int RandomTrees::test(const char* sample_filename, const char* model_filename, double &test_error)
{
CvMat* data = 0;
CvMat* responses = 0;
int ok = read_num_class_data( sample_filename, this->number_of_features_, &data, &responses );
int nsamples_all = 0;
int i = 0;
if( !ok )
{
printf( "Could not read the sample file %s\n", sample_filename );
return -1;
}
printf( "The sample file %s is loaded.\n", sample_filename );
nsamples_all = data->rows;
// compute prediction error on train and test data
for( i = 0; i < nsamples_all; i++ )
{
CvMat sample;
cvGetRow( data, &sample, i );
this->loadModel(model_filename);
this->classify(&sample);
}
cvReleaseMat( &data );
cvReleaseMat( &responses );
return 0;
}
static int build_nbayes_classifier( char* data_filename, CvNormalBayesClassifier **nbayes){
const int var_count = 51;
CvMat* data = 0;
CvMat train_data;
CvMat* responses;
int ok = read_num_class_data( data_filename, 51, &data, &responses );
int nsamples_all = 0;
int i, j;
double train_hr = 0, test_hr = 0;
CvANN_MLP mlp;
if( !ok ){
printf( "No se pudo leer la información de entrenamiento %s\n", data_filename );
return -1;
}
printf( "La base de datos %s está siendo cargada...\n", data_filename );
nsamples_all = data->rows;
printf( "Entrenando el clasificador...\n");
// 1. unroll the responses
cvGetRows( data, &train_data, 0, nsamples_all);
// 2. train classifier
CvMat* train_resp = cvCreateMat( nsamples_all, 1, CV_32FC1);
for (int i = 0; i < nsamples_all; i++)
train_resp->data.fl[i] = responses->data.fl[i];
*nbayes = new CvNormalBayesClassifier(&train_data, train_resp);
if(DEBUG){
std::cout << "Train_data = "<< std::endl << std::endl;
PrintMat(&train_data);
std::cout << "Train_resp = "<< std::endl << " " << train_resp << std::endl << std::endl;
PrintMat(train_resp);
}
cvReleaseMat( &train_resp );
cvReleaseMat( &data );
cvReleaseMat( &responses );
return 0;
}
static
int build_rtrees_classifier( char* data_filename,
char* filename_to_save, char* filename_to_load )
{
CvMat* data = 0;
CvMat* responses = 0;
CvMat* var_type = 0;
CvMat* sample_idx = 0;
int ok = read_num_class_data( data_filename, 16, &data, &responses );
int nsamples_all = 0, ntrain_samples = 0;
int i = 0;
double train_hr = 0, test_hr = 0;
CvRTrees forest;
CvMat* var_importance = 0;
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*0.8);
// Create or load Random Trees classifier
if( filename_to_load )
{
// load classifier from the specified file
forest.load( filename_to_load );
ntrain_samples = 0;
if( forest.get_tree_count() == 0 )
{
printf( "Could not read the classifier %s\n", filename_to_load );
return -1;
}
printf( "The classifier %s is loaded.\n", data_filename );
}
else
{
// create classifier by using <data> and <responses>
printf( "Training the classifier ...\n");
// 1. create type mask
var_type = cvCreateMat( data->cols + 1, 1, CV_8U );
cvSet( var_type, cvScalarAll(CV_VAR_ORDERED) );
cvSetReal1D( var_type, data->cols, CV_VAR_CATEGORICAL );
// 2. create sample_idx
sample_idx = cvCreateMat( 1, nsamples_all, CV_8UC1 );
{
CvMat mat;
cvGetCols( sample_idx, &mat, 0, ntrain_samples );
cvSet( &mat, cvRealScalar(1) );
cvGetCols( sample_idx, &mat, ntrain_samples, nsamples_all );
cvSetZero( &mat );
}
// 3. train classifier
forest.train( data, CV_ROW_SAMPLE, responses, 0, sample_idx, var_type, 0,
CvRTParams(10,10,0,false,15,0,true,4,100,0.01f,CV_TERMCRIT_ITER));
printf( "\n");
}
// compute prediction error on train and test data
for( i = 0; i < nsamples_all; i++ )
{
double r;
CvMat sample;
cvGetRow( data, &sample, i );
r = forest.predict( &sample );
r = fabs((double)r - 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", forest.get_tree_count() );
// Print variable importance
var_importance = (CvMat*)forest.get_var_importance();
if( var_importance )
{
double rt_imp_sum = cvSum( var_importance ).val[0];
printf("var#\timportance (in %%):\n");
for( i = 0; i < var_importance->cols; i++ )
printf( "%-2d\t%-4.1f\n", i,
100.f*var_importance->data.fl[i]/rt_imp_sum);
}
//Print some proximitites
printf( "Proximities between some samples corresponding to the letter 'T':\n" );
{
CvMat sample1, sample2;
const int pairs[][2] = {{0,103}, {0,106}, {106,103}, {-1,-1}};
for( i = 0; pairs[i][0] >= 0; i++ )
{
cvGetRow( data, &sample1, pairs[i][0] );
cvGetRow( data, &sample2, pairs[i][1] );
printf( "proximity(%d,%d) = %.1f%%\n", pairs[i][0], pairs[i][1],
forest.get_proximity( &sample1, &sample2 )*100. );
}
}
// Save Random Trees classifier to file if needed
if( filename_to_save )
forest.save( filename_to_save );
cvReleaseMat( &sample_idx );
cvReleaseMat( &var_type );
cvReleaseMat( &data );
cvReleaseMat( &responses );
return 0;
}
static
int build_svm_classifier( char* data_filename )
{
CvMat* data = 0;
CvMat* responses = 0;
CvMat train_data;
int nsamples_all = 0, ntrain_samples = 0;
int var_count;
CvSVM svm;
int ok = read_num_class_data( data_filename, 16, &data, &responses );
if( !ok )
{
printf( "Could not read the database %s\n", data_filename );
return -1;
}
////////// SVM parameters ///////////////////////////////
CvSVMParams param;
param.kernel_type=CvSVM::LINEAR;
param.svm_type=CvSVM::C_SVC;
param.C=1;
///////////////////////////////////////////////////////////
printf( "The database %s is loaded.\n", data_filename );
nsamples_all = data->rows;
ntrain_samples = (int)(nsamples_all*0.1);
var_count = data->cols;
// train classifier
printf( "Training the classifier (may take a few minutes)...\n");
cvGetRows( data, &train_data, 0, ntrain_samples );
CvMat* train_resp = cvCreateMat( ntrain_samples, 1, CV_32FC1);
for (int i = 0; i < ntrain_samples; i++)
train_resp->data.fl[i] = responses->data.fl[i];
svm.train(&train_data, train_resp, 0, 0, param);
// classification
std::vector<float> _sample(var_count * (nsamples_all - ntrain_samples));
CvMat sample = cvMat( nsamples_all - ntrain_samples, 16, CV_32FC1, &_sample[0] );
std::vector<float> true_results(nsamples_all - ntrain_samples);
for (int j = ntrain_samples; j < nsamples_all; j++)
{
float *s = data->data.fl + j * var_count;
for (int i = 0; i < var_count; i++)
{
sample.data.fl[(j - ntrain_samples) * var_count + i] = s[i];
}
true_results[j - ntrain_samples] = responses->data.fl[j];
}
CvMat *result = cvCreateMat(1, nsamples_all - ntrain_samples, CV_32FC1);
printf("Classification (may take a few minutes)...\n");
svm.predict(&sample, result);
int true_resp = 0;
for (int i = 0; i < nsamples_all - ntrain_samples; i++)
{
if (result->data.fl[i] == true_results[i])
true_resp++;
}
printf("true_resp = %f%%\n", (float)true_resp / (nsamples_all - ntrain_samples) * 100);
cvReleaseMat( &train_resp );
cvReleaseMat( &result );
cvReleaseMat( &data );
cvReleaseMat( &responses );
return 0;
}
static
int build_nbayes_classifier( char* data_filename )
{
const int var_count = 16;
CvMat* data = 0;
CvMat train_data;
CvMat* responses;
int ok = read_num_class_data( data_filename, 16, &data, &responses );
int nsamples_all = 0, ntrain_samples = 0;
//int i, j;
//double /*train_hr = 0, */test_hr = 0;
CvANN_MLP mlp;
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);
// 1. unroll the responses
printf( "Unrolling the responses...\n");
cvGetRows( data, &train_data, 0, ntrain_samples );
// 2. train classifier
CvMat* train_resp = cvCreateMat( ntrain_samples, 1, CV_32FC1);
for (int i = 0; i < ntrain_samples; i++)
train_resp->data.fl[i] = responses->data.fl[i];
CvNormalBayesClassifier nbayes(&train_data, train_resp);
float* _sample = new float[var_count * (nsamples_all - ntrain_samples)];
CvMat sample = cvMat( nsamples_all - ntrain_samples, 16, CV_32FC1, _sample );
float* true_results = new float[nsamples_all - ntrain_samples];
for (int j = ntrain_samples; j < nsamples_all; j++)
{
float *s = data->data.fl + j * var_count;
for (int i = 0; i < var_count; i++)
{
sample.data.fl[(j - ntrain_samples) * var_count + i] = s[i];
}
true_results[j - ntrain_samples] = responses->data.fl[j];
}
CvMat *result = cvCreateMat(1, nsamples_all - ntrain_samples, CV_32FC1);
nbayes.predict(&sample, result);
int true_resp = 0;
//int accuracy = 0;
for (int i = 0; i < nsamples_all - ntrain_samples; i++)
{
if (result->data.fl[i] == true_results[i])
true_resp++;
}
printf("true_resp = %f%%\n", (float)true_resp / (nsamples_all - ntrain_samples) * 100);
delete[] true_results;
delete[] _sample;
cvReleaseMat( &train_resp );
cvReleaseMat( &result );
cvReleaseMat( &data );
cvReleaseMat( &responses );
return 0;
}
static
int build_mlp_classifier( char* data_filename,
char* filename_to_save, char* filename_to_load )
{
const int class_count = 26;
CvMat* data = 0;
CvMat train_data;
CvMat* responses = 0;
CvMat* mlp_response = 0;
int ok = read_num_class_data( data_filename, 16, &data, &responses );
int nsamples_all = 0, ntrain_samples = 0;
int i, j;
double train_hr = 0, test_hr = 0;
CvANN_MLP mlp;
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*0.8);
// Create or load MLP classifier
if( filename_to_load )
{
// load classifier from the specified file
mlp.load( filename_to_load );
ntrain_samples = 0;
if( !mlp.get_layer_count() )
{
printf( "Could not read the classifier %s\n", filename_to_load );
return -1;
}
printf( "The classifier %s is loaded.\n", data_filename );
}
else
{
// !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
//
// MLP does not support categorical variables by explicitly.
// So, instead of the output class label, we will use
// a binary vector of <class_count> components for training and,
// therefore, MLP will give us a vector of "probabilities" at the
// prediction stage
//
// !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
CvMat* new_responses = cvCreateMat( ntrain_samples, class_count, CV_32F );
// 1. unroll the responses
printf( "Unrolling the responses...\n");
for( i = 0; i < ntrain_samples; i++ )
{
int cls_label = cvRound(responses->data.fl[i]) - 'A';
float* bit_vec = (float*)(new_responses->data.ptr + i*new_responses->step);
for( j = 0; j < class_count; j++ )
bit_vec[j] = 0.f;
bit_vec[cls_label] = 1.f;
}
cvGetRows( data, &train_data, 0, ntrain_samples );
// 2. train classifier
int layer_sz[] = { data->cols, 100, 100, class_count };
CvMat layer_sizes =
cvMat( 1, (int)(sizeof(layer_sz)/sizeof(layer_sz[0])), CV_32S, layer_sz );
mlp.create( &layer_sizes );
printf( "Training the classifier (may take a few minutes)...\n");
mlp.train( &train_data, new_responses, 0, 0,
CvANN_MLP_TrainParams(cvTermCriteria(CV_TERMCRIT_ITER,300,0.01),
#if 1
CvANN_MLP_TrainParams::BACKPROP,0.001));
#else
CvANN_MLP_TrainParams::RPROP,0.05));
#endif
cvReleaseMat( &new_responses );
printf("\n");
}
mlp_response = cvCreateMat( 1, class_count, CV_32F );
// compute prediction error on train and test data
for( i = 0; i < nsamples_all; i++ )
{
int best_class;
CvMat sample;
cvGetRow( data, &sample, i );
CvPoint max_loc = {0,0};
mlp.predict( &sample, mlp_response );
cvMinMaxLoc( mlp_response, 0, 0, 0, &max_loc, 0 );
best_class = max_loc.x + 'A';
int r = fabs((double)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. );
// Save classifier to file if needed
if( filename_to_save )
mlp.save( filename_to_save );
cvReleaseMat( &mlp_response );
cvReleaseMat( &data );
cvReleaseMat( &responses );
return 0;
}
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 RandomTrees::train(const char* samples_filename, const char* model_filename, const double ratio, double &train_error, double &test_error)
{
CvMat* data = 0;
CvMat* responses = 0;
CvMat* var_type = 0;
CvMat* sample_idx = 0;
this->tree_parameters_.nactive_vars = (int)sqrt(this->number_of_features_);
int ok = read_num_class_data( samples_filename, this->number_of_features_, &data, &responses );
int nsamples_all = 0, ntrain_samples = 0;
int i = 0;
double train_hr = 0, test_hr = 0;
CvRTrees forest;
CvMat* var_importance = 0;
if( !ok )
{
cout << "Could not read the sample in" << samples_filename << endl;;
return -1;
}
cout << "The sample file " << samples_filename << " is loaded." << endl;
nsamples_all = data->rows;
ntrain_samples = (int)(nsamples_all * ratio);
// create classifier by using <data> and <responses>
cout << "Training the classifier ..." << endl;
// 1. create type mask
var_type = cvCreateMat( data->cols + 1, 1, CV_8U );
cvSet( var_type, cvScalarAll(CV_VAR_ORDERED) );
cvSetReal1D( var_type, data->cols, CV_VAR_CATEGORICAL );
// 2. create sample_idx
sample_idx = cvCreateMat( 1, nsamples_all, CV_8UC1 );
{
CvMat mat;
cvGetCols( sample_idx, &mat, 0, ntrain_samples );
cvSet( &mat, cvRealScalar(1) );
cvGetCols( sample_idx, &mat, ntrain_samples, nsamples_all );
cvSetZero( &mat );
}
// 3. train classifier
forest.train( data, CV_ROW_SAMPLE, responses, 0, sample_idx, var_type, 0, this->tree_parameters_);
cout << endl;
// compute prediction error on train and test data
for( i = 0; i < nsamples_all; i++ )
{
double r;
CvMat sample;
cvGetRow( data, &sample, i );
r = forest.predict( &sample );
r = fabs((double)r - 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;
train_error = 1 - train_hr;
test_error = 1 - test_hr;
cout << "Recognition rate: train = " << train_hr*100 << ", test = " << test_hr*100 << endl;
cout << "Number of trees: " << forest.get_tree_count() << endl;
// Print variable importance
var_importance = (CvMat*)forest.get_var_importance();
if( var_importance )
{
double rt_imp_sum = cvSum( var_importance ).val[0];
printf("var#\timportance (in %%):\n");
for( i = 0; i < var_importance->cols; i++ )
printf( "%-2d\t%-4.1f\n", i,100.f*var_importance->data.fl[i]/rt_imp_sum);
}
// Save Random Trees classifier to file if needed
if( model_filename )
forest.save( model_filename );
//cvReleaseMat( &var_importance ); //causes a segmentation fault
cvReleaseMat( &sample_idx );
cvReleaseMat( &var_type );
cvReleaseMat( &data );
cvReleaseMat( &responses );
return 0;
}
int AdaBoost::train(const char* samples_filename, const char* model_filename, const double ratio, double &train_error, double &test_error)
{
CvMat* data = 0;
CvMat* responses = 0;
CvMat* var_type = 0;
CvMat* temp_sample = 0;
CvMat* weak_responses = 0;
int ok = read_num_class_data( samples_filename, this->number_of_features_, &data, &responses );
int nsamples_all = 0, ntrain_samples = 0;
int var_count = 0;
int i=0, j=0, k=0;
double train_hr = 0, test_hr = 0;
CvBoost boost;
if( !ok )
{
cout << "Could not read the sample in" << samples_filename << endl;;
return -1;
}
cout << "The sample file " << samples_filename << " is loaded." << endl;
nsamples_all = data->rows;
ntrain_samples = (int)(nsamples_all * ratio);
var_count = data->cols;
// create classifier by using <data> and <responses>
cout << "Training the classifier ..." << endl;
// create classifiers
CvMat* new_data = cvCreateMat(ntrain_samples * this->number_of_classes_, var_count + 1 , CV_32F );//+1
CvMat* new_responses = cvCreateMat( ntrain_samples * this->number_of_classes_, 1, CV_32S );
// unroll the database type mask
printf( "Unrolling the samples ...\n");
for( i = 0; i < ntrain_samples; i++ )
{
float* data_row = (float*)(data->data.ptr + data->step*i);
for( j = 0; j < this->number_of_classes_; j++ )
{
float* new_data_row = (float*)(new_data->data.ptr + new_data->step*(i * this->number_of_classes_ + 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 * this->number_of_classes_ + j] = responses->data.fl[i] == j + FIRST_LABEL;
}
}
// 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 );//CV_VAR_CATEGORICAL CV_VAR_NUMERICAL
cvSetReal1D( var_type, var_count+1, CV_VAR_CATEGORICAL ); //CV_VAR_CATEGORICAL
// train classifier
//printf( "training the classifier (may take a few minutes)...");
boost.train( new_data, CV_ROW_SAMPLE, new_responses, 0, 0, var_type, 0, this->boost_parameters_);
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 < this->number_of_classes_; 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 + FIRST_LABEL;
}
}
r = fabs(best_class - responses->data.fl[i]) < FLT_EPSILON ? 1 : 0;
if( i < ntrain_samples )
train_hr += r;
else
test_hr += r;
}
train_hr /= (double)ntrain_samples;
test_hr /= ((double)nsamples_all - (double)ntrain_samples);
cout << "Recognition rate: train = " << train_hr * 100 << ", test = " << test_hr * 100 << endl;
// fill result-parameters
train_error = 1 - train_hr;
test_error = 1 - test_hr;
// Save classifier to file if needed
if( model_filename )
boost.save( model_filename );
boost.clear();
cvReleaseMat( &temp_sample );
cvReleaseMat( &weak_responses );
cvReleaseMat( &var_type );
cvReleaseMat( &data );
cvReleaseMat( &responses );
return 0;
}
int AdaBoost::test(const char* sample_filename, const char* model_filename, double &test_error)
{
CvMat* data = 0;
CvMat* responses = 0;
CvMat* var_type = 0;
CvMat* temp_sample = 0;
CvMat* weak_responses = 0;
int ok = 0;
int nsamples_all = 0;
int var_count;
int i, j, k;
double test_hr = 0;
CvBoost boost;
ok = read_num_class_data( sample_filename, this->number_of_features_, &data, &responses );
if( !ok )
{
printf( "Could not read the test-file %s\n", sample_filename );
return -1;
}
printf( "The test-file %s is loaded.\n", sample_filename );
nsamples_all = data->rows;
var_count = data->cols;
cout << "no. of test samples: " << nsamples_all << std::endl;
cout << "no. of features: " << var_count << std::endl;
cout << "no. of classifiers: " << this->number_of_classes_ << std::endl;
// load classifier from the specified file
boost.load( model_filename );
if( !boost.get_weak_predictors() )
{
printf( "Could not read the classifier %s\n", model_filename );
return -1;
}
//printf( "The classifier %s is loaded.\n", filename_to_load );
temp_sample = cvCreateMat( 1, var_count + 1, CV_32F );
weak_responses = cvCreateMat( 1, boost.get_weak_predictors()->total, CV_32F );
// compute prediction error on 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 < this->number_of_classes_; 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 + FIRST_LABEL;
}
}
r = fabs(best_class - responses->data.fl[i]) < FLT_EPSILON ? 1 : 0;
test_hr += r;
}
test_hr /= (double) nsamples_all;
test_error = 1 - test_hr;
boost.clear();
cvReleaseMat( &temp_sample );
cvReleaseMat( &weak_responses );
cvReleaseMat( &var_type );
cvReleaseMat( &data );
cvReleaseMat( &responses );
return 0;
}
