();
const CvMat* missing = data.get_missing();
const CvMat* var_types = data.get_var_types();
const CvMat* train_sidx = data.get_train_sample_idx();
const CvMat* var_idx = data.get_var_idx();
CvMat*response_map;
CvMat*ordered_response = cv_preprocess_categories(response, var_idx, response->rows, &response_map, NULL);
int num_classes = response_map->cols;
CvDTree dtree;
printf("======DTREE=====\n");
CvDTreeParams cvd_params( 10, 1, 0, false, 16, 0, false, false, 0);
dtree.train( &data, cvd_params);
print_result( dtree.calc_error( &data, CV_TRAIN_ERROR), dtree.calc_error( &data, CV_TEST_ERROR ), dtree.get_var_importance() );
#if 0
/* boosted trees are only implemented for two classes */
printf("======BOOST=====\n");
CvBoost boost;
boost.train( &data, CvBoostParams(CvBoost::DISCRETE, 100, 0.95, 2, false, 0));
print_result( boost.calc_error( &data, CV_TRAIN_ERROR ), boost.calc_error( &data, CV_TEST_ERROR), 0 );
#endif
printf("======RTREES=====\n");
CvRTrees rtrees;
rtrees.train( &data, CvRTParams( 10, 2, 0, false, 16, 0, true, 0, 100, 0, CV_TERMCRIT_ITER ));
print_result( rtrees.calc_error( &data, CV_TRAIN_ERROR), rtrees.calc_error( &data, CV_TEST_ERROR ), rtrees.get_var_importance() );
printf("======ERTREES=====\n");
CvERTrees ertrees;
ertrees.train( &data, CvRTParams( 10, 2, 0, false, 16, 0, true, 0, 100, 0, CV_TERMCRIT_ITER ));
print_result( ertrees.calc_error( &data, CV_TRAIN_ERROR), ertrees.calc_error( &data, CV_TEST_ERROR ), ertrees.get_var_importance() );
printf("======GBTREES=====\n");
CvGBTrees gbtrees;
CvGBTreesParams gbparams;
gbparams.loss_function_type = CvGBTrees::DEVIANCE_LOSS; // classification, not regression
gbtrees.train( &data, gbparams);
//gbt_print_error(&gbtrees, values, response, response_idx, train_sidx);
print_result( gbtrees.calc_error( &data, CV_TRAIN_ERROR), gbtrees.calc_error( &data, CV_TEST_ERROR ), 0);
printf("======KNEAREST=====\n");
CvKNearest knearest;
//bool CvKNearest::train( const Mat& _train_data, const Mat& _responses,
// const Mat& _sample_idx, bool _is_regression,
// int _max_k, bool _update_base )
bool is_classifier = var_types->data.ptr[var_types->cols-1] == CV_VAR_CATEGORICAL;
assert(is_classifier);
int max_k = 10;
knearest.train(values, response, train_sidx, is_regression, max_k, false);
CvMat* new_response = cvCreateMat(response->rows, 1, values->type);
//print_types();
//const CvMat* train_sidx = data.get_train_sample_idx();
knearest.find_nearest(values, max_k, new_response, 0, 0, 0);
print_result(knearest_calc_error(values, response, new_response, train_sidx, is_regression, CV_TRAIN_ERROR),
knearest_calc_error(values, response, new_response, train_sidx, is_regression, CV_TEST_ERROR), 0);
printf("======== RBF SVM =======\n");
//printf("indexes: %d / %d, responses: %d\n", train_sidx->cols, var_idx->cols, values->rows);
CvMySVM svm1;
CvSVMParams params1 = CvSVMParams(CvSVM::C_SVC, CvSVM::RBF,
/*degree*/0, /*gamma*/1, /*coef0*/0, /*C*/1,
/*nu*/0, /*p*/0, /*class_weights*/0,
cvTermCriteria(CV_TERMCRIT_ITER+CV_TERMCRIT_EPS, 1000, FLT_EPSILON));
//svm1.train(values, response, train_sidx, var_idx, params1);
svm1.train_auto(values, response, var_idx, train_sidx, params1);
svm_print_error(&svm1, values, response, response_idx, train_sidx);
printf("======== Linear SVM =======\n");
CvMySVM svm2;
CvSVMParams params2 = CvSVMParams(CvSVM::C_SVC, CvSVM::LINEAR,
/*degree*/0, /*gamma*/1, /*coef0*/0, /*C*/1,
/*nu*/0, /*p*/0, /*class_weights*/0,
cvTermCriteria(CV_TERMCRIT_ITER+CV_TERMCRIT_EPS, 1000, FLT_EPSILON));
//svm2.train(values, response, train_sidx, var_idx, params2);
svm2.train_auto(values, response, var_idx, train_sidx, params2);
svm_print_error(&svm2, values, response, response_idx, train_sidx);
printf("======NEURONAL NETWORK=====\n");
int num_layers = 3;
CvMat layers = cvMat(1, num_layers, CV_32SC1, calloc(1, sizeof(double)*num_layers*1));
cvmSetI(&layers, 0, 0, values->cols-1);
cvmSetI(&layers, 0, 1, num_classes);
cvmSetI(&layers, 0, 2, num_classes);
CvANN_MLP ann(&layers, CvANN_MLP::SIGMOID_SYM, 0.0, 0.0);
CvANN_MLP_TrainParams ann_params;
//ann_params.train_method = CvANN_MLP_TrainParams::BACKPROP;
CvMat ann_response = cvmat_make_boolean_class_columns(response, num_classes);
CvMat values2 = cvmat_remove_column(values, response_idx);
ann.train(&values2, &ann_response, NULL, train_sidx, ann_params, 0x0000);
//ann.train(values, &ann_response, NULL, train_sidx, ann_params, 0x0000);
ann_print_error(&ann, values, num_classes, &ann_response, response, response_idx, train_sidx);
#if 0 /* slow */
printf("======== Polygonal SVM =======\n");
//printf("indexes: %d / %d, responses: %d\n", train_sidx->cols, var_idx->cols, values->rows);
CvMySVM svm3;
CvSVMParams params3 = CvSVMParams(CvSVM::C_SVC, CvSVM::POLY,
/*degree*/2, /*gamma*/1, /*coef0*/0, /*C*/1,
/*nu*/0, /*p*/0, /*class_weights*/0,
cvTermCriteria(CV_TERMCRIT_ITER+CV_TERMCRIT_EPS, 1000, FLT_EPSILON));
//svm3.train(values, response, train_sidx, var_idx, params3);
svm3.train_auto(values, response, var_idx, train_sidx, params3);
svm_print_error(&svm3, values, response, response_idx, train_sidx);
#endif
return 0;
}