// return classification error and the normalized difference between predicted and true sentiment
std::pair<double, double> do_predict(const struct problem *test_prob, struct model* model_)
{
double acc = 0;
double clse=0;
int total = 0;
double *prob_estimates=NULL;
int *labels=NULL;
int nr_class=get_nr_class(model_);
if(flag_predict_probability)
{
if(!check_probability_model(model_))
{
fprintf(stderr, "probability output is only supported for logistic regression\n");
exit(1);
}
labels=(int *) malloc(nr_class*sizeof(int));
get_labels(model_,labels);
prob_estimates = (double *) malloc(nr_class*sizeof(double));
}
int l = test_prob->l;
int i = 0;
for(i=0; i<l; i++)
{
int predict_label = 0;
int target_label=test_prob->y[i];
feature_node *xi = test_prob->x[i];
if(flag_predict_probability)
{
int j;
predict_label = predict_probability(model_,xi,prob_estimates);
double predict_score=0;
for(j=0;j<model_->nr_class;j++)
predict_score+=prob_estimates[j]*labels[j];
//double acc_max= fabs(target_label-3)+2;
//acc+=(acc_max-sqrt((predict_score - target_label)*(predict_score - target_label)))/acc_max;
acc += (predict_score - target_label) * (predict_score - target_label);
if (predict_label!=target_label)
clse++;
}
else
{
predict_label = predict(model_,xi);
//double acc_max= fabs(target_label-3)+2;
//acc+=(acc_max-sqrt((predict_label - target_label)*(predict_label - target_label)))/acc_max;
acc += (predict_label - target_label) * (predict_label - target_label);
if (predict_label!=target_label)
clse++;
}
++total;
}
if(flag_predict_probability)
{
free(prob_estimates);
free(labels);
}
//printf("Error = %g%% (%d/%d)\n",(double) (total-correct)/total*100,total-correct,total);
return std::make_pair(clse/total,acc/total) ;
}
static PyObject *PyHdbscan_run(PyHdbscan *self, PyObject *args){
/// TODO: check for errors
PyObject *dataset;
double *dset = NULL;
if (! PyArg_ParseTuple(args, "O", &dataset)){
return NULL;
}
if (dataset) {
Py_INCREF(dataset);
self->rows = PyList_Size(dataset);
PyObject* row = PyList_GetItem(dataset, 0);
self->cols = PyList_Size(row);
dset = PyList_toArray(dataset, NULL, self->rows, self->cols);
self->labels = PyList_New(0);
Py_INCREF(self->labels);
Py_XDECREF(dataset);
if(!scan){
return NULL;
}
} else {
return NULL;
}
int err = hdbscan_run(scan, dset, self->rows, self->cols, TRUE);
get_labels(self, scan->clusterLabels);
free(dset);
return Py_BuildValue("i", err);
}
void do_predict(FILE *input, FILE *output)
{
std::vector<double> pred_values; //store decision values
std::vector<double> true_values; //store true values
int total = 0;
int nr_class = get_nr_class(model_);
int * labels = Malloc(int, nr_class);
get_labels(model_, labels);
double * prob_estimates = NULL;
int j, n;
int nr_feature = get_nr_feature(model_);
if(model_->bias >=0)
n = nr_feature+1;
else
n = nr_feature;
// not yet support multiclass
assert(nr_class==2);
//print out header...
if(output_option ==2) {
prob_estimates = Malloc(double, nr_class);
fprintf(output,"labels");
for(j=0;j<nr_class;j++)
fprintf(output," %d",labels[j]);
fprintf(output,"\n");
}
bool
edit_interface_rep::complete_try () {
tree st= subtree (et, path_up (tp));
if (is_compound (st)) return false;
string s= st->label, ss;
int end= last_item (tp);
array<string> a;
if (inside (LABEL) || inside (REFERENCE) || inside (PAGEREF)) {
if (end != N(s)) return false;
ss= copy (s);
tree t= get_labels ();
int i, n= N(t);
for (i=0; i<n; i++)
if (is_atomic (t[i]) && starts (t[i]->label, s))
a << string (t[i]->label (N(s), N(t[i]->label)));
}
else {
if ((end==0) || (!is_iso_alpha (s[end-1])) ||
((end!=N(s)) && is_iso_alpha (s[end]))) return false;
int start= end-1;
while ((start>0) && is_iso_alpha (s[start-1])) start--;
ss= s (start, end);
a= find_completions (drd, et, ss);
}
if (N(a) == 0) return false;
complete_start (ss, a);
return true;
}
void label_classifier(char *datacfg, char *filename, char *weightfile)
{
int i;
network *net = load_network(filename, weightfile, 0);
set_batch_network(net, 1);
srand(time(0));
list *options = read_data_cfg(datacfg);
char *label_list = option_find_str(options, "names", "data/labels.list");
char *test_list = option_find_str(options, "test", "data/train.list");
int classes = option_find_int(options, "classes", 2);
char **labels = get_labels(label_list);
list *plist = get_paths(test_list);
char **paths = (char **)list_to_array(plist);
int m = plist->size;
free_list(plist);
for(i = 0; i < m; ++i){
image im = load_image_color(paths[i], 0, 0);
image resized = resize_min(im, net->w);
image crop = crop_image(resized, (resized.w - net->w)/2, (resized.h - net->h)/2, net->w, net->h);
float *pred = network_predict(net, crop.data);
if(resized.data != im.data) free_image(resized);
free_image(im);
free_image(crop);
int ind = max_index(pred, classes);
printf("%s\n", labels[ind]);
}
}
void validate_imagenet(char *filename, char *weightfile)
{
int i = 0;
network net = parse_network_cfg(filename, 1);
if(weightfile){
load_weights(&net, weightfile);
}
srand(time(0));
char **labels = get_labels("data/inet.labels.list");
//list *plist = get_paths("data/inet.suppress.list");
list *plist = get_paths("data/inet.val.list");
char **paths = (char **)list_to_array(plist);
int m = plist->size;
free_list(plist);
clock_t time;
float avg_acc = 0;
float avg_top5 = 0;
int splits = 50;
int num = (i+1)*m/splits - i*m/splits;
data val, buffer;
load_args args = {0};
args.w = net.w;
args.h = net.h;
args.paths = paths;
args.classes = 1000;
args.n = num;
args.m = 0;
args.labels = labels;
args.d = &buffer;
args.type = CLASSIFICATION_DATA;
pthread_t load_thread = load_data_in_thread(args);
for(i = 1; i <= splits; ++i){
time=clock();
pthread_join(load_thread, 0);
val = buffer;
num = (i+1)*m/splits - i*m/splits;
char **part = paths+(i*m/splits);
if(i != splits){
args.paths = part;
load_thread = load_data_in_thread(args);
}
printf("Loaded: %d images in %lf seconds\n", val.X.rows, sec(clock()-time));
time=clock();
float *acc = network_accuracies(net, val, 5);
avg_acc += acc[0];
avg_top5 += acc[1];
printf("%d: top1: %f, top5: %f, %lf seconds, %d images\n", i, avg_acc/i, avg_top5/i, sec(clock()-time), val.X.rows);
free_data(val);
}
}
void validate_classifier_full(char *datacfg, char *filename, char *weightfile)
{
int i, j;
network net = parse_network_cfg(filename);
set_batch_network(&net, 1);
if(weightfile){
load_weights(&net, weightfile);
}
srand(time(0));
list *options = read_data_cfg(datacfg);
char *label_list = option_find_str(options, "labels", "data/labels.list");
char *valid_list = option_find_str(options, "valid", "data/train.list");
int classes = option_find_int(options, "classes", 2);
int topk = option_find_int(options, "top", 1);
char **labels = get_labels(label_list);
list *plist = get_paths(valid_list);
char **paths = (char **)list_to_array(plist);
int m = plist->size;
free_list(plist);
float avg_acc = 0;
float avg_topk = 0;
int *indexes = calloc(topk, sizeof(int));
int size = net.w;
for(i = 0; i < m; ++i){
int class = -1;
char *path = paths[i];
for(j = 0; j < classes; ++j){
if(strstr(path, labels[j])){
class = j;
break;
}
}
image im = load_image_color(paths[i], 0, 0);
image resized = resize_min(im, size);
resize_network(&net, resized.w, resized.h);
//show_image(im, "orig");
//show_image(crop, "cropped");
//cvWaitKey(0);
float *pred = network_predict(net, resized.data);
if(net.hierarchy) hierarchy_predictions(pred, net.outputs, net.hierarchy, 1, 1);
free_image(im);
free_image(resized);
top_k(pred, classes, topk, indexes);
if(indexes[0] == class) avg_acc += 1;
for(j = 0; j < topk; ++j){
if(indexes[j] == class) avg_topk += 1;
}
printf("%d: top 1: %f, top %d: %f\n", i, avg_acc/(i+1), topk, avg_topk/(i+1));
}
}
void test_detector(char *datacfg, char *cfgfile, char *weightfile, char *filename, float thresh, float hier_thresh)
{
int show_flag = 1;
list *options = read_data_cfg(datacfg);
char *name_list = option_find_str(options, "names", "data/names.list");
char **names = get_labels(name_list);
image **alphabet = load_alphabet();
network net = parse_network_cfg(cfgfile);
if(weightfile){
load_weights(&net, weightfile);
}
set_batch_network(&net, 1);
srand(2222222);
clock_t time;
char buff[256];
char *input = buff;
int j;
float nms=.4;
while(1){
if(filename){
strncpy(input, filename, 256);
} else {
printf("Enter Image Path: ");
fflush(stdout);
input = fgets(input, 256, stdin);
if(!input) return;
strtok(input, "\n");
}
image im = load_image_color(input,0,0);
image sized = resize_image(im, net.w, net.h);
layer l = net.layers[net.n-1];
box *boxes = calloc(l.w*l.h*l.n, sizeof(box));
float **probs = calloc(l.w*l.h*l.n, sizeof(float *));
for(j = 0; j < l.w*l.h*l.n; ++j) probs[j] = calloc(l.classes + 1, sizeof(float *));
float *X = sized.data;
time=clock();
network_predict(net, X);
printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
get_region_boxes(l, 1, 1, thresh, probs, boxes, 0, 0, hier_thresh);
if (l.softmax_tree && nms) do_nms_obj(boxes, probs, l.w*l.h*l.n, l.classes, nms);
else if (nms) do_nms_sort(boxes, probs, l.w*l.h*l.n, l.classes, nms);
draw_detections(im, l.w*l.h*l.n, thresh, boxes, probs, names, alphabet, l.classes, show_flag);
save_image(im, "predictions");
show_image(im, "predictions");
free_image(im);
free_image(sized);
free(boxes);
free_ptrs((void **)probs, l.w*l.h*l.n);
#ifdef OPENCV
cvWaitKey(0);
cvDestroyAllWindows();
#endif
if (filename) break;
}
}
void train_cifar_distill(char *cfgfile, char *weightfile)
{
srand(time(0));
float avg_loss = -1;
char *base = basecfg(cfgfile);
printf("%s\n", base);
network net = parse_network_cfg(cfgfile);
if(weightfile){
load_weights(&net, weightfile);
}
printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
char *backup_directory = "/home/pjreddie/backup/";
int classes = 10;
int N = 50000;
char **labels = get_labels("data/cifar/labels.txt");
int epoch = (*net.seen)/N;
data train = load_all_cifar10();
matrix soft = csv_to_matrix("results/ensemble.csv");
float weight = .9;
scale_matrix(soft, weight);
scale_matrix(train.y, 1. - weight);
matrix_add_matrix(soft, train.y);
while(get_current_batch(net) < net.max_batches || net.max_batches == 0){
clock_t time=clock();
float loss = train_network_sgd(net, train, 1);
if(avg_loss == -1) avg_loss = loss;
avg_loss = avg_loss*.95 + loss*.05;
printf("%d, %.3f: %f, %f avg, %f rate, %lf seconds, %d images\n", get_current_batch(net), (float)(*net.seen)/N, loss, avg_loss, get_current_rate(net), sec(clock()-time), *net.seen);
if(*net.seen/N > epoch){
epoch = *net.seen/N;
char buff[256];
sprintf(buff, "%s/%s_%d.weights",backup_directory,base, epoch);
save_weights(net, buff);
}
if(get_current_batch(net)%100 == 0){
char buff[256];
sprintf(buff, "%s/%s.backup",backup_directory,base);
save_weights(net, buff);
}
}
char buff[256];
sprintf(buff, "%s/%s.weights", backup_directory, base);
save_weights(net, buff);
free_network(net);
free_ptrs((void**)labels, classes);
free(base);
free_data(train);
}
void train_imagenet(char *cfgfile, char *weightfile)
{
data_seed = time(0);
srand(time(0));
float avg_loss = -1;
char *base = basecfg(cfgfile);
printf("%s\n", base);
network net = parse_network_cfg(cfgfile);
if(weightfile){
load_weights(&net, weightfile);
}
printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
//net.seen=0;
int imgs = 1024;
int i = net.seen/imgs;
char **labels = get_labels("data/inet.labels.list");
list *plist = get_paths("/data/imagenet/cls.train.list");
char **paths = (char **)list_to_array(plist);
printf("%d\n", plist->size);
clock_t time;
pthread_t load_thread;
data train;
data buffer;
load_thread = load_data_thread(paths, imgs, plist->size, labels, 1000, 256, 256, &buffer);
while(1){
++i;
time=clock();
pthread_join(load_thread, 0);
train = buffer;
/*
image im = float_to_image(256, 256, 3, train.X.vals[114]);
show_image(im, "training");
cvWaitKey(0);
*/
load_thread = load_data_thread(paths, imgs, plist->size, labels, 1000, 256, 256, &buffer);
printf("Loaded: %lf seconds\n", sec(clock()-time));
time=clock();
float loss = train_network(net, train);
net.seen += imgs;
if(avg_loss == -1) avg_loss = loss;
avg_loss = avg_loss*.9 + loss*.1;
printf("%d: %f, %f avg, %lf seconds, %d images\n", i, loss, avg_loss, sec(clock()-time), net.seen);
free_data(train);
if((i % 20000) == 0) net.learning_rate *= .1;
//if(i%100 == 0 && net.learning_rate > .00001) net.learning_rate *= .97;
if(i%1000==0){
char buff[256];
sprintf(buff, "/home/pjreddie/imagenet_backup/%s_%d.weights",base, i);
save_weights(net, buff);
}
}
}
void predict_classifier(char *datacfg, char *cfgfile, char *weightfile, char *filename, int top)
{
network net = parse_network_cfg(cfgfile);
if(weightfile){
load_weights(&net, weightfile);
}
set_batch_network(&net, 1);
srand(2222222);
list *options = read_data_cfg(datacfg);
char *name_list = option_find_str(options, "names", 0);
if(!name_list) name_list = option_find_str(options, "labels", "data/labels.list");
if(top == 0) top = option_find_int(options, "top", 1);
int i = 0;
char **names = get_labels(name_list);
clock_t time;
int *indexes = calloc(top, sizeof(int));
char buff[256];
char *input = buff;
while(1){
if(filename){
strncpy(input, filename, 256);
}else{
printf("Enter Image Path: ");
fflush(stdout);
input = fgets(input, 256, stdin);
if(!input) return;
strtok(input, "\n");
}
image im = load_image_color(input, 0, 0);
image r = letterbox_image(im, net.w, net.h);
//resize_network(&net, r.w, r.h);
//printf("%d %d\n", r.w, r.h);
float *X = r.data;
time=clock();
float *predictions = network_predict(net, X);
if(net.hierarchy) hierarchy_predictions(predictions, net.outputs, net.hierarchy, 1, 1);
top_k(predictions, net.outputs, top, indexes);
fprintf(stderr, "%s: Predicted in %f seconds.\n", input, sec(clock()-time));
for(i = 0; i < top; ++i){
int index = indexes[i];
//if(net.hierarchy) printf("%d, %s: %f, parent: %s \n",index, names[index], predictions[index], (net.hierarchy->parent[index] >= 0) ? names[net.hierarchy->parent[index]] : "Root");
//else printf("%s: %f\n",names[index], predictions[index]);
printf("%5.2f%%: %s\n", predictions[index]*100, names[index]);
}
if(r.data != im.data) free_image(r);
free_image(im);
if (filename) break;
}
}
void predict_classifier(char *datacfg, char *cfgfile, char *weightfile, char *filename)
{
network net = parse_network_cfg(cfgfile);
if(weightfile){
load_weights(&net, weightfile);
}
set_batch_network(&net, 1);
srand(2222222);
list *options = read_data_cfg(datacfg);
char *name_list = option_find_str(options, "names", 0);
if(!name_list) name_list = option_find_str(options, "labels", "data/labels.list");
int top = option_find_int(options, "top", 1);
int i = 0;
char **names = get_labels(name_list);
clock_t time;
int *indexes = calloc(top, sizeof(int));
char buff[256];
char *input = buff;
int size = net.w;
while(1){
if(filename){
strncpy(input, filename, 256);
}else{
printf("Enter Image Path: ");
fflush(stdout);
input = fgets(input, 256, stdin);
if(!input) return;
strtok(input, "\n");
}
image im = load_image_color(input, 0, 0);
image r = resize_min(im, size);
resize_network(&net, r.w, r.h);
printf("%d %d\n", r.w, r.h);
float *X = r.data;
time=clock();
float *predictions = network_predict(net, X);
top_predictions(net, top, indexes);
printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
for(i = 0; i < top; ++i){
int index = indexes[i];
printf("%s: %f\n", names[index], predictions[index]);
}
if(r.data != im.data) free_image(r);
free_image(im);
if (filename) break;
}
}
void boogie_proof::pp_proof(std::ostream& out) {
vector<step> steps;
ptr_vector<proof> rules;
rules.push_back(m_proof);
steps.push_back(step());
obj_map<proof, unsigned> index;
index.insert(m_proof, 0);
for (unsigned j = 0; j < rules.size(); ++j) {
proof* p = rules[j];
proof_ref_vector premises(m);
expr_ref conclusion(m);
svector<std::pair<unsigned, unsigned> > positions;
vector<expr_ref_vector> substs;
expr* tmp;
steps[j].m_fact = m.get_fact(p);
m.is_implies(steps[j].m_fact, tmp, steps[j].m_fact);
get_subst(p, steps[j].m_subst);
get_labels(p, steps[j].m_labels);
if (m.is_hyper_resolve(p, premises, conclusion, positions, substs)) {
for (unsigned i = 1; i < premises.size(); ++i) {
proof* premise = premises[i].get();
unsigned position = 0;
if (!index.find(premise, position)) {
position = rules.size();
rules.push_back(premise);
steps.push_back(step());
index.insert(premise, position);
}
steps[j].m_refs.push_back(position);
}
get_rule_name(premises[0].get(), steps[j].m_rule_name);
}
}
for (unsigned j = steps.size(); j > 0; ) {
--j;
step &s = steps[j];
// TBD
// s.m_labels;
// set references, compensate for reverse ordering.
for (unsigned i = 0; i < s.m_refs.size(); ++i) {
s.m_refs[i] = rules.size()-1-s.m_refs[i];
}
}
steps.reverse();
pp_steps(out, steps);
}
void run_detector(int argc, char **argv)
{
char *prefix = find_char_arg(argc, argv, "-prefix", 0);
float thresh = find_float_arg(argc, argv, "-thresh", .24);
int cam_index = find_int_arg(argc, argv, "-c", 0);
int frame_skip = find_int_arg(argc, argv, "-s", 0);
if(argc < 4){
fprintf(stderr, "usage: %s %s [train/test/valid] [cfg] [weights (optional)]\n", argv[0], argv[1]);
return;
}
char *gpu_list = find_char_arg(argc, argv, "-gpus", 0);
int *gpus = 0;
int gpu = 0;
int ngpus = 0;
if(gpu_list){
printf("%s\n", gpu_list);
int len = strlen(gpu_list);
ngpus = 1;
int i;
for(i = 0; i < len; ++i){
if (gpu_list[i] == ',') ++ngpus;
}
gpus = calloc(ngpus, sizeof(int));
for(i = 0; i < ngpus; ++i){
gpus[i] = atoi(gpu_list);
gpu_list = strchr(gpu_list, ',')+1;
}
} else {
gpu = gpu_index;
gpus = &gpu;
ngpus = 1;
}
int clear = find_arg(argc, argv, "-clear");
char *datacfg = argv[3];
char *cfg = argv[4];
char *weights = (argc > 5) ? argv[5] : 0;
char *filename = (argc > 6) ? argv[6]: 0;
if(0==strcmp(argv[2], "test")) test_detector(datacfg, cfg, weights, filename, thresh);
else if(0==strcmp(argv[2], "train")) train_detector(datacfg, cfg, weights, gpus, ngpus, clear);
else if(0==strcmp(argv[2], "valid")) validate_detector(datacfg, cfg, weights);
else if(0==strcmp(argv[2], "recall")) validate_detector_recall(cfg, weights);
else if(0==strcmp(argv[2], "demo")) {
list *options = read_data_cfg(datacfg);
int classes = option_find_int(options, "classes", 20);
char *name_list = option_find_str(options, "names", "data/names.list");
char **names = get_labels(name_list);
demo(cfg, weights, thresh, cam_index, filename, names, classes, frame_skip, prefix);
}
}
void ofxDarknet::init( std::string cfgfile, std::string weightfile, std::string nameslist )
{
if (nameslist != "") {
labelsAvailable = true;
}
net = parse_network_cfg( cfgfile.c_str() );
load_weights( &net, weightfile.c_str() );
set_batch_network( &net, 1 );
if (!nameslist.empty()){
names = get_labels( (char *) nameslist.c_str() );
}
// load layer names
int numLayerTypes = 24;
int * counts = new int[ numLayerTypes ];
for (int i=0; i<numLayerTypes; i++) {counts[i] = 0;}
for (int i=0; i<net.n; i++) {
LAYER_TYPE type = net.layers[i].type;
string layerName = "Unknown";
if (type == CONVOLUTIONAL) layerName = "Conv";
else if (type == DECONVOLUTIONAL) layerName = "Deconv";
else if (type == CONNECTED) layerName = "FC";
else if (type == MAXPOOL) layerName = "MaxPool";
else if (type == SOFTMAX) layerName = "Softmax";
else if (type == DETECTION) layerName = "Detect";
else if (type == DROPOUT) layerName = "Dropout";
else if (type == CROP) layerName = "Crop";
else if (type == ROUTE) layerName = "Route";
else if (type == COST) layerName = "Cost";
else if (type == NORMALIZATION) layerName = "Normalize";
else if (type == AVGPOOL) layerName = "AvgPool";
else if (type == LOCAL) layerName = "Local";
else if (type == SHORTCUT) layerName = "Shortcut";
else if (type == ACTIVE) layerName = "Active";
else if (type == RNN) layerName = "RNN";
else if (type == GRU) layerName = "GRU";
else if (type == CRNN) layerName = "CRNN";
else if (type == BATCHNORM) layerName = "Batchnorm";
else if (type == NETWORK) layerName = "Network";
else if (type == XNOR) layerName = "XNOR";
else if (type == REGION) layerName = "Region";
else if (type == REORG) layerName = "Reorg";
else if (type == BLANK) layerName = "Blank";
layerNames.push_back(layerName+" "+ofToString(counts[type]));
counts[type] += 1;
}
delete counts;
loaded = true;
}
int test_get_labels()
{
const char *test_name = "test_get_labels";
struct rooted_tree tree = tree_7(); /* ((A:1,:1.0)f:2.0,(C:1,(D:1,E:1):2)h:3)i; */
struct llist *labels = get_labels(&tree);
struct list_elem *el = labels->head;
if (strcmp("A", (char *) el->data) != 0) {
printf ("%s: expected label 'A', got '%s'.\n", test_name, (char *) el->data);
return 1;
}
el = el->next;
if (strcmp("f", (char *) el->data) != 0) {
printf ("%s: expected label 'f', got '%s'.\n", test_name, (char *) el->data);
return 1;
}
el = el->next;
if (strcmp("C", (char *) el->data) != 0) {
printf ("%s: expected label 'C', got '%s'.\n", test_name, (char *) el->data);
return 1;
}
el = el->next;
if (strcmp("D", (char *) el->data) != 0) {
printf ("%s: expected label 'D', got '%s'.\n", test_name, (char *) el->data);
return 1;
}
el = el->next;
if (strcmp("E", (char *) el->data) != 0) {
printf ("%s: expected label 'E', got '%s'.\n", test_name, (char *) el->data);
return 1;
}
el = el->next;
if (strcmp("h", (char *) el->data) != 0) {
printf ("%s: expected label 'h', got '%s'.\n", test_name, (char *) el->data);
return 1;
}
el = el->next;
if (strcmp("i", (char *) el->data) != 0) {
printf ("%s: expected label 'i', got '%s'.\n", test_name, (char *) el->data);
return 1;
}
el = el->next;
if (NULL != el) {
printf ("%s: expected end of list.\n", test_name);
return 1;
}
printf ("%s: ok.\n", test_name);
return 0;
}
void demo_regressor(char *datacfg, char *cfgfile, char *weightfile, int cam_index, const char *filename)
{
#ifdef OPENCV
printf("Regressor Demo\n");
network *net = load_network(cfgfile, weightfile, 0);
set_batch_network(net, 1);
srand(2222222);
list *options = read_data_cfg(datacfg);
int classes = option_find_int(options, "classes", 1);
char *name_list = option_find_str(options, "names", 0);
char **names = get_labels(name_list);
void * cap = open_video_stream(filename, cam_index, 0,0,0);
if(!cap) error("Couldn't connect to webcam.\n");
float fps = 0;
while(1){
struct timeval tval_before, tval_after, tval_result;
gettimeofday(&tval_before, NULL);
image in = get_image_from_stream(cap);
image crop = center_crop_image(in, net->w, net->h);
grayscale_image_3c(crop);
float *predictions = network_predict(net, crop.data);
printf("\033[2J");
printf("\033[1;1H");
printf("\nFPS:%.0f\n",fps);
int i;
for(i = 0; i < classes; ++i){
printf("%s: %f\n", names[i], predictions[i]);
}
show_image(crop, "Regressor", 10);
free_image(in);
free_image(crop);
gettimeofday(&tval_after, NULL);
timersub(&tval_after, &tval_before, &tval_result);
float curr = 1000000.f/((long int)tval_result.tv_usec);
fps = .9*fps + .1*curr;
}
free_network(net);
#endif
}
metadata get_metadata(char *file)
{
metadata m = {0};
list *options = read_data_cfg(file);
char *name_list = option_find_str(options, "names", 0);
if(!name_list) name_list = option_find_str(options, "labels", 0);
if(!name_list) {
fprintf(stderr, "No names or labels found\n");
} else {
m.names = get_labels(name_list);
}
m.classes = option_find_int(options, "classes", 2);
free_list(options);
return m;
}
static PyObject *PyHdbscan_rerun(PyHdbscan *self, PyObject *args){
Py_XDECREF(self->labels);
if (!PyArg_ParseTuple(args, "i", &self->minPoints))
return NULL;
if(self->minPoints < 3){
return NULL;
}
int err = hdbscan_rerun(scan, self->minPoints);
self->labels = PyList_New(0);
Py_INCREF(self->labels);
get_labels(self, scan->clusterLabels);
return Py_BuildValue("i", err);
}
void test_tag(char *cfgfile, char *weightfile, char *filename)
{
network net = parse_network_cfg(cfgfile);
if(weightfile){
load_weights(&net, weightfile);
}
set_batch_network(&net, 1);
srand(2222222);
int i = 0;
char **names = get_labels("data/tags.txt");
clock_t time;
int indexes[10];
char buff[256];
char *input = buff;
int size = net.w;
while(1){
if(filename){
strncpy(input, filename, 256);
}else{
printf("Enter Image Path: ");
fflush(stdout);
input = fgets(input, 256, stdin);
if(!input) return;
strtok(input, "\n");
}
image im = load_image_color(input, 0, 0);
image r = resize_min(im, size);
resize_network(&net, r.w, r.h);
printf("%d %d\n", r.w, r.h);
float *X = r.data;
time=clock();
float *predictions = network_predict(net, X);
top_predictions(net, 10, indexes);
printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
for(i = 0; i < 10; ++i){
int index = indexes[i];
printf("%.1f%%: %s\n", predictions[index]*100, names[index]);
}
if(r.data != im.data) free_image(r);
free_image(im);
if (filename) break;
}
}
void validate_imagenet(char *filename, char *weightfile)
{
int i = 0;
network net = parse_network_cfg(filename);
if(weightfile){
load_weights(&net, weightfile);
}
srand(time(0));
char **labels = get_labels("data/inet.labels.list");
list *plist = get_paths("data/inet.val.list");
char **paths = (char **)list_to_array(plist);
int m = plist->size;
free_list(plist);
clock_t time;
float avg_acc = 0;
float avg_top5 = 0;
int splits = 50;
int num = (i+1)*m/splits - i*m/splits;
data val, buffer;
pthread_t load_thread = load_data_thread(paths, num, 0, labels, 1000, 256, 256, &buffer);
for(i = 1; i <= splits; ++i){
time=clock();
pthread_join(load_thread, 0);
val = buffer;
num = (i+1)*m/splits - i*m/splits;
char **part = paths+(i*m/splits);
if(i != splits) load_thread = load_data_thread(part, num, 0, labels, 1000, 256, 256, &buffer);
printf("Loaded: %d images in %lf seconds\n", val.X.rows, sec(clock()-time));
time=clock();
float *acc = network_accuracies(net, val);
avg_acc += acc[0];
avg_top5 += acc[1];
printf("%d: top1: %f, top5: %f, %lf seconds, %d images\n", i, avg_acc/i, avg_top5/i, sec(clock()-time), val.X.rows);
free_data(val);
}
}
void valid_captcha(char *cfgfile, char *weightfile, char *filename)
{
char **labels = get_labels("/data/captcha/reimgs.labels.list");
network net = parse_network_cfg(cfgfile);
if(weightfile){
load_weights(&net, weightfile);
}
list *plist = get_paths("/data/captcha/reimgs.fg.list");
char **paths = (char **)list_to_array(plist);
int N = plist->size;
int outputs = net.outputs;
set_batch_network(&net, 1);
srand(2222222);
int i, j;
for(i = 0; i < N; ++i){
if (i%100 == 0) fprintf(stderr, "%d\n", i);
image im = load_image_color(paths[i], net.w, net.h);
float *X = im.data;
float *predictions = network_predict(net, X);
//printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
int truth = -1;
for(j = 0; j < 13; ++j){
if (strstr(paths[i], labels[j])) truth = j;
}
if (truth == -1){
fprintf(stderr, "bad: %s\n", paths[i]);
return;
}
printf("%d, ", truth);
for(j = 0; j < outputs; ++j){
if (j != 0) printf(", ");
printf("%f", predictions[j]);
}
printf("\n");
fflush(stdout);
free_image(im);
if (filename) break;
}
}
void test_captcha(char *cfgfile, char *weightfile, char *filename)
{
network net = parse_network_cfg(cfgfile);
if(weightfile){
load_weights(&net, weightfile);
}
set_batch_network(&net, 1);
srand(2222222);
int i = 0;
char **names = get_labels("/data/captcha/reimgs.labels.list");
char buff[256];
char *input = buff;
int indexes[26];
while(1){
if(filename){
strncpy(input, filename, 256);
}else{
//printf("Enter Image Path: ");
//fflush(stdout);
input = fgets(input, 256, stdin);
if(!input) return;
strtok(input, "\n");
}
image im = load_image_color(input, net.w, net.h);
float *X = im.data;
float *predictions = network_predict(net, X);
top_predictions(net, 26, indexes);
//printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
for(i = 0; i < 26; ++i){
int index = indexes[i];
if(i != 0) printf(", ");
printf("%s %f", names[index], predictions[index]);
}
printf("\n");
fflush(stdout);
free_image(im);
if (filename) break;
}
}
void test_imagenet(char *cfgfile, char *weightfile, char *filename)
{
network net = parse_network_cfg(cfgfile, 1);
if(weightfile){
load_weights(&net, weightfile);
}
set_batch_network(&net, 1);
srand(2222222);
int i = 0;
char **names = get_labels("data/shortnames.txt");
clock_t time;
int indexes[10];
char buff[256];
char *input = buff;
while(1){
if(filename){
strncpy(input, filename, 256);
}else{
printf("Enter Image Path: ");
fflush(stdout);
input = fgets(input, 256, stdin);
if(!input) return;
strtok(input, "\n");
}
image im = load_image_color(input, 256, 256);
float *X = im.data;
time=clock();
float *predictions = network_predict(net, X);
top_predictions(net, 10, indexes);
printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
for(i = 0; i < 10; ++i){
int index = indexes[i];
printf("%s: %f\n", names[index], predictions[index]);
}
free_image(im);
if (filename) break;
}
}
void do_predict(FILE *input, FILE *output)
{
int correct = 0;
int total = 0;
double error = 0;
double sump = 0, sumt = 0, sumpp = 0, sumtt = 0, sumpt = 0;
int nr_class=get_nr_class(model_);
double *prob_estimates=NULL;
int j, n;
int nr_feature=get_nr_feature(model_);
if(model_->bias>=0)
n=nr_feature+1;
else
n=nr_feature;
if(flag_predict_probability)
{
int *labels;
if(!check_probability_model(model_))
{
fprintf(stderr, "probability output is only supported for logistic regression\n");
exit(1);
}
labels=(int *) malloc(nr_class*sizeof(int));
get_labels(model_,labels);
prob_estimates = (double *) malloc(nr_class*sizeof(double));
fprintf(output,"labels");
for(j=0;j<nr_class;j++)
fprintf(output," %d",labels[j]);
fprintf(output,"\n");
free(labels);
}
max_line_len = 1024;
line = (char *)malloc(max_line_len*sizeof(char));
while(readline(input) != NULL)
{
int i = 0;
double target_label, predict_label;
char *idx, *val, *label, *endptr;
int inst_max_index = 0; // strtol gives 0 if wrong format
label = strtok(line," \t\n");
if(label == NULL) // empty line
exit_input_error(total+1);
target_label = strtod(label,&endptr);
if(endptr == label || *endptr != '\0')
exit_input_error(total+1);
while(1)
{
if(i>=max_nr_attr-2) // need one more for index = -1
{
max_nr_attr *= 2;
x = (struct feature_node *) realloc(x,max_nr_attr*sizeof(struct feature_node));
}
idx = strtok(NULL,":");
val = strtok(NULL," \t");
if(val == NULL)
break;
errno = 0;
x[i].index = (int) strtol(idx,&endptr,10);
if(endptr == idx || errno != 0 || *endptr != '\0' || x[i].index <= inst_max_index)
exit_input_error(total+1);
else
inst_max_index = x[i].index;
errno = 0;
x[i].value = strtod(val,&endptr);
if(endptr == val || errno != 0 || (*endptr != '\0' && !isspace(*endptr)))
exit_input_error(total+1);
// feature indices larger than those in training are not used
if(x[i].index <= nr_feature)
++i;
}
if(model_->bias>=0)
{
x[i].index = n;
x[i].value = model_->bias;
i++;
}
x[i].index = -1;
if(model_->normal){
double length = 0;
for(int kk = 0; x[kk].index != -1; kk++)
length += x[kk].value * x[kk].value;
length = sqrt(length);
for(int kk = 0; x[kk].index != -1; kk++)
x[kk].value /= length;
}
if(flag_predict_probability)
{
int j;
predict_label = predict_probability(model_,x,prob_estimates);
fprintf(output,"%g",predict_label);
for(j=0;j<model_->nr_class;j++)
fprintf(output," %g",prob_estimates[j]);
fprintf(output,"\n");
}
else
{
predict_label = predict(model_,x);
fprintf(output,"%g\n",predict_label);
}
if(predict_label == target_label)
++correct;
error += (predict_label-target_label)*(predict_label-target_label);
sump += predict_label;
sumt += target_label;
sumpp += predict_label*predict_label;
sumtt += target_label*target_label;
sumpt += predict_label*target_label;
++total;
}
if(model_->param.solver_type==L2R_L2LOSS_SVR ||
model_->param.solver_type==L2R_L1LOSS_SVR_DUAL ||
model_->param.solver_type==L2R_L2LOSS_SVR_DUAL)
{
info("Mean squared error = %g (regression)\n",error/total);
info("Squared correlation coefficient = %g (regression)\n",
((total*sumpt-sump*sumt)*(total*sumpt-sump*sumt))/
((total*sumpp-sump*sump)*(total*sumtt-sumt*sumt))
);
}
else
info("Accuracy = %g%% (%d/%d)\n",(double) correct/total*100,correct,total);
if(flag_predict_probability)
free(prob_estimates);
}
void do_predict(FILE *input, FILE *output, struct model* model_)
{
int correct = 0;
int total = 0;
int nr_class=get_nr_class(model_);
double *prob_estimates=NULL;
int j, n;
int nr_feature=get_nr_feature(model_);
if(model_->bias>=0)
n=nr_feature+1;
else
n=nr_feature;
if(flag_predict_probability)
{
int *labels;
if(!check_probability_model(model_))
{
fprintf(stderr, "probability output is only supported for logistic regression\n");
exit(1);
}
labels=(int *) malloc(nr_class*sizeof(int));
get_labels(model_,labels);
prob_estimates = (double *) malloc(nr_class*sizeof(double));
fprintf(output,"labels");
for(j=0;j<nr_class;j++)
fprintf(output," %d",labels[j]);
fprintf(output,"\n");
free(labels);
}
max_line_len = 1024;
line = (char *)malloc(max_line_len*sizeof(char));
while(readline(input) != NULL)
{
int i = 0;
int target_label, predict_label;
char *idx, *val, *label, *endptr;
int inst_max_index = 0; // strtol gives 0 if wrong format
label = strtok(line," \t");
target_label = (int) strtol(label,&endptr,10);
if(endptr == label)
exit_input_error(total+1);
while(1)
{
if(i>=max_nr_attr-2) // need one more for index = -1
{
max_nr_attr *= 2;
x = (struct feature_node *) realloc(x,max_nr_attr*sizeof(struct feature_node));
}
idx = strtok(NULL,":");
val = strtok(NULL," \t");
if(val == NULL)
break;
errno = 0;
x[i].index = (int) strtol(idx,&endptr,10);
if(endptr == idx || errno != 0 || *endptr != '\0' || x[i].index <= inst_max_index)
exit_input_error(total+1);
else
inst_max_index = x[i].index;
errno = 0;
x[i].value = strtod(val,&endptr);
if(endptr == val || errno != 0 || (*endptr != '\0' && !isspace(*endptr)))
exit_input_error(total+1);
// feature indices larger than those in training are not used
if(x[i].index <= nr_feature)
++i;
}
if(model_->bias>=0)
{
x[i].index = n;
x[i].value = model_->bias;
i++;
}
x[i].index = -1;
if(flag_predict_probability)
{
int j;
predict_label = predict_probability(model_,x,prob_estimates);
fprintf(output,"%d",predict_label);
for(j=0;j<model_->nr_class;j++)
fprintf(output," %g",prob_estimates[j]);
fprintf(output,"\n");
}
else
{
predict_label = predict(model_,x);
fprintf(output,"%d\n",predict_label);
}
if(predict_label == target_label)
++correct;
++total;
}
printf("Accuracy = %g%% (%d/%d)\n",(double) correct/total*100,correct,total);
if(flag_predict_probability)
free(prob_estimates);
}
void validate_detector(char *datacfg, char *cfgfile, char *weightfile, char *outfile)
{
int j;
list *options = read_data_cfg(datacfg);
char *valid_images = option_find_str(options, "valid", "data/train.list");
char *name_list = option_find_str(options, "names", "data/names.list");
char *prefix = option_find_str(options, "results", "results");
char **names = get_labels(name_list);
char *mapf = option_find_str(options, "map", 0);
int *map = 0;
if (mapf) map = read_map(mapf);
network net = parse_network_cfg(cfgfile);
if(weightfile){
load_weights(&net, weightfile);
}
set_batch_network(&net, 1);
fprintf(stderr, "Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
srand(time(0));
list *plist = get_paths(valid_images);
char **paths = (char **)list_to_array(plist);
layer l = net.layers[net.n-1];
int classes = l.classes;
char buff[1024];
char *type = option_find_str(options, "eval", "voc");
FILE *fp = 0;
FILE **fps = 0;
int coco = 0;
int imagenet = 0;
if(0==strcmp(type, "coco")){
if(!outfile) outfile = "coco_results";
snprintf(buff, 1024, "%s/%s.json", prefix, outfile);
fp = fopen(buff, "w");
fprintf(fp, "[\n");
coco = 1;
} else if(0==strcmp(type, "imagenet")){
if(!outfile) outfile = "imagenet-detection";
snprintf(buff, 1024, "%s/%s.txt", prefix, outfile);
fp = fopen(buff, "w");
imagenet = 1;
classes = 200;
} else {
if(!outfile) outfile = "comp4_det_test_";
fps = calloc(classes, sizeof(FILE *));
for(j = 0; j < classes; ++j){
snprintf(buff, 1024, "%s/%s%s.txt", prefix, outfile, names[j]);
fps[j] = fopen(buff, "w");
}
}
box *boxes = calloc(l.w*l.h*l.n, sizeof(box));
float **probs = calloc(l.w*l.h*l.n, sizeof(float *));
for(j = 0; j < l.w*l.h*l.n; ++j) probs[j] = calloc(classes, sizeof(float *));
int m = plist->size;
int i=0;
int t;
float thresh = .005;
float nms = .45;
int nthreads = 4;
image *val = calloc(nthreads, sizeof(image));
image *val_resized = calloc(nthreads, sizeof(image));
image *buf = calloc(nthreads, sizeof(image));
image *buf_resized = calloc(nthreads, sizeof(image));
pthread_t *thr = calloc(nthreads, sizeof(pthread_t));
load_args args = {0};
args.w = net.w;
args.h = net.h;
args.type = IMAGE_DATA;
for(t = 0; t < nthreads; ++t){
args.path = paths[i+t];
args.im = &buf[t];
args.resized = &buf_resized[t];
thr[t] = load_data_in_thread(args);
}
time_t start = time(0);
for(i = nthreads; i < m+nthreads; i += nthreads){
fprintf(stderr, "%d\n", i);
for(t = 0; t < nthreads && i+t-nthreads < m; ++t){
pthread_join(thr[t], 0);
val[t] = buf[t];
val_resized[t] = buf_resized[t];
}
for(t = 0; t < nthreads && i+t < m; ++t){
args.path = paths[i+t];
args.im = &buf[t];
args.resized = &buf_resized[t];
thr[t] = load_data_in_thread(args);
}
for(t = 0; t < nthreads && i+t-nthreads < m; ++t){
char *path = paths[i+t-nthreads];
char *id = basecfg(path);
float *X = val_resized[t].data;
network_predict(net, X);
int w = val[t].w;
int h = val[t].h;
get_region_boxes(l, w, h, thresh, probs, boxes, 0, map, .5);
if (nms) do_nms_sort(boxes, probs, l.w*l.h*l.n, classes, nms);
if (coco){
print_cocos(fp, path, boxes, probs, l.w*l.h*l.n, classes, w, h);
} else if (imagenet){
print_imagenet_detections(fp, i+t-nthreads+1, boxes, probs, l.w*l.h*l.n, classes, w, h);
} else {
print_detector_detections(fps, id, boxes, probs, l.w*l.h*l.n, classes, w, h);
}
free(id);
free_image(val[t]);
free_image(val_resized[t]);
}
}
for(j = 0; j < classes; ++j){
if(fps) fclose(fps[j]);
}
if(coco){
fseek(fp, -2, SEEK_CUR);
fprintf(fp, "\n]\n");
fclose(fp);
}
fprintf(stderr, "Total Detection Time: %f Seconds\n", (double)(time(0) - start));
}
void *predictModelWholeGenome(void *arg) {
thread_data_t *data = (thread_data_t *) arg;
printf("data->trainedModel is %s\n", data->trainedModel);
printf("data->coverageFileList is %s\n", data->coverageFileList);
printf("data->trainFile %s\n", data->trainFile);
printf("data->paramFile %s\n", data->paramFile);
printf("data->chr is %d\n", data->chr);
char *trainedModel = data->trainedModel;
char *coverageFileList = data->coverageFileList;
// char *trainFile = data->trainFile;
char *paramFile = data->paramFile;
int chr = data->chr;
// utility var
int i,j,k;
// trainedModel
struct model *mymodel;
if( (mymodel = load_model(trainedModel)) == 0) {
printf("cannot load model from file %s\n", trainedModel);
return EXIT_SUCCESS;
}
// coverageFileList
int totalCoverageFiles;
FILE *coverageFileListFp = NULL;
if( (coverageFileListFp = fopen(coverageFileList, "r") ) == NULL) {
printf("Cannot open file %s\n", coverageFileList);
return EXIT_SUCCESS;
}
char **coverageFiles = (char **)calloc(MAX_BAM_FILES,sizeof(char *));
for(i = 0; i < MAX_BAM_FILES; i++) {
coverageFiles[i] = (char *)calloc(MAX_DIR_LEN, sizeof(char));
}
i = 0;
while (!feof(coverageFileListFp)) {
if (i >= MAX_BAM_FILES) {
printf("Error: the number of input coverages files exceeds the limit %d\n", i);
return EXIT_SUCCESS;
}
if( ( fscanf(coverageFileListFp, "%s\n", coverageFiles[i]) ) != 1) {
printf("Error: reading %dth from %s\n", i, coverageFileList);
return EXIT_SUCCESS;
}
i++;
}
totalCoverageFiles = i;
fclose(coverageFileListFp);
// open coverage Files
FILE *coverageFps[totalCoverageFiles];
for(i = 0; i < totalCoverageFiles; i++) {
if( (coverageFps[i] = fopen(coverageFiles[i], "rb")) == NULL ) {
printf("Error opening coverage file %s\n", coverageFiles[i]);
return EXIT_SUCCESS;
}
}
// paramFile
struct extractFeatureParam *param = (struct extractFeatureParam *)calloc(1, sizeof(struct extractFeatureParam));
parseParam(paramFile, param);
// predict model: by default: predict probability
int nr_class = get_nr_class(mymodel);
double *prob_estimates = (double *)calloc(nr_class, sizeof(double));
// predResult for storing results
int totalBins = 0;
int cumBins[NUM_SEQ];
for (i = 0; i < NUM_SEQ; i++) {
totalBins += (int)(chrlen[i] / param->resolution) + 1;
cumBins[i] = totalBins;
}
// allocate memory for result based on thread data chr
// as we are using one thread for each chr
float *predResult = (float *)calloc( (int)(chrlen[chr] / param->resolution) + 1, sizeof(float));
// read in feature for each bin and do prediction
for(j = 0; j < (int)(chrlen[chr] / param->resolution) + 1; j++) {
if(j % 100000 == 0) {
printf("Predicting chr%d:%dth bin\n", chr,j);
fflush(stdout);
}
int max_nr_feature = 100;
struct feature_node *myX = (struct feature_node *)calloc(max_nr_feature, sizeof(struct feature_node));
int idx = 0;
for(k = 0; k < totalCoverageFiles; k++) {
float *buffer = (float *)calloc( param->windowSize/param->resolution,sizeof(float));
int offset = j;
offset += -(int)((float)(param->windowSize / 2) / (float)param->resolution + 0.5);
if(offset < 0 || offset + (int)((float)(param->windowSize) / (float)param->resolution + 0.5) > (int)(chrlen[i] / param->resolution) + 1) {
// printf("offset is %d\n", offset);
free(buffer);
continue;
}
if(chr != 0) offset += cumBins[chr-1];
// printf("offset is %d\n", offset);
fseek(coverageFps[k], offset*sizeof(float), SEEK_SET);
fread(buffer, sizeof(float), param->windowSize/param->resolution, coverageFps[k]);
int l;
// printf("buffer[%d] is:",l);
for(l = 0; l < param->windowSize/param->resolution; l++) {
// if(j == 289540) printf("%f,",buffer[l]);
if(buffer[l] != 0) {
myX[idx].index = k*(param->windowSize/param->resolution) + l + 1;
myX[idx].value = buffer[l];
idx++;
}
if(idx >= max_nr_feature -2) { // feature_node is not long enough
max_nr_feature *= 2;
myX = (struct feature_node *)realloc(myX, max_nr_feature*sizeof(struct feature_node));
}
}
free(buffer);
} // end of loop through coverageFiles
// printf("\n");
myX[idx].index = -1; // a flag for end of features
if(idx == 0) {
// printf("idx is %d\n",idx);
predResult[j] = 0.0;
free(myX);
continue;
}
// printf("nr_feature is %d\n", idx);
predict_probability(mymodel, myX, prob_estimates);
// printf("num of feature is %d\n", get_nr_feature(mymodel));
// printf("num of class is %d\n", get_nr_class(mymodel));
int *mylabel = (int *)calloc(10, sizeof(int));
// added, in order to get the correct label
get_labels(mymodel, mylabel);
if(mylabel[0] == 1) {
predResult[j] = prob_estimates[0];
} else {
predResult[j] = prob_estimates[1];
}
free(myX);
free(mylabel);
}
for(i = 0; i < totalCoverageFiles; i++) {
fclose(coverageFps[i]);
}
// free pointers
for(i = 0; i < MAX_BAM_FILES; i++) {
free(coverageFiles[i]);
}
free(coverageFiles);
free(param);
free(prob_estimates);
// give address of pointer to this function, so that the function can free the pointer.
free_and_destroy_model(&mymodel);
pthread_exit((void *) predResult);
}
void train_captcha(char *cfgfile, char *weightfile)
{
srand(time(0));
float avg_loss = -1;
char *base = basecfg(cfgfile);
printf("%s\n", base);
network net = parse_network_cfg(cfgfile);
if(weightfile){
load_weights(&net, weightfile);
}
printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
int imgs = 1024;
int i = *net.seen/imgs;
int solved = 1;
list *plist;
char **labels = get_labels("/data/captcha/reimgs.labels.list");
if (solved){
plist = get_paths("/data/captcha/reimgs.solved.list");
}else{
plist = get_paths("/data/captcha/reimgs.raw.list");
}
char **paths = (char **)list_to_array(plist);
printf("%d\n", plist->size);
clock_t time;
#if defined __linux__ || defined __APPLE__ || defined PTHREAD_WINDOWS
pthread_t load_thread;
#else
#endif
data train;
data buffer;
load_args args = {0};
args.w = net.w;
args.h = net.h;
args.paths = paths;
args.classes = 26;
args.n = imgs;
args.m = plist->size;
args.labels = labels;
args.d = &buffer;
args.type = CLASSIFICATION_DATA;
#if defined __linux__ || defined __APPLE__ || defined PTHREAD_WINDOWS
load_thread = load_data_in_thread(args);
#endif
while(1){
++i;
time=clock();
#if defined __linux__ || defined __APPLE__ || defined PTHREAD_WINDOWS
pthread_join(load_thread, 0);
#endif
train = buffer;
fix_data_captcha(train, solved);
/*
image im = float_to_image(256, 256, 3, train.X.vals[114]);
show_image(im, "training");
cvWaitKey(0);
*/
#if defined __linux__ || defined __APPLE__ || defined PTHREAD_WINDOWS
load_thread = load_data_in_thread(args);
#endif
printf("Loaded: %lf seconds\n", sec(clock()-time));
time=clock();
float loss = train_network(net, train);
if(avg_loss == -1) avg_loss = loss;
avg_loss = avg_loss*.9 + loss*.1;
printf("%d: %f, %f avg, %lf seconds, %d images\n", i, loss, avg_loss, sec(clock()-time), *net.seen);
free_data(train);
if(i%100==0){
char buff[256];
sprintf(buff, "/home/pjreddie/imagenet_backup/%s_%d.weights",base, i);
save_weights(net, buff);
}
}
}
void train_imagenet(char *cfgfile, char *weightfile)
{
data_seed = time(0);
srand(time(0));
float avg_loss = -1;
char *base = basecfg(cfgfile);
char *backup_directory = "/home/pjreddie/backup/";
printf("%s\n", base);
network net = parse_network_cfg(cfgfile, 1);
if(weightfile){
load_weights(&net, weightfile);
}
printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
int imgs = 1024;
char **labels = get_labels("data/inet.labels.list");
list *plist = get_paths("data/inet.train.list");
char **paths = (char **)list_to_array(plist);
printf("%d\n", plist->size);
int N = plist->size;
clock_t time;
pthread_t load_thread;
data train;
data buffer;
load_args args = {0};
args.w = net.w;
args.h = net.h;
args.paths = paths;
args.classes = 1000;
args.n = imgs;
args.m = N;
args.labels = labels;
args.d = &buffer;
args.type = CLASSIFICATION_DATA;
load_thread = load_data_in_thread(args);
int epoch = (*net.seen)/N;
while(get_current_batch(net) < net.max_batches || net.max_batches == 0){
time=clock();
pthread_join(load_thread, 0);
train = buffer;
load_thread = load_data_in_thread(args);
printf("Loaded: %lf seconds\n", sec(clock()-time));
time=clock();
float loss = train_network(net, train);
if(avg_loss == -1) avg_loss = loss;
avg_loss = avg_loss*.9 + loss*.1;
printf("%d, %.3f: %f, %f avg, %f rate, %lf seconds, %d images\n", get_current_batch(net), (float)(*net.seen)/N, loss, avg_loss, get_current_rate(net), sec(clock()-time), *net.seen);
free_data(train);
if(*net.seen/N > epoch){
epoch = *net.seen/N;
char buff[256];
sprintf(buff, "%s/%s_%d.weights",backup_directory,base, epoch);
save_weights(net, buff);
}
if(*net.seen%1000 == 0){
char buff[256];
sprintf(buff, "%s/%s.backup",backup_directory,base);
save_weights(net, buff);
}
}
char buff[256];
sprintf(buff, "%s/%s.weights", backup_directory, base);
save_weights(net, buff);
pthread_join(load_thread, 0);
free_data(buffer);
free_network(net);
free_ptrs((void**)labels, 1000);
free_ptrs((void**)paths, plist->size);
free_list(plist);
free(base);
}
