/**
* Allows to set the call template, throws in case the
* template parameters are not found!
* @param call_templ the call template
*/
inline void set_call_template(string & call_templ) {
//Store the template
m_call_templ = call_templ;
//Check the presence of the parameters
check_parameter(WORK_DIR_TEMPL_PARAM_NAME);
check_parameter(JOB_UID_TEMPL_PARAM_NAME);
check_parameter(LANGUAGE_TEMPL_PARAM_NAME);
}
int train_fs(const char* input_file_name, const char* model_file_name){
// Initialization
const char* error_msg;
set_default_params();
read_problem(input_file_name);
error_msg = check_parameter(&prob,¶m);
if(error_msg){
fprintf(stderr,"Error: %s\n",error_msg);
return -1;
}
// Do the cross-validation and save accuracy
double accuracy = do_cross_validation(nr_fold);
std::string info_fpath = std::string(model_file_name) + ".info";
FILE* info = fopen(info_fpath.c_str(), "w");
fprintf(info, "Accuracy : %f", accuracy);
//fflush(info);
fclose(info);
// Train a model on the whole dataset
model_train=train(&prob, ¶m);
if(save_model(model_file_name, model_train)){
fprintf(stderr,"can't save model to file %s\n",model_file_name);
return -1;
}
// Free resources
destroy_param(¶m);
free(prob.y);
free(prob.x);
free(x_space);
free(line);
return 0;
}
int main(int argc, char **argv)
{
char input_file_name[1024];
char model_file_name[1024];
const char *error_msg;
parse_command_line(argc, argv, input_file_name, model_file_name);
read_problem(input_file_name);
error_msg = check_parameter(&prob,¶m);
if(error_msg)
{
fprintf(stderr,"Error: %s\n",error_msg);
exit(1);
}
if(flag_cross_validation)
{
do_cross_validation();
}
else
{
model_=train(&prob, ¶m);
save_model(model_file_name, model_);
destroy_model(model_);
}
destroy_param(¶m);
free(prob.y);
free(prob.x);
free(x_space);
free(line);
return 0;
}
// Training SVM with feature vector X and label Y.
// Each row of X is a feature vector, with corresponding label in Y.
// Return a CV_32F weight Mat
Mat Objectness::trainSVM(CMat &X1f, const vecI &Y, int sT, double C, double bias, double eps)
{
// Set SVM parameters
parameter param; {
param.solver_type = sT; // L2R_L2LOSS_SVC_DUAL;
param.C = C;
param.eps = eps; // see setting below
param.p = 0.1;
param.nr_weight = 0;
param.weight_label = NULL;
param.weight = NULL;
set_print_string_function(print_null);
CV_Assert(X1f.rows == Y.size() && X1f.type() == CV_32F);
}
// Initialize a problem
feature_node *x_space = NULL;
problem prob;{
prob.l = X1f.rows;
prob.bias = bias;
prob.y = Malloc(double, prob.l);
prob.x = Malloc(feature_node*, prob.l);
const int DIM_FEA = X1f.cols;
prob.n = DIM_FEA + (bias >= 0 ? 1 : 0);
x_space = Malloc(feature_node, (prob.n + 1) * prob.l);
int j = 0;
for (int i = 0; i < prob.l; i++){
prob.y[i] = Y[i];
prob.x[i] = &x_space[j];
const float* xData = X1f.ptr<float>(i);
for (int k = 0; k < DIM_FEA; k++){
x_space[j].index = k + 1;
x_space[j++].value = xData[k];
}
if (bias >= 0){
x_space[j].index = prob.n;
x_space[j++].value = bias;
}
x_space[j++].index = -1;
}
CV_Assert(j == (prob.n + 1) * prob.l);
}
// Training SVM for current problem
const char* error_msg = check_parameter(&prob, ¶m);
if(error_msg){
fprintf(stderr,"ERROR: %s\n",error_msg);
exit(1);
}
model *svmModel = train(&prob, ¶m);
Mat wMat(1, prob.n, CV_64F, svmModel->w);
wMat.convertTo(wMat, CV_32F);
free_and_destroy_model(&svmModel);
destroy_param(¶m);
free(prob.y);
free(prob.x);
free(x_space);
return wMat;
}
void LVlinear_train(lvError *lvErr, const LVlinear_problem *prob_in, const LVlinear_parameter *param_in, LVlinear_model * model_out){
try{
// Input verification: Problem dimensions
if ((*(prob_in->x))->dimSize != (*(prob_in->y))->dimSize)
throw LVException(__FILE__, __LINE__, "The problem must have an equal number of labels and feature vectors (x and y).");
//-- Convert problem
std::unique_ptr<problem> prob(new problem);
uint32_t nr_nodes = (*(prob_in->y))->dimSize;
prob->l = nr_nodes;
prob->y = (*(prob_in->y))->elt;
// Create and array of pointers (sparse datastructure)
std::unique_ptr<feature_node*[]> x(new feature_node*[nr_nodes]);
prob->x = x.get();
auto x_in = prob_in->x;
for (unsigned int i = 0; i < (*x_in)->dimSize; i++){
// Assign the innermost svm_node array pointers to the array of pointers
auto xi_in_Hdl = (*x_in)->elt[i];
x[i] = reinterpret_cast<feature_node*>((*xi_in_Hdl)->elt);
}
//-- Convert parameters
std::unique_ptr<parameter> param(new parameter());
LVConvertParameter(param_in, param.get());
// Verify parameters
const char * param_check = check_parameter(prob.get(), param.get());
if (param_check != nullptr)
throw LVException(__FILE__, __LINE__, "Parameter check failed with the following error: " + std::string(param_check));
// Train model
model *result = train(prob.get(), param.get());
// Copy model to LabVIEW memory
LVConvertModel(result, model_out);
// Release memory allocated by train
free_model_content(result);
}
catch (LVException &ex) {
ex.returnError(lvErr);
// To avoid LabVIEW reading and utilizing bad memory, the dimension sizes of arrays is set to zero
(*(model_out->label))->dimSize = 0;
(*(model_out->w))->dimSize = 0;
}
catch (std::exception &ex) {
LVException::returnStdException(lvErr, __FILE__, __LINE__, ex);
(*(model_out->label))->dimSize = 0;
(*(model_out->w))->dimSize = 0;
}
catch (...) {
LVException ex(__FILE__, __LINE__, "Unknown exception has occurred");
ex.returnError(lvErr);
(*(model_out->label))->dimSize = 0;
(*(model_out->w))->dimSize = 0;
}
}
int main(int argc, char **argv)
{
char input_file_name[1024];
char model_file_name[1024];
const char *error_msg;
parse_command_line(argc, argv, input_file_name, model_file_name);
read_problem(input_file_name);
error_msg = check_parameter(&prob,¶m);
if(error_msg)
{
fprintf(stderr,"ERROR: %s\n",error_msg);
exit(1);
}
if( flag_find_C && flag_warm_start)
{
fprintf(stderr,"ERROR: Option -C and -i can't both exist\n");
exit(1);
}
if (flag_find_C)
{
do_find_parameter_C();
}
else if(flag_cross_validation)
{
do_cross_validation();
}
else
{
if(flag_warm_start)
{
if(prob.n != initial_model->nr_feature)
fprintf(stderr,"WARNING: The number of features in the input file does not match that in the initial model\n");
model_=warm_start_train(&prob, ¶m, initial_model);
free_and_destroy_model(&initial_model);
}
else
model_=train(&prob, ¶m);
if(save_model(model_file_name, model_))
{
fprintf(stderr,"can't save model to file %s\n",model_file_name);
exit(1);
}
free_and_destroy_model(&model_);
}
destroy_param(¶m);
free(prob.y);
free(prob.x);
free(x_space);
free(line);
return 0;
}
void rt_task4_thread_entry(void* parameter)
{
extern void start_transmit(void);
extern void stop_transmit(void);
extern uint8_t check_parameter(void);
// extern uint8_t self_check(void);
// extern void cpu_usage_init();
rt_uint32_t ev;
if((GPIO_ReadInputDataBit(GPIOD, GPIO_Pin_3) == 0))
{
coil.usRegCoilBuf |= M(0);
}
else
{
coil.usRegCoilBuf &= ~M(0);
}
rt_event_init(&key_event, "key_event", RT_IPC_FLAG_FIFO );
while(1)
{
if( rt_event_recv( &key_event, FOOT_PUPD | KEY_PUPD, RT_EVENT_FLAG_OR | RT_EVENT_FLAG_CLEAR, RT_WAITING_FOREVER, &ev ) == RT_EOK )
{
rt_thread_delay(6);
if( (ev & FOOT_PUPD) && (coil.usRegCoilBuf & M(0)) &&(GPIO_ReadInputDataBit(GPIOA, GPIO_Pin_0) == 0)&& \
(check_parameter()) && (coil.usRegCoilBuf & M(7)))
{
start_transmit();
}
else
{
stop_transmit();
}
if(ev & KEY_PUPD)
{
if((GPIO_ReadInputDataBit(GPIOD, GPIO_Pin_3) == 0))
{
coil.usRegCoilBuf |= M(0);
}
else
{
coil.usRegCoilBuf &= ~M(0);
}
}
}
rt_event_recv( &key_event, FOOT_PUPD | KEY_PUPD, RT_EVENT_FLAG_OR | RT_EVENT_FLAG_CLEAR, 2, &ev );
rt_thread_delay(20);
}
}
void LVlinear_cross_validation(lvError *lvErr, const LVlinear_problem *prob_in, const LVlinear_parameter *param_in, const int32_t nr_fold, LVArray_Hdl<double> target_out){
try{
// Input verification: Problem dimensions
if ((*(prob_in->x))->dimSize != (*(prob_in->y))->dimSize)
throw LVException(__FILE__, __LINE__, "The problem must have an equal number of labels and feature vectors (x and y).");
// Convert LVsvm_problem to svm_problem
std::unique_ptr<problem> prob(new problem);
uint32_t nr_nodes = (*(prob_in->y))->dimSize;
prob->l = nr_nodes;
prob->y = (*(prob_in->y))->elt;
// Create and array of pointers (sparse datastructure)
std::unique_ptr<feature_node*[]> x(new feature_node*[nr_nodes]);
prob->x = x.get();
auto x_in = prob_in->x;
for (unsigned int i = 0; i < (*x_in)->dimSize; i++){
// Assign the innermost svm_node array pointers to the array of pointers
auto xi_in_Hdl = (*x_in)->elt[i];
x[i] = reinterpret_cast<feature_node*>((*xi_in_Hdl)->elt);
}
// Assign parameters to svm_parameter
std::unique_ptr<parameter> param(new parameter());
LVConvertParameter(param_in, param.get());
// Verify parameters
const char * param_check = check_parameter(prob.get(), param.get());
if (param_check != nullptr)
throw LVException(__FILE__, __LINE__, "Parameter check failed with the following error: " + std::string(param_check));
// Allocate room in target_out
LVResizeNumericArrayHandle(target_out, nr_nodes);
// Run cross validation
cross_validation(prob.get(), param.get(), nr_fold, (*target_out)->elt);
(*target_out)->dimSize = nr_nodes;
}
catch (LVException &ex) {
ex.returnError(lvErr);
(*target_out)->dimSize = 0;
}
catch (std::exception &ex) {
LVException::returnStdException(lvErr, __FILE__, __LINE__, ex);
(*target_out)->dimSize = 0;
}
catch (...) {
LVException ex(__FILE__, __LINE__, "Unknown exception has occurred");
ex.returnError(lvErr);
(*target_out)->dimSize = 0;
}
}
void LibLinearWrapper::trainModel(Mat labels, Mat trainingData, vector<float>& weight)
{
CV_Assert(labels.rows == trainingData.rows);
m_prob.l = labels.rows;
m_prob.n = trainingData.cols;
auto num_samples = trainingData.total();
auto elements = num_samples + m_prob.l * 2;
vector<double> y(m_prob.l);
vector<struct feature_node*> x(m_prob.l);
vector<struct feature_node> x_spaceVec (elements);
m_prob.y = y.data();
m_prob.x = x.data();
auto x_space = x_spaceVec.data();
m_prob.bias = -1;
int j = 0;
for (int i = 0; i<m_prob.l; ++i)
{
m_prob.x[i] = &x_space[j];
m_prob.y[i] = labels.at<float>(i);
auto row_ptr = trainingData.ptr<float>(i);
for (int k = 0; k < trainingData.cols; ++k)
{
if (row_ptr[k])
{
x_space[j].index = k + 1;
x_space[j].value = row_ptr[k];
++j;
}
}
x_space[j++].index = -1;
}
auto error_msg = check_parameter(&m_prob, &m_param);
if (error_msg)
{
std::clog << "Error: " << error_msg << std::endl;
return;
}
struct model *model_ = train(&m_prob, &m_param);
double norm = std::inner_product(model_->w, model_->w + model_->nr_feature, model_->w, 0.0);
norm = sqrt(norm);
weight.resize(model_->nr_feature);
transform(model_->w, model_->w + model_->nr_feature, weight.begin(), [norm](double val) {
return val / norm;
});
}
int count_lines_parameters(FILE *fp) {
int n_lines = 0;
char * line = NULL;
size_t n = 0;
int r;
while(!feof(fp)) {
r = getline(&line, &n, fp);
if(r > 0 && !check_parameter(line))
n_lines++;
}
SID_free(SID_FARG line);
rewind(fp);
return (n_lines);
}
int main(int argc, char **argv)
{
char input_file_name[1024];
char model_file_name[1024];
const char *error_msg;
parse_command_line(argc, argv, input_file_name, model_file_name);
read_problem(input_file_name);
error_msg = check_parameter(&prob,¶m);
if(error_msg)
{
fprintf(stderr,"Error: %s\n",error_msg);
exit(1);
}
if(flag_cross_validation)
{
if (nr_fold <= 10)
{
do_cross_validation();
}
else
{
double cv;
nr_fold = nr_fold - 10;
cv = binary_class_cross_validation(&prob, ¶m, nr_fold);
printf("Cross Validation = %g%%\n",100.0*cv);
}
}
else
{
model_=train(&prob, ¶m);
if(save_model(model_file_name, model_))
{
fprintf(stderr,"can't save model to file %s\n",model_file_name);
exit(1);
}
free_and_destroy_model(&model_);
}
destroy_param(¶m);
free(prob.y);
free(prob.x);
free(prob.W);
free(x_space);
free(line);
return 0;
}
int main(int argc, char **argv)
{
char input_file_name[1024];
char model_file_name[1024];
const char *error_msg;
parse_command_line(argc, argv, input_file_name, model_file_name);
read_problem(input_file_name);
param.train_file = Malloc(char,1024);
strcpy(param.train_file, input_file_name);
error_msg = check_parameter(&prob,¶m);
if(error_msg)
{
fprintf(stderr,"ERROR: %s\n",error_msg);
exit(1);
}
if(flag_cross_validation)
{
do_cross_validation();
}
else
{
clock_t start_cpu, end_cpu;
double cpu_time_used;
start_cpu = clock();
model_=train(&prob, ¶m);
end_cpu = clock();
cpu_time_used = ((double) (end_cpu - start_cpu)) / CLOCKS_PER_SEC;
if(save_model(model_file_name, model_))
{
fprintf(stderr,"can't save model to file %s\n",model_file_name);
exit(1);
}
free_and_destroy_model(&model_);
}
destroy_param(¶m);
free(prob.y);
free(prob.x);
free(x_space);
free(line);
return 0;
}
struct model* main(int argc, char **argv)
{
char input_file_name[1024];
char model_file_name[1024];
const char *error_msg;
parse_command_line(argc, argv, input_file_name, model_file_name);
auto prob = read_problem(input_file_name);
error_msg = check_parameter(&prob, ¶m);
if (error_msg)
{
fprintf(stderr, "ERROR: %s\n", error_msg);
exit(1);
}
struct model *pmodel;
if (flag_find_C)
{
do_find_parameter_C(&prob);
}
else if (flag_cross_validation)
{
do_cross_validation(&prob);
}
else
{
pmodel = train(&prob, ¶m);
/*if (save_model(model_file_name, pmodel))
{
fprintf(stderr, "can't save model to file %s\n", model_file_name);
exit(1);
}
free_and_destroy_model(&pmodel);*/
}
destroy_param(¶m);
free(prob.y);
free(prob.x);
free(x_space);
free(line);
return pmodel;
}
// Interface function of matlab
// now assume prhs[0]: label prhs[1]: features
int main(int argc, char **argv)
{
const char *error_msg;
// fix random seed to have same results for each run
// (for cross validation)
srand(1);
char input_file_name[1024];
char model_file_name[1024];
parse_command_line(argc, argv, input_file_name, model_file_name);
read_problem(input_file_name);
error_msg = check_parameter(&prob,¶m);
if(error_msg)
{
fprintf(stderr,"Error: %s\n",error_msg);
destroy_param(¶m);
free(prob.y);
free(prob.x);
free(x_space);
exit(1);
}
if(cross_validation_flag)
{
do_cross_validation();
}
else
{
model_=FGM_train(&prob, ¶m);
printf("training is done!\n");
save_model_poly(model_file_name, model_);
printf("model is saved!\n");
destroy_model(model_);
}
destroy_param(¶m);
free(prob.y);
free(prob.x);
free(x_space);
}
int main(int argc, char *argv[])
{
int fd = 0;
int ret = 0;
struct aiocb my_aiocb = {0};
check_parameter(argc);
fd = open(argv[argc-1], O_RDONLY);
if (fd < 0)
{
fprintf(stderr, "open failure\n");
return EXIT_FAILURE;
}
my_aiocb.aio_buf = malloc(BUFSIZ+1);
my_aiocb.aio_fildes = fd;
my_aiocb.aio_nbytes = BUFSIZ;
my_aiocb.aio_offset = 0;
ret = aio_read(&my_aiocb);
if (ret < 0)
{
fprintf(stderr, "aio_read failure\n");
return EXIT_FAILURE;
}
while (aio_error(&my_aiocb) == EINPROGRESS);
if ((ret = aio_return(&my_aiocb)) > 0)
{
printf("%s", my_aiocb.aio_buf);
}
else
{
fprintf(stderr, "aio_return failure\n");
}
return EXIT_SUCCESS;
}
//void copy_parameter(param_temp,¶m)
//{
// param_t
//}
// Interface function of matlab
// now assume prhs[0]: label prhs[1]: features
int main(int argc, char **argv)
{
const char *error_msg;
// fix random seed to have same results for each run
// (for cross validation)
srand(1);
char input_file_name[1024];
char model_file_name[1024];
char param_file_name[1024];
int n_flag = 0;
parse_command_line(argc, argv, input_file_name, model_file_name,n_flag,param_file_name);
char char_para;
int length_param = 0;
double *para_entry; //
//n_flag = 1;
//int para_B[20] = {2, 3, 4, 5, 6, 7, 8, 9, 10, 12,14,16, 18, 20, 25, 30,35,40,45,50};
int para_B[40] = {2, 3, 4, 5, 6, 7, 8, 9, 10, 12, 14, 16, 18, 20, 24, 25, 26, 30,32, 35, 38, 40, 42, 45, 48, 50, 55, 60, 65,70,75,80, 85, 90, 95, 100, 105, 110, 115, 120};
//int para_B[32] = { 20, 24, 25, 26, 30,32, 35, 38, 40, 42, 45, 48, 50, 55, 60, 80, 100, 120, 140, 160, 180, 200, 220, 240, 260, 280};
if (n_flag==1)
{
read_parameter(param_file_name, para_entry, char_para, length_param);
}
read_problem(input_file_name);
error_msg = check_parameter(&prob,¶m);
//parameter *param_temp = new parameter[1];
//copy_parameter(param_temp,¶m);
if(error_msg)
{
fprintf(stderr,"Error: %s\n",error_msg);
exit(1);
}
if(cross_validation_flag)
{
do_cross_validation();
}
else
{
if(n_flag==0)
{
model_ = FGM_train(&prob, ¶m);
printf("training is done!\n");
save_model_poly(model_file_name, model_);
printf("model is saved!\n");
destroy_model(model_);
}
else
{
int i;
if (char_para=='C')
{
length_param = length_param;
}else
{
length_param = 40;
}
for (i=0;i<length_param;i++)
{
char param_char[1000];
char model_file[1024];
strcpy(model_file,model_file_name);
if (char_para=='C')
{
param.C = para_entry[i];
sprintf(param_char, "%.10lf ", para_entry[i]);
strcat(model_file,".c.");
strcat(model_file,param_char);
model_=FGM_train(&prob, ¶m);
}
else
{
int B = para_B[i];
param.B = B;
sprintf(param_char, "%d ", param.B);
printf("%d\n ", param.B);
strcat(model_file,".B.");
strcat(model_file,param_char);
model_=FGM_train(&prob, ¶m);
}
printf("training is done!\n");
save_model_poly(model_file, model_);
printf("model is saved!\n");
destroy_model(model_);
if(model_->feature_pair>600)
{
break;
}
}
}
}
if (n_flag==1)
{
delete []para_entry;
}
destroy_param(¶m);
free(prob.y);
free(prob.x);
free(x_space);
}
// Interface function of matlab
// now assume prhs[0]: label prhs[1]: features
void mexFunction( int nlhs, mxArray *plhs[],
int nrhs, const mxArray *prhs[] )
{
const char *error_msg;
// fix random seed to have same results for each run
// (for cross validation)
srand(1);
// Transform the input Matrix to libsvm format
if(nrhs > 0 && nrhs < 5)
{
int err=0;
if(!mxIsDouble(prhs[0]) || !mxIsDouble(prhs[1])) {
mexPrintf("Error: label vector and instance matrix must be double\n");
fake_answer(plhs);
return;
}
if(parse_command_line(nrhs, prhs, NULL))
{
exit_with_help();
destroy_param(¶m);
fake_answer(plhs);
return;
}
if(mxIsSparse(prhs[1]))
err = read_problem_sparse(prhs[0], prhs[1]);
else
{
mexPrintf("Training_instance_matrix must be sparse\n");
destroy_param(¶m);
fake_answer(plhs);
return;
}
// train's original code
error_msg = check_parameter(&prob, ¶m);
if(err || error_msg)
{
if (error_msg != NULL)
mexPrintf("Error: %s\n", error_msg);
destroy_param(¶m);
free(prob.y);
free(prob.x);
free(x_space);
fake_answer(plhs);
return;
}
if(cross_validation_flag)
{
double *ptr;
plhs[0] = mxCreateDoubleMatrix(1, 1, mxREAL);
ptr = mxGetPr(plhs[0]);
ptr[0] = do_cross_validation();
}
else
{
const char *error_msg;
model_ = train(&prob, ¶m);
error_msg = model_to_matlab_structure(plhs, model_);
if(error_msg)
mexPrintf("Error: can't convert libsvm model to matrix structure: %s\n", error_msg);
destroy_model(model_);
}
destroy_param(¶m);
free(prob.y);
free(prob.x);
free(x_space);
}
else
{
exit_with_help();
fake_answer(plhs);
return;
}
}
int main(int argc, char **argv)
{
#ifdef GPU
int dev = findCudaDevice(argc, (const char **) argv);
if (dev == -1)
return 0;
if (cublasCreate(&handle) != CUBLAS_STATUS_SUCCESS)
{
fprintf(stdout, "CUBLAS initialization failed!\n");
cudaDeviceReset();
exit(EXIT_FAILURE);
}
#endif // GPU
char input_file_name[1024];
char model_file_name[1024];
const char *error_msg;
parse_command_line(argc, argv, input_file_name, model_file_name);
time_t t1 = clock();
read_problem(input_file_name);
time_t t2 = clock();
printf("reading the input file took %f seconds.\n", float(t2-t1)/CLOCKS_PER_SEC);
error_msg = check_parameter(&prob,¶m);
if(error_msg)
{
fprintf(stderr,"ERROR: %s\n",error_msg);
exit(1);
}
if(flag_cross_validation)
{
do_cross_validation();
}
else
{
model_=train(&prob, ¶m);
if(save_model(model_file_name, model_))
{
fprintf(stderr,"can't save model to file %s\n",model_file_name);
exit(1);
}
free_and_destroy_model(&model_);
}
destroy_param(¶m);
free(prob.y);
free(prob.x);
free(x_space);
free(line);
#ifdef GPU
cublasDestroy(handle);
cudaDeviceReset();
#endif // GPU
printf("reading the input file took %f seconds.\n", float(t2-t1)/CLOCKS_PER_SEC);
return 0;
}
cv::Mat_<double> cRegression::__train_regressor(const cv::Mat_<double>& label_vec, const cv::Mat_<int>& instance_mat)
{
void(*print_func)(const char*) = &print_null;
const char *error_msg;
struct parameter param;
struct problem problem;
struct feature_node *x_space = NULL;
srand(1);
// std::cout << "initialize liblinear parameter." << std::endl;
param.solver_type = L2R_L2LOSS_SVR_DUAL;
param.C = 1.0 / (double)label_vec.rows;
param.eps = 0.1;
param.p = 0;
param.nr_weight = 0;
param.weight_label = NULL;
param.weight = NULL;
// std::cout << "initialize liblinear parameter finished." << std::endl;
set_print_string_function(print_func);
std::vector<int>* prob_x = NULL;
prob_x = new std::vector<int>[label_vec.rows]; // number of samples = label_vec.rows
size_t nzcount = 0;
// std::cout << "copy feature." << std::endl;
for (int i = 0; i < instance_mat.rows; ++i) {
for (int j = 0; j < instance_mat.cols; ++j) {
int elem = instance_mat(i, j);
if (elem != 0) {
prob_x[i].push_back(j);
++nzcount;
}
}
}
// std::cout << "copy feature finished." << std::endl;
//sort the vector
for (int i = 0; i < label_vec.rows; i++){
std::sort(prob_x[i].begin(), prob_x[i].end());
}
problem.l = label_vec.rows;
problem.n = instance_mat.cols;
problem.bias = -1;
int elements = (int)(nzcount + problem.l);
problem.y = Malloc(double, problem.l);
problem.x = Malloc(struct feature_node *, problem.l);
x_space = Malloc(struct feature_node, elements);
int j = 0;
for (int i = 0; i < problem.l; i++){
problem.y[i] = label_vec(i, 0);
problem.x[i] = &x_space[j];
for (int k = 0; k < prob_x[i].size(); k++){
x_space[j].index = prob_x[i][k] + 1;
x_space[j].value = 1;
j++;
}
x_space[j++].index = -1;
}
delete[] prob_x;
error_msg = check_parameter(&problem, ¶m);
if (error_msg){
fprintf(stderr, "ERROR: %s\n", error_msg);
}
// std::cout << "train model." << std::endl;
struct model *model = NULL;
model = train(&problem, ¶m);
// std::cout << "train model finished." << std::endl;
cv::Mat_<double> weight = cv::Mat::zeros(model->nr_feature, 1, CV_64FC1);
for (int i = 0; i < model->nr_feature; i++){
weight(i, 0) = model->w[i];
// std::cout << weight(i, 0) << " "; // std::endl;
}
free_and_destroy_model(&model);
destroy_param(¶m);
free((void*)(problem.y));
free((void*)(problem.x));
free((void*)(x_space));
return weight;
}
bool lt(ast * n1, ast * n2) {
unsigned num;
start:
if (n1 == n2)
return false;
check_value(n1->get_kind(), n2->get_kind());
switch(n1->get_kind()) {
case AST_SORT:
check_symbol(to_sort(n1)->get_name(), to_sort(n2)->get_name());
check_value(to_sort(n1)->get_num_parameters(), to_sort(n2)->get_num_parameters());
num = to_sort(n1)->get_num_parameters();
SASSERT(num > 0);
for (unsigned i = 0; i < num; i++) {
parameter p1 = to_sort(n1)->get_parameter(i);
parameter p2 = to_sort(n2)->get_parameter(i);
check_parameter(p1, p2);
}
UNREACHABLE();
return false;
case AST_FUNC_DECL:
check_symbol(to_func_decl(n1)->get_name(), to_func_decl(n2)->get_name());
check_value(to_func_decl(n1)->get_arity(), to_func_decl(n2)->get_arity());
check_value(to_func_decl(n1)->get_num_parameters(), to_func_decl(n2)->get_num_parameters());
num = to_func_decl(n1)->get_num_parameters();
for (unsigned i = 0; i < num; i++) {
parameter p1 = to_func_decl(n1)->get_parameter(i);
parameter p2 = to_func_decl(n2)->get_parameter(i);
check_parameter(p1, p2);
}
num = to_func_decl(n1)->get_arity();
for (unsigned i = 0; i < num; i++) {
ast * d1 = to_func_decl(n1)->get_domain(i);
ast * d2 = to_func_decl(n2)->get_domain(i);
check_ast(d1, d2);
}
n1 = to_func_decl(n1)->get_range();
n2 = to_func_decl(n2)->get_range();
goto start;
case AST_APP:
check_value(to_app(n1)->get_num_args(), to_app(n2)->get_num_args());
check_value(to_app(n1)->get_depth(), to_app(n2)->get_depth());
check_ast(to_app(n1)->get_decl(), to_app(n2)->get_decl());
num = to_app(n1)->get_num_args();
for (unsigned i = 0; i < num; i++) {
expr * arg1 = to_app(n1)->get_arg(i);
expr * arg2 = to_app(n2)->get_arg(i);
check_ast(arg1, arg2);
}
UNREACHABLE();
return false;
case AST_QUANTIFIER:
check_bool(to_quantifier(n1)->is_forall(), to_quantifier(n2)->is_forall());
check_value(to_quantifier(n1)->get_num_decls(), to_quantifier(n2)->get_num_decls());
check_value(to_quantifier(n1)->get_num_patterns(), to_quantifier(n2)->get_num_patterns());
check_value(to_quantifier(n1)->get_num_no_patterns(), to_quantifier(n2)->get_num_no_patterns());
check_value(to_quantifier(n1)->get_weight(), to_quantifier(n2)->get_weight());
num = to_quantifier(n1)->get_num_decls();
for (unsigned i = 0; i < num; i++) {
check_symbol(to_quantifier(n1)->get_decl_name(i), to_quantifier(n2)->get_decl_name(i));
check_ast(to_quantifier(n1)->get_decl_sort(i), to_quantifier(n2)->get_decl_sort(i));
}
num = to_quantifier(n1)->get_num_patterns();
for (unsigned i = 0; i < num; i++) {
check_ast(to_quantifier(n1)->get_pattern(i), to_quantifier(n2)->get_pattern(i));
}
num = to_quantifier(n1)->get_num_no_patterns();
for (unsigned i = 0; i < num; i++) {
check_ast(to_quantifier(n1)->get_no_pattern(i), to_quantifier(n2)->get_no_pattern(i));
}
n1 = to_quantifier(n1)->get_expr();
n2 = to_quantifier(n2)->get_expr();
goto start;
case AST_VAR:
check_value(to_var(n1)->get_idx(), to_var(n2)->get_idx());
n1 = to_var(n1)->get_sort();
n2 = to_var(n2)->get_sort();
goto start;
default:
UNREACHABLE();
return false;
}
}
bool QPredictLinearLearner::train(QPredictDocumentList &doc_list)
{
uint32_t cnt;
struct problem prob;
struct feature_node *x_space;
int32_t max_index;
size_t num_space;
const char * error_msg;
int i, j;
cnt = 1;
prob.l = doc_list.size();
prob.y = new int[prob.l];
memset(prob.y, 0, sizeof(int) * prob.l);
prob.x = new struct feature_node *[prob.l];
memset(prob.x, 0, sizeof(struct feature_node *) * prob.l);
prob.bias = m_bias;
num_space = 0;
QPredictDocumentListIter end_doc_it = doc_list.end();
for (QPredictDocumentListIter doc_it = doc_list.begin(); doc_it != end_doc_it; ++doc_it) {
num_space += doc_it->feature_list.size() + 1;
}
x_space = new struct feature_node[num_space + prob.l];
memset(x_space, 0, sizeof(struct feature_node) * (num_space + prob.l));
max_index = 0;
for (i = 0, j = 0; i < prob.l; i++) {
std::vector<uint32_t>::iterator termIt;
prob.x[i] = &x_space[j];
prob.y[i] = doc_list[i].class_index;
QPredictFeatureList &feature_list = doc_list[i].feature_list;
// sort feature
sort(feature_list.begin(), feature_list.end(), QPredictFeature::feature_compare);
const QPredictFeatureListIter &feature_end_it = feature_list.end();
for (QPredictFeatureListIter feature_it = feature_list.begin(); feature_it != feature_end_it; ++feature_it) {
x_space[j].index = feature_it->id;
x_space[j].value = feature_it->value;
++j;
}
if (j >= 1 && x_space[j - 1].index > max_index)
max_index = x_space[j - 1].index;
if(prob.bias >= 0)
x_space[j++].value = prob.bias;
x_space[j++].index = -1;
cnt++;
}
if(prob.bias >= 0) {
prob.n = max_index + 1;
for(i = 1;i < prob.l; i++)
(prob.x[i]-2)->index = prob.n;
x_space[j-2].index = prob.n;
} else {
prob.n = max_index;
}
if ((error_msg = check_parameter(&prob, &m_param))) {
//
std::cerr << "error " << error_msg << std::endl;
}
m_model = ::train(&prob, &m_param);
/*/ cross validation
int total_correct = 0;
int *target = (int*) malloc(sizeof(int) * prob.l);
cross_validation(&prob,&m_param,10,target);
for(int i=0;i<prob.l;i++)
if(target[i] == prob.y[i])
++total_correct;
fprintf(stderr, "Cross Validation Accuracy = %g%%\n",100.0*total_correct/prob.l);
free(target);
*/
//destroy_param(&m_param);
delete []prob.y;
delete []prob.x;
delete []x_space;
return true;
}
// Interface function of matlab
// now assume prhs[0]: label prhs[1]: features
void mexFunction( int nlhs, mxArray *plhs[],
int nrhs, const mxArray *prhs[] )
{
const char *error_msg;
// fix random seed to have same results for each run
// (for cross validation)
srand(1);
// Transform the input Matrix to libsvm format
if(nrhs > 2 && nrhs <= 6)
{
int err=0;
if(!mxIsDouble(prhs[0]) || !mxIsDouble(prhs[1]) ) {
mexPrintf("Error: weight vector, label vector matrix must be double\n");
fake_answer(plhs);
return;
}
if(!mxIsSingle(prhs[2])) {
mexPrintf("Error: instance matrix must be single\n");
fake_answer(plhs);
return;
}
if(parse_command_line(nrhs, prhs, NULL))
{
exit_with_help();
destroy_param(¶m);
fake_answer(plhs);
return;
}
#ifdef _DENSE_REP
if(!mxIsSparse(prhs[2]))
err = read_problem_sparse(prhs[0], prhs[1],prhs[2]);
else
{
mexPrintf("Training_instance_matrix must be dense\n");
destroy_param(¶m);
fake_answer(plhs);
return;
}
#else
if(mxIsSparse(prhs[2]))
err = read_problem_sparse(prhs[0], prhs[1],prhs[2]);
else
{
mexPrintf("Training_instance_matrix must be sparse\n");
destroy_param(¶m);
fake_answer(plhs);
return;
}
#endif
// xren: delete the input instance matrix to free up space
if (nrhs==6) {
mxArray* var=(mxArray*)prhs[5];
int status=mexCallMATLAB(0,NULL,1, &var, "clear");
if (status!=0) mexPrintf("Failed to delete variable %s\n",mxArrayToString(prhs[5]));
//mxDestroyArray( (mxArray*)prhs[1] );
}
// train's original code
error_msg = check_parameter(&prob, ¶m);
if(err || error_msg)
{
if (error_msg != NULL)
mexPrintf("Error: %s\n", error_msg);
destroy_param(¶m);
free(prob.y);
free(prob.x);
if (!use_existing_space)
free(x_space);
fake_answer(plhs);
return;
}
if(cross_validation_flag)
{
double *ptr;
plhs[0] = mxCreateDoubleMatrix(1, 1, mxREAL);
ptr = mxGetPr(plhs[0]);
ptr[0] = do_cross_validation();
}
else
{
const char *error_msg;
model_ = train(&prob, ¶m);
error_msg = model_to_matlab_structure(plhs, model_);
if(error_msg)
mexPrintf("Error: can't convert libsvm model to matrix structure: %s\n", error_msg);
free_and_destroy_model(&model_);
}
destroy_param(¶m);
free(prob.y);
free(prob.x);
free(prob.W);
if (!use_existing_space)
free(x_space);
}
else
{
exit_with_help();
fake_answer(plhs);
return;
}
}
int grab_next_line_parameter(FILE *fp, char **line, size_t *n) {
int rval = grab_next_line(fp, line, n);
while(!feof(fp) && !check_parameter(*line))
rval = grab_next_line(fp, line, n);
return (rval);
}
/* -------------------------------------------------------------
* MAIN:
* Check all parameters passed on the command line, calculate
* the date to be displayed, and display it.
* ------------------------------------------------------------- */
int main( int argc, char **argv, char **envp ) {
struct tm *time_var;
time_t time_number;
signed long time_offset;
char *ptr;
int i, date_override;
char saved_command[MAX_PARM_LEN+1];
char saved_format[MAX_MASK_LEN+1];
char saved_startdate_override[13]; /* YYYYMMDDHHMM_ */
/*
* Check to see what command line parameters we have
*/
if (argc < 2) {
printf( "%s: (c)Mark Dickinson, 2001\n", argv[0] );
show_syntax();
exit( 1 );
}
time_offset = 0; /* default, and start point for adjustments */
date_override = 0; /* use current system date and time */
strcpy(saved_format,"YYYYMMDD"); /* default */
i = 1;
/* use a while loop instead of a for loop as we may
* increment the counter ourselves */
while ( i < argc ) {
ptr = argv[i];
i++;
if (i >= argc) {
printf( "Missing value for %s\n", ptr );
exit( 1 );
}
strncpy( saved_command, ptr, MAX_PARM_LEN );
ptr = argv[i];
if (strncmp("-format",saved_command,7) == 0) {
validate_format( ptr, saved_format );
}
else if (strncmp("-workingdate",saved_command,12) == 0) {
date_override = 1;
strncpy( saved_startdate_override, ptr, 12 ); /* YYYYMMDDHHMM */
}
else {
time_offset = time_offset + check_parameter( saved_command, ptr );
}
i++;
}
/*
* Work out the new time and print the result.
*/
if (date_override == 1) {
/* have to get the dst flag setting for this */
time_number = time(0);
time_var = localtime( &time_number );
/* then workout the callers passed time */
time_number = make_time( (char *)&saved_startdate_override, time_var->tm_isdst );
}
else {
time_number = time(0); /* time now in seconds from 00:00, Jan 1 1970 */
}
time_number = time_number + time_offset;
if (strcmp("CTIME",saved_format) == 0) {
printf( "%s", ctime( &time_number ) );
}
else {
time_var = localtime( &time_number );
print_time( time_var, saved_format );
}
exit( 0 );
} /* end main */
//---------------------------- global variables -------------------------------
int main(int argc, char **argv)
{
char input_file_name[1024];
char model_file_name[1024];
const char *error_msg;
#ifdef FIGURE56
char test_file_name[1024];
parse_command_line(argc, argv, input_file_name, test_file_name);
#else
parse_command_line(argc, argv, input_file_name, model_file_name);//initialize global struct param, according to commond line
//_parse_command_line(argc, argv, input_file_name, model_file_name);//initialize global struct param, according to commond line
#endif
read_problem(input_file_name);//get all possible information about the train file into global struct prob
#ifdef FIGURE56
read_problem_test(test_file_name);
#endif
error_msg = check_parameter(&prob,¶m);
if(error_msg)
{
fprintf(stderr,"ERROR: %s\n",error_msg);
exit(1);
}
// struct model
//{
// struct parameter param;
// int nr_class; /* number of classes */
// int nr_feature;
// double *w;
// int *label; /* label of each class */
//};
// model_=train(&prob, ¶m);
//--------apply memory for V matrix--------------
int i=0;
double * p = Malloc(double,param.col_size * prob.l);
//srand( (unsigned)time( NULL ) ); //种子函数
for (i=0;i<param.col_size * prob.l;i++)
{
p[i]=rand()/(RAND_MAX+1.0); //产生随机数的函数
//p[i]=rand();
}
double ** v_pp = Malloc(double* ,prob.l);
param.v_pp = v_pp;
for (i=0;i<prob.l;i++)
param.v_pp[i] = &p[param.col_size * i];
model_=_train(&prob, ¶m);
#ifdef FIGURE56
#else
if(save_model(model_file_name, model_))
{
fprintf(stderr,"can't save model to file %s\n",model_file_name);
exit(1);
}
#endif
free_and_destroy_model(&model_);
destroy_param(¶m);
free(prob.y);
free(prob.x);
free(prob.query);
free(x_space);
////////free the variable
free(v_pp);
free(p);
#ifdef FIGURE56
free(probtest.y);
free(probtest.x);
free(x_spacetest);
#endif
free(line);
return 0;
}
void LVlinear_train(lvError *lvErr, const LVlinear_problem *prob_in, const LVlinear_parameter *param_in, LVlinear_model * model_out){
try{
// Input verification: Nonempty problem
if (prob_in->x == nullptr || (*(prob_in->x))->dimSize == 0)
throw LVException(__FILE__, __LINE__, "Empty problem passed to liblinear_train.");
// Input verification: Problem dimensions
if ((*(prob_in->x))->dimSize != (*(prob_in->y))->dimSize)
throw LVException(__FILE__, __LINE__, "The problem must have an equal number of labels and feature vectors (x and y).");
uint32_t nr_nodes = (*(prob_in->y))->dimSize;
// Input validation: Number of feature vectors too large (exceeds max signed int)
if(nr_nodes > INT_MAX)
throw LVException(__FILE__, __LINE__, "Number of feature vectors too large (grater than " + std::to_string(INT_MAX) + ")");
//-- Convert problem
auto prob = std::make_unique<problem>();
prob->l = nr_nodes;
prob->y = (*(prob_in->y))->elt;
prob->n = 0; // Calculated later
prob->bias = prob_in->bias;
// Create and array of pointers (sparse datastructure)
auto x = std::make_unique<feature_node*[]>(nr_nodes);
prob->x = x.get();
auto x_in = prob_in->x;
for (unsigned int i = 0; i < (*x_in)->dimSize; i++){
// Assign the innermost svm_node array pointers to the array of pointers
auto xi_in_Hdl = (*x_in)->elt[i];
x[i] = reinterpret_cast<feature_node*>((*xi_in_Hdl)->elt);
// Input validation: Final index -1?
if ((*xi_in_Hdl)->elt[(*xi_in_Hdl)->dimSize - 1].index != -1)
throw LVException(__FILE__, __LINE__, "The index of the last element of each feature vector needs to be -1 (liblinear_train).");
// Calculate the max index
// This detail is not exposed in LabVIEW, as setting the wrong value causes a crash
// Second to last element should contain the max index for that feature vector (as they are in ascending order).
auto secondToLast = (*xi_in_Hdl)->dimSize - 2; // Ignoring -1 index
auto largestIndex = (*xi_in_Hdl)->elt[secondToLast].index;
if (secondToLast >= 0 && largestIndex > prob->n)
prob->n = largestIndex;
}
//-- Convert parameters
auto param = std::make_unique<parameter>();
LVConvertParameter(*param_in, *param);
// Verify parameters
const char * param_check = check_parameter(prob.get(), param.get());
if (param_check != nullptr)
throw LVException(__FILE__, __LINE__, "Parameter check failed with the following error: " + std::string(param_check));
// Train model
model *result = train(prob.get(), param.get());
// Copy model to LabVIEW memory
LVConvertModel(*result, *model_out);
// Release memory allocated by train
free_model_content(result);
}
catch (LVException &ex) {
(*(model_out->label))->dimSize = 0;
(*(model_out->w))->dimSize = 0;
(*(model_out->param).weight)->dimSize = 0;
(*(model_out->param).weight_label)->dimSize = 0;
ex.returnError(lvErr);
}
catch (std::exception &ex) {
(*(model_out->label))->dimSize = 0;
(*(model_out->w))->dimSize = 0;
(*(model_out->param).weight)->dimSize = 0;
(*(model_out->param).weight_label)->dimSize = 0;
LVException::returnStdException(lvErr, __FILE__, __LINE__, ex);
}
catch (...) {
(*(model_out->label))->dimSize = 0;
(*(model_out->w))->dimSize = 0;
(*(model_out->param).weight)->dimSize = 0;
(*(model_out->param).weight_label)->dimSize = 0;
LVException ex(__FILE__, __LINE__, "Unknown exception has occurred");
ex.returnError(lvErr);
}
}
void mexFunction( int nlhs, mxArray *plhs[],
int nrhs, const mxArray *prhs[] )
{
const char *error_msg;
srand(1);
if(nrhs == 7) /* force alphas_in and w_in to be initialized */
{
int err=0;
if(!mxIsClass(prhs[0], "single") || !mxIsClass(prhs[1], "single") || !mxIsClass(prhs[4], "single") || !mxIsClass(prhs[4], "single") || !mxIsClass(prhs[6], "single")) {
mexPrintf("Error: label vector, instance matrix and alphas_in must be float\n");
fake_answer(plhs);
return;
}
if(parse_command_line(nrhs, prhs, NULL))
{
exit_with_help();
destroy_param(¶m);
fake_answer(plhs);
return;
}
#ifdef _DENSE_REP
if(!mxIsSparse(prhs[1]))
err = read_problem_sparse(prhs[0], prhs[1], prhs[4], prhs[5], prhs[6]);
else
{
mexPrintf("Training_instance_matrix must be dense\n");
destroy_param(¶m);
fake_answer(plhs);
return;
}
#else
if(mxIsSparse(prhs[1]))
err = read_problem_sparse(prhs[0], prhs[1], prhs[4]);
else
{
mexPrintf("Training_instance_matrix must be sparse\n");
destroy_param(¶m);
fake_answer(plhs);
return;
}
#endif
error_msg = check_parameter(&prob, ¶m);
if(err || error_msg)
{
if (error_msg != NULL)
mexPrintf("Error: %s\n", error_msg);
destroy_param(¶m);
free(prob.y);
free(prob.x);
free(prob.alphas_in);
free(prob.w_in);
/*free(x_space);*/
fake_answer(plhs);
return;
}
if(cross_validation_flag)
{
float *ptr;
plhs[0] = mxCreateDoubleMatrix(1, 1, mxREAL);
ptr = (float*) mxGetPr(plhs[0]);
ptr[0] = do_cross_validation();
}
else
{
const char *error_msg;
model_ = train(&prob, ¶m);
error_msg = model_to_matlab_structure(plhs, model_);
if(error_msg)
mexPrintf("Error: can't convert libsvm model to matrix structure: %s\n", error_msg);
destroy_model(model_);
}
destroy_param(¶m);
free(prob.y);
free(prob.x);
free(prob.alphas_in);
free(prob.w_in);
/*free(x_space);*/
}
else
{
exit_with_help();
fake_answer(plhs);
return;
}
}
void BoostCart::GlobalRegression(const vector<Mat_<int> >& lbf, const Mat_<double>& shape_residual) {
Config& c = Config::GetInstance();
const int landmark_n = c.landmark_n;
const int n = lbf.size();
const int m = K; // true size of local binary feature
const int f = m*carts[0].leafNum; // full size of local binary feature
vector<int> idx;
// prepare linear regression X, Y
struct feature_node** X = (struct feature_node**)malloc(n*sizeof(struct feature_node*));
double** Y = (double**)malloc(2 * landmark_n*sizeof(double*));
for (int i = 0; i < n; i++) {
X[i] = (struct feature_node*)malloc((m + 1)*sizeof(struct feature_node));
for (int j = 0; j < m; j++) {
X[i][j].index = lbf[i](0, j) + 1; // index starts from 1
X[i][j].value = 1.;
}
X[i][m].index = -1;
X[i][m].value = -1.;
}
for (int i = 0; i < landmark_n; i++) {
Y[2 * i] = (double*)malloc(n*sizeof(double));
Y[2 * i + 1] = (double*)malloc(n*sizeof(double));
for (int j = 0; j < n; j++) {
Y[2 * i][j] = shape_residual(j, 2 * i);
Y[2 * i + 1][j] = shape_residual(j, 2 * i + 1);
}
}
// train every landmark
struct problem prob;
struct parameter param;
prob.l = n;
prob.n = f;
prob.x = X;
prob.bias = -1;
param.solver_type = L2R_L2LOSS_SVR_DUAL;
param.C = 1. / n;
param.p = 0;
param.eps = 0.0001;
#pragma omp parallel for
for (int i = 0; i < landmark_n; i++) {
struct problem prob_ = prob;
prob_.y = Y[2 * i];
check_parameter(&prob_, ¶m);
struct model *model = train(&prob_, ¶m);
for (int j = 0; j < f; j++) w(j, 2 * i) = get_decfun_coef(model, j + 1, 0);
freeModel(model);
prob_.y = Y[2 * i + 1];
check_parameter(&prob_, ¶m);
model = train(&prob_, ¶m);
for (int j = 0; j < f; j++) w(j, 2 * i + 1) = get_decfun_coef(model, j + 1, 0);
freeModel(model);
}
// free
for (int i = 0; i < n; i++) free(X[i]);
for (int i = 0; i < 2 * landmark_n; i++) free(Y[i]);
free(X);
free(Y);
}
int main(int argc, char *argv[])
{
return check_parameter(NULL);
}
int main(int argc, char **argv)
{
const char *error_msg;
parse_command_line(argc, argv); // also load data
error_msg = check_parameter(prob,¶m);
if(error_msg)
{
fprintf(stderr,"Error: %s\n",error_msg);
exit(1);
}
std::vector< std::pair<double, double> > test_errors(nb_runs);
std::vector< std::pair<double, double> > train_errors(nb_runs);
double trn_mean=0;
double tst_mean=0;
double mse_trn_mean=0;
double mse_tst_mean=0;
int *start = NULL;
// perform runs
for (int run=0; run<nb_runs; run++)
{
if ((trnsz>=prob->l) || (trnsz<=0))
{
fprintf(stderr,"\nRun %d (from 0 to %d)\n", run, prob->l-1);
//train
model_=train(prob, ¶m);
// test
test_errors[run]=do_predict(tprob, model_);
train_errors[run]=do_predict(prob, model_);
}
else
{
// select all the splits before optimizing
if(run == 0)
{
start = Malloc(int,nb_runs);
for (int run2=0; run2<nb_runs; run2++)
start[run2] = (rand() % (prob->l-trnsz));
}
// select examples
fprintf(stderr,"\nRun %d (from %d to %d)\n", run, start[run], start[run]+trnsz-1);
struct problem* subprob=extract_subprob(prob, start[run], trnsz);
//train
model_=train(subprob, ¶m);
// test
test_errors[run]=do_predict(tprob, model_);
train_errors[run]=do_predict(subprob, model_);
free(subprob->y);
free(subprob->x);
}
tst_mean+=test_errors[run].first;
printf("Test classification ERROR = %g\n",test_errors[run].first);
trn_mean+=train_errors[run].first;
printf("Train classification ERROR = %g\n",train_errors[run].first);
mse_tst_mean+=test_errors[run].second;
printf("Test normalized ACCURACY (ET requirement) = %g\n",test_errors[run].second);
mse_trn_mean+=train_errors[run].second;
printf("Train normalized ACCURACY (ET requirement) = %g\n",train_errors[run].second);
//destroy model
free_and_destroy_model(&model_);
destroy_param(¶m);
}