int main(int argc, char** argv){
if(argc<2){ throw ArgumentError(); }
const char* filename = argv[1];
list<Box> v = read_boxes(filename);
list<Tower> tows = get_best_towers(v);
Tower tallest = get_tallest(tows);
show_tower(tallest);
std::cout << "height = " << tower_height(tallest) << '\n';
return 0;
}
int main(int argc, char **argv)
{
char* input = argv[1];
int channels = 3;
list *plist = get_paths(input);
//int N = plist->size;
char **paths = (char **)list_to_array(plist);
int m = plist->size;
int count_label = 0;
char labelpath[256];
sprintf(labelpath, "../labels/01_5_1.txt");
int count = 0;
box_label *boxes = read_boxes(labelpath, &count);
for (int i = 0; i < m; i++)
{
if (!paths[i])
{
printf("load error!\n");
break;
}
image im = load_image(paths[i], 0, 0, channels);
printf("load %s", paths[i]);
float x, y, w, h;
count_label++;
x = boxes[i].x;
y = boxes[i].y;
w = boxes[i].w;
h = boxes[i].h;
box box = { x, y, w, h };
char *save_path1 = get_basename(paths[i]);
char save_path[256];
sprintf(save_path, "./images/%s", save_path1);
//show_image(im, save_path);
image crop_im = crop_image(im, x,y,w,h);
printf(" %f %f %f %f \n", x,y,w,h);
show_image(crop_im, save_path);
free_image(crop_im);
free_image(im);
}
}
void validate_detector_recall(char *cfgfile, char *weightfile)
{
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("data/voc.2007.test");
char **paths = (char **)list_to_array(plist);
layer l = net.layers[net.n-1];
int classes = l.classes;
int j, k;
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;
float thresh = .001;
float iou_thresh = .5;
float nms = .4;
int total = 0;
int correct = 0;
int proposals = 0;
float avg_iou = 0;
for(i = 0; i < m; ++i){
char *path = paths[i];
image orig = load_image_color(path, 0, 0);
image sized = resize_image(orig, net.w, net.h);
char *id = basecfg(path);
network_predict(net, sized.data);
get_region_boxes(l, 1, 1, thresh, probs, boxes, 1, 0, .5);
if (nms) do_nms(boxes, probs, l.w*l.h*l.n, 1, nms);
char labelpath[4096];
find_replace(path, "images", "labels", labelpath);
find_replace(labelpath, "JPEGImages", "labels", labelpath);
find_replace(labelpath, ".jpg", ".txt", labelpath);
find_replace(labelpath, ".JPEG", ".txt", labelpath);
int num_labels = 0;
box_label *truth = read_boxes(labelpath, &num_labels);
for(k = 0; k < l.w*l.h*l.n; ++k){
if(probs[k][0] > thresh){
++proposals;
}
}
for (j = 0; j < num_labels; ++j) {
++total;
box t = {truth[j].x, truth[j].y, truth[j].w, truth[j].h};
float best_iou = 0;
for(k = 0; k < l.w*l.h*l.n; ++k){
float iou = box_iou(boxes[k], t);
if(probs[k][0] > thresh && iou > best_iou){
best_iou = iou;
}
}
avg_iou += best_iou;
if(best_iou > iou_thresh){
++correct;
}
}
fprintf(stderr, "%5d %5d %5d\tRPs/Img: %.2f\tIOU: %.2f%%\tRecall:%.2f%%\n", i, correct, total, (float)proposals/(i+1), avg_iou*100/total, 100.*correct/total);
free(id);
free_image(orig);
free_image(sized);
}
}
void validate_yolo_classify(char *datacfg, char *cfgfile, char *weightfile)
{
list *options = read_data_cfg(datacfg);
//char *train_list = option_find_str(options, "train", "data/train_list.txt");
//char *test_list = option_find_str(options, "test", "data/test_list.txt");
char *valid_list = option_find_str(options, "valid", "data/valid_list.txt");
//char *backup_directory = option_find_str(options, "backup", "/backup/");
//char *label_list = option_find_str(options, "labels", "data/labels_list.txt");
//int classes = option_find_int(options, "classes", 2);
//char **labels = get_labels(label_list);
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));
char *base = "results/comp4_det_test_";
//list *plist = get_paths("data/voc.2007.test");
list *plist = get_paths(valid_list);
char **paths = (char **)list_to_array(plist);
layer l = net.layers[net.n-1];
int classes = l.classes;
int square = l.sqrt;
int side = l.side;
int j, k;
FILE **fps = calloc(classes, sizeof(FILE *));
for(j = 0; j < classes; ++j){
char buff[1024];
snprintf(buff, 1024, "%s%s.txt", base, voc_names[j]);
fps[j] = fopen(buff, "w");
}
box *boxes = calloc(side*side*l.n, sizeof(box));
float **probs = calloc(side*side*l.n, sizeof(float *));
for(j = 0; j < side*side*l.n; ++j) probs[j] = calloc(classes, sizeof(float *));
int m = plist->size;
int i=0;
//float thresh = .001;
float thresh = .2;
float iou_thresh = .5;
//float nms = 0;
float nms = 0.5;
int total = 0;
int correct = 0;
int class_correct = 0;
int proposals = 0;
float avg_iou = 0;
for(i = 0; i < m; ++i){
char *path = paths[i];
image orig = load_image_color(path, 0, 0);
image sized = resize_image(orig, net.w, net.h);
char *id = basecfg(path);
float *predictions = network_predict(net, sized.data);
convert_yolo_detections(predictions, classes, l.n, square, side, 1, 1, thresh, probs, boxes, 0);
//if (nms) do_nms(boxes, probs, side*side*l.n, 1, nms);
if (nms) do_nms(boxes, probs, side*side*l.n, classes, nms);
char *labelpath = find_replace(path, "images", "labels");
labelpath = find_replace(labelpath, "JPEGImages", "labels");
labelpath = find_replace(labelpath, ".jpg", ".txt");
labelpath = find_replace(labelpath, ".JPEG", ".txt");
labelpath = find_replace(labelpath, ".bmp", ".txt");
labelpath = find_replace(labelpath, ".dib", ".txt");
labelpath = find_replace(labelpath, ".jpe", ".txt");
labelpath = find_replace(labelpath, ".jp2", ".txt");
labelpath = find_replace(labelpath, ".png", ".txt");
labelpath = find_replace(labelpath, ".pbm", ".txt");
labelpath = find_replace(labelpath, ".pgm", ".txt");
labelpath = find_replace(labelpath, ".ppm", ".txt");
labelpath = find_replace(labelpath, ".sr", ".txt");
labelpath = find_replace(labelpath, ".ras", ".txt");
labelpath = find_replace(labelpath, ".tiff", ".txt");
labelpath = find_replace(labelpath, ".tif", ".txt");
int num_labels = 0;
box_label *truth = read_boxes(labelpath, &num_labels);
for(k = 0; k < side*side*l.n; ++k){
int class = max_index(probs[k], classes);
float prob = probs[k][class];
//fprintf(stderr, "path=%s\t\tk=%d\tprob=%f\tclass=%d\n", path, k, prob, class);
if(prob > thresh){
++proposals;
}
}
for (j = 0; j < num_labels; ++j) {
++total;
box t = {truth[j].x, truth[j].y, truth[j].w, truth[j].h};
float best_iou = 0;
int pre_class = -1;
for(k = 0; k < side*side*l.n; ++k){
float iou = box_iou(boxes[k], t);
int class = max_index(probs[k], classes);
float prob = probs[k][class];
//fprintf(stderr, "path=%s\t\tk=%d\tprob=%f\tclass=%d\n", path, k, prob, class);
if(prob > thresh && iou > best_iou){
best_iou = iou;
pre_class = class;
}
}
avg_iou += best_iou;
if(best_iou > iou_thresh){
++correct;
}
if(pre_class == truth[j].id){
++class_correct;
}
//fprintf(stderr, "true_class=%d\tpre_class=%d\n", truth[j].id, pre_class);
}
fprintf(stderr, "%5d %5d %5d\tRPs/Img: %.2f\tIOU: %.2f%%\tRecall:%.2f%%\t\tClassify:%.2f%%\n", i, correct, total, (float)proposals/(i+1), avg_iou*100/total, 100.*correct/total, 100.*class_correct/total);
free(id);
free_image(orig);
free_image(sized);
}
void validate_coco_recall(char *cfgfile, char *weightfile)
{
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));
char *base = "results/comp4_det_test_";
list *plist = get_paths("/home/pjreddie/data/voc/test/2007_test.txt");
char **paths = (char **)list_to_array(plist);
layer l = net.layers[net.n-1];
int classes = l.classes;
int square = l.sqrt;
int side = l.side;
int j, k;
FILE **fps = calloc(classes, sizeof(FILE *));
for(j = 0; j < classes; ++j){
char buff[1024];
_snprintf(buff, 1024, "%s%s.txt", base, coco_classes[j]);
fps[j] = fopen(buff, "w");
}
box *boxes = calloc(side*side*l.n, sizeof(box));
float **probs = calloc(side*side*l.n, sizeof(float *));
for(j = 0; j < side*side*l.n; ++j) probs[j] = calloc(classes, sizeof(float *));
int m = plist->size;
int i=0;
float thresh = .001;
int nms = 0;
float iou_thresh = .5;
float nms_thresh = .5;
int total = 0;
int correct = 0;
int proposals = 0;
float avg_iou = 0;
for(i = 0; i < m; ++i){
char *path = paths[i];
image orig = load_image_color(path, 0, 0);
image sized = resize_image(orig, net.w, net.h);
char *id = basecfg(path);
float *predictions = network_predict(net, sized.data);
convert_detections(predictions, classes, l.n, square, side, 1, 1, thresh, probs, boxes, 1);
if (nms) do_nms(boxes, probs, side*side*l.n, 1, nms_thresh);
char *labelpath = find_replace(path, "images", "labels");
labelpath = find_replace(labelpath, "JPEGImages", "labels");
labelpath = find_replace(labelpath, ".jpg", ".txt");
labelpath = find_replace(labelpath, ".JPEG", ".txt");
int num_labels = 0;
box_label *truth = read_boxes(labelpath, &num_labels);
for(k = 0; k < side*side*l.n; ++k){
if(probs[k][0] > thresh){
++proposals;
}
}
for (j = 0; j < num_labels; ++j) {
++total;
box t = {truth[j].x, truth[j].y, truth[j].w, truth[j].h};
float best_iou = 0;
for(k = 0; k < side*side*l.n; ++k){
float iou = box_iou(boxes[k], t);
if(probs[k][0] > thresh && iou > best_iou){
best_iou = iou;
}
}
avg_iou += best_iou;
if(best_iou > iou_thresh){
++correct;
}
}
fprintf(stderr, "%5d %5d %5d\tRPs/Img: %.2f\tIOU: %.2f%%\tRecall:%.2f%%\n", i, correct, total, (float)proposals/(i+1), avg_iou*100/total, 100.*correct/total);
free(id);
free_image(orig);
free_image(sized);
}
}
void validate_yolo_recall(char *cfg, char *weights)
{
network *net = load_network(cfg, weights, 0);
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));
char *base = "results/comp4_det_test_";
list *plist = get_paths("data/voc.2007.test");
char **paths = (char **)list_to_array(plist);
layer l = net->layers[net->n-1];
int classes = l.classes;
int side = l.side;
int j, k;
FILE **fps = calloc(classes, sizeof(FILE *));
for(j = 0; j < classes; ++j){
char buff[1024];
snprintf(buff, 1024, "%s%s.txt", base, voc_names[j]);
fps[j] = fopen(buff, "w");
}
int m = plist->size;
int i=0;
float thresh = .001;
float iou_thresh = .5;
float nms = 0;
int total = 0;
int correct = 0;
int proposals = 0;
float avg_iou = 0;
for(i = 0; i < m; ++i){
char *path = paths[i];
image orig = load_image_color(path, 0, 0);
image sized = resize_image(orig, net->w, net->h);
char *id = basecfg(path);
network_predict(net, sized.data);
int nboxes = 0;
detection *dets = get_network_boxes(net, orig.w, orig.h, thresh, 0, 0, 1, &nboxes);
if (nms) do_nms_obj(dets, side*side*l.n, 1, nms);
char labelpath[4096];
find_replace(path, "images", "labels", labelpath);
find_replace(labelpath, "JPEGImages", "labels", labelpath);
find_replace(labelpath, ".jpg", ".txt", labelpath);
find_replace(labelpath, ".JPEG", ".txt", labelpath);
int num_labels = 0;
box_label *truth = read_boxes(labelpath, &num_labels);
for(k = 0; k < side*side*l.n; ++k){
if(dets[k].objectness > thresh){
++proposals;
}
}
for (j = 0; j < num_labels; ++j) {
++total;
box t = {truth[j].x, truth[j].y, truth[j].w, truth[j].h};
float best_iou = 0;
for(k = 0; k < side*side*l.n; ++k){
float iou = box_iou(dets[k].bbox, t);
if(dets[k].objectness > thresh && iou > best_iou){
best_iou = iou;
}
}
avg_iou += best_iou;
if(best_iou > iou_thresh){
++correct;
}
}
fprintf(stderr, "%5d %5d %5d\tRPs/Img: %.2f\tIOU: %.2f%%\tRecall:%.2f%%\n", i, correct, total, (float)proposals/(i+1), avg_iou*100/total, 100.*correct/total);
free_detections(dets, nboxes);
free(id);
free_image(orig);
free_image(sized);
}
free_network( net );
}
int main(int argc, char *argv[])
{
std::string train_path;
std::string gt_path;
std::string output_file;
std::string output_patch_file;
int numbers = 0;
int start = 100;
int c;
std::vector<int> excludes(nexcludes);
excludes.assign(exclude_nums, exclude_nums + nexcludes);
while ((c = getopt(argc, argv, "i:g:n:s:e:o:p:h")) != -1) {
switch (c) {
case 'i':
train_path = optarg;
break;
case 'g':
gt_path = optarg;
break;
case 'n':
{
std::stringstream stream(optarg);
stream >> numbers;
}
break;
case 's':
{
std::stringstream stream(optarg);
stream >> start;
}
break;
case 'e':
excludes = spliti(std::string(optarg),',');
break;
case 'o':
output_file = optarg;
break;
case 'p':
output_patch_file = optarg;
break;
case 'h':
default:
std::cout << c << std::endl;
std::cerr << "Usage: extract_train_set OPTIONS" << std::endl
<< "\t -i <training directory>" << std::endl
<< "\t -g <gt box directory>" << std::endl
<< "\t -n <maximum id>" << std::endl
<< "\t -s <start id>" << std::endl
<< "\t -o <output path>" << std::endl
<< "\t -p <output patch file>" << std::endl
<< "\t -e <exclude list>" << std::endl;
return 1;
}
}
if (train_path == "" || gt_path == "") {
std::cerr << "Training path and gt path are mandatory" << std::endl;
return 1;
}
if (output_file == "") {
std::cerr << "output file is mandatory" << std::endl;
return 1;
}
srand(time(NULL));
std::ofstream ofs(output_file.c_str());
std::ofstream ofs_patch;
if (output_patch_file != "") {
ofs_patch.open(output_patch_file);
}
for (unsigned int i = start; i <= numbers; ++i) {
if (std::find(excludes.begin(), excludes.end(), i) != excludes.end()) continue;
std::cout << "Processing: " << i << std::endl;
std::string train_img;
std::string gt_box;
{
std::stringstream stream(train_path);
stream << train_path << "/" << i << ".jpg";
train_img = (stream.str());
}
{
std::stringstream stream(gt_path);
stream << gt_path << "/" << i << ".txt";
gt_box = (stream.str());
}
std::vector<cv::Rect> rects(read_boxes(gt_box));
cv::Mat img = cv::imread(train_img);
// first we extract the positive instances
for (unsigned int j = 0; j < rects.size(); ++j) {
extract_positive_samples(img, rects[j], ofs, ofs_patch);
}
std::cout << "Extracting random images" << std::endl;
// then we gonna extract negative samples
float size = img.rows;
cv::Mat scaledImage = img;
float scale = 1.0;
for (unsigned int j = 0; j < nscales; ++j) {
std::cout << "scale: " << size << std::endl;
if (scaledImage.rows > (int) size) {
float ratio = size / scaledImage.rows;
int h = (int) size;
int w = ratio * scaledImage.cols;
std::cout << w << " " << h << " " << ratio << std::endl;
cv::resize(img, scaledImage, cv::Size(w,h));
rects = scale_rects(rects, ratio);
scale = scale * ratio;
}
if (scaledImage.rows < window_height || scaledImage.cols < window_width) {
continue;
}
extract_negative_samples(scaledImage, rects, scale, ofs, ofs_patch);
size = size * scale_ratio;
}
}
return 0;
}
void extract_boxes(char *cfgfile, char *weightfile)
{
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));
char *val_images = "/home/pjreddie/data/voc/test/train.txt";
list *plist = get_paths(val_images);
char **paths = (char **)list_to_array(plist);
layer l = net.layers[net.n - 1];
int num_boxes = l.side;
int num = l.n;
int classes = l.classes;
int j;
box *boxes = calloc(num_boxes*num_boxes*num, sizeof(box));
float **probs = calloc(num_boxes*num_boxes*num, sizeof(float *));
for(j = 0; j < num_boxes*num_boxes*num; ++j) probs[j] = calloc(classes+1, sizeof(float *));
int N = plist->size;
int i=0;
int k;
int count = 0;
float iou_thresh = .3;
for (i = 0; i < N; ++i) {
fprintf(stderr, "%5d %5d\n", i, count);
char *path = paths[i];
image orig = load_image_color(path, 0, 0);
image resized = resize_image(orig, net.w, net.h);
float *X = resized.data;
float *predictions = network_predict(net, X);
get_boxes(predictions+1+classes, num, num_boxes, 5+classes, boxes);
get_probs(predictions, num*num_boxes*num_boxes, classes, 5+classes, probs);
char *labelpath = find_replace(path, "images", "labels");
labelpath = find_replace(labelpath, "JPEGImages", "labels");
labelpath = find_replace(labelpath, ".jpg", ".txt");
labelpath = find_replace(labelpath, ".JPEG", ".txt");
int num_labels = 0;
box_label *truth = read_boxes(labelpath, &num_labels);
FILE *label = stdin;
for(k = 0; k < num_boxes*num_boxes*num; ++k){
int overlaps = 0;
for (j = 0; j < num_labels; ++j) {
box t = {truth[j].x, truth[j].y, truth[j].w, truth[j].h};
float iou = box_iou(boxes[k], t);
if (iou > iou_thresh){
if (!overlaps) {
char buff[256];
sprintf(buff, "/data/extracted/labels/%d.txt", count);
label = fopen(buff, "w");
overlaps = 1;
}
fprintf(label, "%d %f\n", truth[j].id, iou);
}
}
if (overlaps) {
char buff[256];
sprintf(buff, "/data/extracted/imgs/%d", count++);
int dx = (boxes[k].x - boxes[k].w/2) * orig.w;
int dy = (boxes[k].y - boxes[k].h/2) * orig.h;
int w = boxes[k].w * orig.w;
int h = boxes[k].h * orig.h;
image cropped = crop_image(orig, dx, dy, w, h);
image sized = resize_image(cropped, 224, 224);
#ifdef OPENCV
save_image_jpg(sized, buff);
#endif
free_image(sized);
free_image(cropped);
fclose(label);
}
}
free(truth);
free_image(orig);
free_image(resized);
}
}
void validate_recall(char *cfgfile, char *weightfile)
{
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));
char *val_images = "/home/pjreddie/data/voc/test/2007_test.txt";
list *plist = get_paths(val_images);
char **paths = (char **)list_to_array(plist);
layer l = net.layers[net.n - 1];
int num_boxes = l.side;
int num = l.n;
int classes = l.classes;
int j;
box *boxes = calloc(num_boxes*num_boxes*num, sizeof(box));
float **probs = calloc(num_boxes*num_boxes*num, sizeof(float *));
for(j = 0; j < num_boxes*num_boxes*num; ++j) probs[j] = calloc(classes+1, sizeof(float *));
int N = plist->size;
int i=0;
int k;
float iou_thresh = .5;
float thresh = .1;
int total = 0;
int correct = 0;
float avg_iou = 0;
int nms = 1;
int proposals = 0;
int save = 1;
for (i = 0; i < N; ++i) {
char *path = paths[i];
image orig = load_image_color(path, 0, 0);
image resized = resize_image(orig, net.w, net.h);
float *X = resized.data;
float *predictions = network_predict(net, X);
get_boxes(predictions+1+classes, num, num_boxes, 5+classes, boxes);
get_probs(predictions, num*num_boxes*num_boxes, classes, 5+classes, probs);
if (nms) do_nms(boxes, probs, num*num_boxes*num_boxes, (classes>0) ? classes : 1, iou_thresh);
char *labelpath = find_replace(path, "images", "labels");
labelpath = find_replace(labelpath, "JPEGImages", "labels");
labelpath = find_replace(labelpath, ".jpg", ".txt");
labelpath = find_replace(labelpath, ".JPEG", ".txt");
int num_labels = 0;
box_label *truth = read_boxes(labelpath, &num_labels);
for(k = 0; k < num_boxes*num_boxes*num; ++k){
if(probs[k][0] > thresh){
++proposals;
if(save){
char buff[256];
sprintf(buff, "/data/extracted/nms_preds/%d", proposals);
int dx = (boxes[k].x - boxes[k].w/2) * orig.w;
int dy = (boxes[k].y - boxes[k].h/2) * orig.h;
int w = boxes[k].w * orig.w;
int h = boxes[k].h * orig.h;
image cropped = crop_image(orig, dx, dy, w, h);
image sized = resize_image(cropped, 224, 224);
#ifdef OPENCV
save_image_jpg(sized, buff);
#endif
free_image(sized);
free_image(cropped);
sprintf(buff, "/data/extracted/nms_pred_boxes/%d.txt", proposals);
char *im_id = basecfg(path);
FILE *fp = fopen(buff, "w");
fprintf(fp, "%s %d %d %d %d\n", im_id, dx, dy, dx+w, dy+h);
fclose(fp);
free(im_id);
}
}
}
for (j = 0; j < num_labels; ++j) {
++total;
box t = {truth[j].x, truth[j].y, truth[j].w, truth[j].h};
float best_iou = 0;
for(k = 0; k < num_boxes*num_boxes*num; ++k){
float iou = box_iou(boxes[k], t);
if(probs[k][0] > thresh && iou > best_iou){
best_iou = iou;
}
}
avg_iou += best_iou;
if(best_iou > iou_thresh){
++correct;
}
}
free(truth);
free_image(orig);
free_image(resized);
fprintf(stderr, "%5d %5d %5d\tRPs/Img: %.2f\tIOU: %.2f%%\tRecall:%.2f%%\n", i, correct, total, (float)proposals/(i+1), avg_iou*100/total, 100.*correct/total);
}
}
void validate_yolo_recall(char *cfgfile, char *weightfile, char *val_images, char *out_dir, float th, int log, int draw)
{
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));
//create output directory if it does not exist
struct stat st= {0};
if(stat(out_dir,&st)==-1){
fprintf(stderr,"Creating output directory\n");
mkdir(out_dir,0700);
}
char *base = out_dir;
list *plist = get_paths(val_images);
char **paths = (char **)list_to_array(plist);
layer l = net.layers[net.n-1];
int classes = l.classes;
int square = l.sqrt;
//int side = l.side;
int rows = l.rows;
int cols = l.cols;
int j, k;
FILE **fps = calloc(classes, sizeof(FILE *));
for(j = 0; j < classes; ++j){
char buff[1024];
snprintf(buff, 1024, "%s%s.txt", base, voc_names[j]);
fps[j] = fopen(buff, "w");
}
box *boxes = calloc(rows*cols*l.n, sizeof(box));
float **probs = calloc(rows*cols*l.n, sizeof(float *));
for(j = 0; j < rows*cols*l.n; ++j) probs[j] = calloc(classes, sizeof(float *));
int m = plist->size;
int i=0;
float thresh = th;
float iou_thresh[11] = {0.0,0.05,0.1,0.15,0.20,0.25,0.30,0.35,0.40,0.45,0.5};
float nms = 0.1;
int total = 0;
int correct[11] = {0,0,0,0,0,0,0,0,0,0,0};
int proposals = 0;
float avg_iou = 0;
Vector id_found;
Vector id_invalid;
initArray(&id_found,5);
initArray(&id_invalid,5);
for(i = 0; i < m; ++i){
char * image_path = strtok(paths[i]," ");
char * label_path = strtok(NULL," ");
image orig = load_image(image_path, 0, 0,net.c);
image color;
if(draw)
color = load_image(image_path, 0, 0, 3);
image sized = resize_image(orig, net.w, net.h);
//char *id = basecfg(path);
float *predictions = network_predict(net, sized.data);
convert_detections(predictions, classes, l.n, square, rows, cols, 1, 1, thresh, probs, boxes, 0);
if (nms) do_nms(boxes, probs, rows*cols*l.n, 1, nms);
int num_labels = 0;
box_label *truth = read_boxes(label_path, &num_labels);
int old_p = proposals;
for(k = 0; k < rows*cols*l.n; ++k){
if(probs[k][0] > thresh){
++proposals;
}
}
if(old_p!=proposals){
if(log){
char filename[256];
sprintf(filename, "%s/%d.txt", base,i);
printf("log in file %s\n",filename);
FILE * out = fopen(filename, "w");
fprintf(out,"W\tH\tX\tY\n");
for(k=0; k<rows*cols*l.n; ++k){
if(probs[k][0] > thresh){
fprintf(out, "%f\t%f\t%f\t%f\n",boxes[k].w,boxes[k].h,boxes[k].x,boxes[k].y);
}
}
fclose(out);
}
if(draw){
draw_detections(color, l.rows*l.cols*l.n, thresh, boxes, probs, voc_names, voc_labels, CLASSNUM);
show_image(color, "predictions");
#ifdef OPENCV
cvWaitKey(0);
//cvDestroyAllWindows();
#endif
}
}
for (j = 0; j < num_labels; ++j) {
++total;
while(id_found.used <= truth[j].id){
insertArray(&id_invalid,0);
insertArray(&id_found,0);
}
if(truth[j].classe > CLASSNUM-1)
id_invalid.array[truth[j].id]=1;
box t = {truth[j].x, truth[j].y, truth[j].w, truth[j].h};
float best_iou = 0;
for(k = 0; k < rows*cols*l.n; ++k){
float iou = box_iou(boxes[k], t);
//find overlapping prediction
if(iou > best_iou){
//find the predicted class
float best_score = thresh;
int best_class_index = -1;
for(int c=0; c<CLASSNUM; c++){
if(probs[k][c]>best_score){
best_score = probs[k][c];
best_class_index = c;
}
}
//check if it's good or not
if(best_class_index == truth[j].classe)
best_iou = iou;
}
}
avg_iou += best_iou;
for(int k=0; k<11; k++){
if(best_iou > iou_thresh[k]){
id_found.array[truth[j].id]=1;
++correct[k];
}
}
}
if(i%10==0){
printf("\033[2J");
printf("\033[1;1H");
printf("#img\tPred\tTP\ttot\tRPs/Img\tAvg-IOU\tRecall\tPrecision\n");
printf("%5d\t%5d\t%5d\t%5d\t%.2f\t%.2f%%\t%.2f%%\t%.2f%%\n", i, proposals, correct[10], total, (float)proposals/(i+1), avg_iou*100/total, 100.*correct[10]/total, 100.*correct[10]/proposals);
printf("IOU_th\tTP\tFP\tRecall\tPrecision\n");
for(int k=0; k<11; k++){
printf("%.2f%%\t%5d\t%5d\t%.2f%%\t%.2f%%\t\n", iou_thresh[k], correct[k], proposals-correct[k], 100.*correct[k]/total, 100.*correct[k]/proposals);
}
int found=0;
int invalid = 0;
for(int i=0; i<id_found.used; i++){
if(id_invalid.array[i]!=1)
found+=id_found.array[i];
invalid+=id_invalid.array[i];
}
printf("Founded: %d/%d\t%d\n", found, id_found.used-invalid,invalid);
}
//free(id);
free_image(orig);
free_image(sized);
}
for(j = 0; j < classes; ++j){
fprintf(fps[j],"IOU_th;TP;FP;Recall;Precision\n");
for(int k=0; k<11; k++){
fprintf(fps[j],"%.2f%%;%5d;%5d;%.2f%%;%.2f%%;\n", iou_thresh[k], correct[k], proposals-correct[k], 100.*correct[k]/total, 100.*correct[k]/proposals);
}
fprintf(fps[j], "\n\nFounded;Total;\n");
int found=0;
int invalid = 0;
for(int i=0; i<id_found.used; i++){
if(id_invalid.array[i]!=1)
found+=id_found.array[i];
invalid+=id_invalid.array[i];
}
fprintf(fps[j], "%d;%d;\n", found, id_found.used-invalid);
fclose(fps[j]);
}
freeArray(&id_found);
}
