github
/
darknet
mirror of https://github.com/AlexeyAB/darknet.git
1
0
Fork 0
Code Issues Releases Wiki Activity

Fixed training, calculation mAP and anchors for Yolo v3

Browse Source
pull/604/merge
AlexeyAB 7 years ago
parent d28f7e6681
commit 3fc3fd0f1f
10 changed files with 321 additions and 299 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 4
      build/darknet/x64/calc_anchors.cmd
  2. 4
      build/darknet/x64/calc_mAP.cmd
  3. 5
      build/darknet/x64/darknet_yolo_v3_video.cmd
  4. 4
      build/darknet/x64/data/voc.data
  5. 8
      build/darknet/x64/yolov3.cfg
  6. 3
      src/data.c
  7. 2
      src/data.h
  8. 189
      src/detector.c
  9. 10
      src/network.c
  10. 21
      src/yolo_layer.c

4
build/darknet/x64/calc_anchors.cmd
Unescape View File

@ -1,10 +1,10 @@
rem # How to calculate Yolo v2 anchors using K-means++
darknet.exe detector calc_anchors data/voc.data -num_of_clusters 5 -final_width 13 -final_heigh 13
darknet.exe detector calc_anchors data/voc.data -num_of_clusters 5 -width 416 -heigh 416
rem darknet.exe detector calc_anchors data/voc.data -num_of_clusters 5 -final_width 13 -final_heigh 13 -show
rem darknet.exe detector calc_anchors data/voc.data -num_of_clusters 5 -width 416 -heigh 416 -show

4
build/darknet/x64/calc_mAP.cmd
Unescape View File

@ -1,10 +1,10 @@
rem # How to calculate mAP (mean average precision)
rem darknet.exe detector map data/voc.data tiny-yolo-voc.cfg tiny-yolo-voc.weights
rem darknet.exe detector map data/voc.data cfg/yolov2-tiny-voc.cfg yolov2-tiny-voc.weights
darknet.exe detector map data/voc.data yolo-voc.cfg yolo-voc.weights
darknet.exe detector map data/voc.data cfg/yolov2-voc.cfg yolo-voc.weights

5
build/darknet/x64/darknet_yolo_v3_video.cmd
Unescape View File

@ -0,0 +1,5 @@
darknet.exe detector demo data/coco.data yolov3.cfg yolov3.weights -i 0 -thresh 0.25 test.mp4
pause

4
build/darknet/x64/data/voc.data
Unescape View File

@ -1,7 +1,7 @@
classes= 20
train = data/train_voc.txt
valid = data/voc/2007_test.txt
#difficult = data/voc/difficult_2007_test.txt
valid = data/2007_test.txt
#difficult = data/difficult_2007_test.txt
names = data/voc.names
backup = backup/

8
build/darknet/x64/yolov3.cfg
Unescape View File

@ -1,10 +1,10 @@
[net]
# Testing
batch=1
subdivisions=1
#batch=1
#subdivisions=1
# Training
# batch=64
# subdivisions=16
batch=64
subdivisions=16
width=416
height=416
channels=3

3
src/data.c
Unescape View File

@ -827,6 +827,9 @@ void *load_thread(void *ptr)
} else if (a.type == IMAGE_DATA){
*(a.im) = load_image_color(a.path, 0, 0);
*(a.resized) = resize_image(*(a.im), a.w, a.h);
}else if (a.type == LETTERBOX_DATA) {
*(a.im) = load_image_color(a.path, 0, 0);
*(a.resized) = letterbox_image(*(a.im), a.w, a.h);
} else if (a.type == TAG_DATA){
*a.d = load_data_tag(a.paths, a.n, a.m, a.classes, a.min, a.max, a.size, a.angle, a.aspect, a.hue, a.saturation, a.exposure);
}

2
src/data.h
Unescape View File

@ -32,7 +32,7 @@ typedef struct{
} data;
typedef enum {
CLASSIFICATION_DATA, DETECTION_DATA, CAPTCHA_DATA, REGION_DATA, IMAGE_DATA, COMPARE_DATA, WRITING_DATA, SWAG_DATA, TAG_DATA, OLD_CLASSIFICATION_DATA, STUDY_DATA, DET_DATA, SUPER_DATA
CLASSIFICATION_DATA, DETECTION_DATA, CAPTCHA_DATA, REGION_DATA, IMAGE_DATA, LETTERBOX_DATA, COMPARE_DATA, WRITING_DATA, SWAG_DATA, TAG_DATA, OLD_CLASSIFICATION_DATA, STUDY_DATA, DET_DATA, SUPER_DATA
} data_type;
typedef struct load_args{

189
src/detector.c
Unescape View File

@ -170,7 +170,7 @@ void train_detector(char *datacfg, char *cfgfile, char *weightfile, int *gpus, i
avg_loss = avg_loss*.9 + loss*.1;
i = get_current_batch(net);
printf("%d: %f, %f avg, %f rate, %lf seconds, %d images\n", get_current_batch(net), loss, avg_loss, get_current_rate(net), sec(clock()-time), i*imgs);
printf("\n %d: %f, %f avg, %f rate, %lf seconds, %d images\n", get_current_batch(net), loss, avg_loss, get_current_rate(net), sec(clock()-time), i*imgs);
#ifdef OPENCV
if(!dont_show)
@ -204,19 +204,21 @@ void train_detector(char *datacfg, char *cfgfile, char *weightfile, int *gpus, i
static int get_coco_image_id(char *filename)
{
char *p = strrchr(filename, '_');
char *p = strrchr(filename, '/');
char *c = strrchr(filename, '_');
if (c) p = c;
return atoi(p + 1);
}
static void print_cocos(FILE *fp, char *image_path, box *boxes, float **probs, int num_boxes, int classes, int w, int h)
static void print_cocos(FILE *fp, char *image_path, detection *dets, int num_boxes, int classes, int w, int h)
{
int i, j;
int image_id = get_coco_image_id(image_path);
for (i = 0; i < num_boxes; ++i) {
float xmin = boxes[i].x - boxes[i].w/2.;
float xmax = boxes[i].x + boxes[i].w/2.;
float ymin = boxes[i].y - boxes[i].h/2.;
float ymax = boxes[i].y + boxes[i].h/2.;
float xmin = dets[i].bbox.x - dets[i].bbox.w / 2.;
float xmax = dets[i].bbox.x + dets[i].bbox.w / 2.;
float ymin = dets[i].bbox.y - dets[i].bbox.h / 2.;
float ymax = dets[i].bbox.y + dets[i].bbox.h / 2.;
if (xmin < 0) xmin = 0;
if (ymin < 0) ymin = 0;
@ -229,40 +231,40 @@ static void print_cocos(FILE *fp, char *image_path, box *boxes, float **probs, i
float bh = ymax - ymin;
for (j = 0; j < classes; ++j) {
if (probs[i][j]) fprintf(fp, "{\"image_id\":%d, \"category_id\":%d, \"bbox\":[%f, %f, %f, %f], \"score\":%f},\n", image_id, coco_ids[j], bx, by, bw, bh, probs[i][j]);
if (dets[i].prob[j]) fprintf(fp, "{\"image_id\":%d, \"category_id\":%d, \"bbox\":[%f, %f, %f, %f], \"score\":%f},\n", image_id, coco_ids[j], bx, by, bw, bh, dets[i].prob[j]);
}
}
}
void print_detector_detections(FILE **fps, char *id, box *boxes, float **probs, int total, int classes, int w, int h)
void print_detector_detections(FILE **fps, char *id, detection *dets, int total, int classes, int w, int h)
{
int i, j;
for (i = 0; i < total; ++i) {
float xmin = boxes[i].x - boxes[i].w/2.;
float xmax = boxes[i].x + boxes[i].w/2.;
float ymin = boxes[i].y - boxes[i].h/2.;
float ymax = boxes[i].y + boxes[i].h/2.;
float xmin = dets[i].bbox.x - dets[i].bbox.w / 2. + 1;
float xmax = dets[i].bbox.x + dets[i].bbox.w / 2. + 1;
float ymin = dets[i].bbox.y - dets[i].bbox.h / 2. + 1;
float ymax = dets[i].bbox.y + dets[i].bbox.h / 2. + 1;
if (xmin < 0) xmin = 0;
if (ymin < 0) ymin = 0;
if (xmin < 1) xmin = 1;
if (ymin < 1) ymin = 1;
if (xmax > w) xmax = w;
if (ymax > h) ymax = h;
for (j = 0; j < classes; ++j) {
if (probs[i][j]) fprintf(fps[j], "%s %f %f %f %f %f\n", id, probs[i][j],
if (dets[i].prob[j]) fprintf(fps[j], "%s %f %f %f %f %f\n", id, dets[i].prob[j],
xmin, ymin, xmax, ymax);
}
}
}
void print_imagenet_detections(FILE *fp, int id, box *boxes, float **probs, int total, int classes, int w, int h)
void print_imagenet_detections(FILE *fp, int id, detection *dets, int total, int classes, int w, int h)
{
int i, j;
for (i = 0; i < total; ++i) {
float xmin = boxes[i].x - boxes[i].w/2.;
float xmax = boxes[i].x + boxes[i].w/2.;
float ymin = boxes[i].y - boxes[i].h/2.;
float ymax = boxes[i].y + boxes[i].h/2.;
float xmin = dets[i].bbox.x - dets[i].bbox.w / 2.;
float xmax = dets[i].bbox.x + dets[i].bbox.w / 2.;
float ymin = dets[i].bbox.y - dets[i].bbox.h / 2.;
float ymax = dets[i].bbox.y + dets[i].bbox.h / 2.;
if (xmin < 0) xmin = 0;
if (ymin < 0) ymin = 0;
@ -270,14 +272,14 @@ void print_imagenet_detections(FILE *fp, int id, box *boxes, float **probs, int
if (ymax > h) ymax = h;
for (j = 0; j < classes; ++j) {
int class_id = j;
if (probs[i][class_id]) fprintf(fp, "%d %d %f %f %f %f %f\n", id, j+1, probs[i][class_id],
int class = j;
if (dets[i].prob[class]) fprintf(fp, "%d %d %f %f %f %f %f\n", id, j + 1, dets[i].prob[class],
xmin, ymin, xmax, ymax);
}
}
}
void validate_detector(char *datacfg, char *cfgfile, char *weightfile)
void validate_detector(char *datacfg, char *cfgfile, char *weightfile, char *outfile)
{
int j;
list *options = read_data_cfg(datacfg);
@ -297,7 +299,6 @@ void validate_detector(char *datacfg, char *cfgfile, char *weightfile)
fprintf(stderr, "Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
srand(time(0));
char *base = "comp4_det_test_";
list *plist = get_paths(valid_images);
char **paths = (char **)list_to_array(plist);
@ -311,28 +312,29 @@ void validate_detector(char *datacfg, char *cfgfile, char *weightfile)
int coco = 0;
int imagenet = 0;
if (0 == strcmp(type, "coco")) {
snprintf(buff, 1024, "%s/coco_results.json", prefix);
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")){
snprintf(buff, 1024, "%s/imagenet-detection.txt", prefix);
}
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 {
}
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, base, names[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;
@ -340,8 +342,6 @@ void validate_detector(char *datacfg, char *cfgfile, char *weightfile)
float thresh = .005;
float nms = .45;
int detection_count = 0;
int nthreads = 4;
image *val = calloc(nthreads, sizeof(image));
image *val_resized = calloc(nthreads, sizeof(image));
@ -353,6 +353,7 @@ void validate_detector(char *datacfg, char *cfgfile, char *weightfile)
args.w = net.w;
args.h = net.h;
args.type = IMAGE_DATA;
//args.type = LETTERBOX_DATA;
for (t = 0; t < nthreads; ++t) {
args.path = paths[i + t];
@ -381,24 +382,20 @@ void validate_detector(char *datacfg, char *cfgfile, char *weightfile)
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);
if (nms) do_nms_sort(boxes, probs, l.w*l.h*l.n, classes, nms);
int x, y;
for (x = 0; x < (l.w*l.h*l.n); ++x) {
for (y = 0; y < classes; ++y)
{
if (probs[x][y]) ++detection_count;
int nboxes = 0;
int letterbox = (args.type == LETTERBOX_DATA);
detection *dets = get_network_boxes(&net, w, h, thresh, .5, map, 0, &nboxes, letterbox);
if (nms) do_nms_sort_v3(dets, nboxes, classes, nms);
if (coco) {
print_cocos(fp, path, dets, nboxes, classes, w, h);
}
else if (imagenet) {
print_imagenet_detections(fp, i + t - nthreads + 1, dets, nboxes, classes, w, h);
}
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);
else {
print_detector_detections(fps, id, dets, nboxes, classes, w, h);
}
free_detections(dets, nboxes);
free(id);
free_image(val[t]);
free_image(val_resized[t]);
@ -412,8 +409,7 @@ void validate_detector(char *datacfg, char *cfgfile, char *weightfile)
fprintf(fp, "\n]\n");
fclose(fp);
}
printf("\n detection_count = %d \n", detection_count);
fprintf(stderr, "Total Detection Time: %f Seconds\n", (double)(time(0) - start));
fprintf(stderr, "Total Detection Time: %f Seconds\n", time(0) - start);
}
void validate_detector_recall(char *datacfg, char *cfgfile, char *weightfile)
@ -423,31 +419,25 @@ void validate_detector_recall(char *datacfg, char *cfgfile, char *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/coco_val_5k.list");
list *options = read_data_cfg(datacfg);
char *valid_images = option_find_str(options, "valid", "data/train.txt");
list *plist = get_paths(valid_images);
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;// .001; // .2;
float thresh = .001;
float iou_thresh = .5;
float nms = .4;
int detection_count = 0, truth_count = 0;
int total = 0;
int correct = 0;
int proposals = 0;
@ -459,21 +449,21 @@ void validate_detector_recall(char *datacfg, char *cfgfile, char *weightfile)
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);
if (nms) do_nms(boxes, probs, l.w*l.h*l.n, 1, nms);
int nboxes = 0;
int letterbox = 0;
detection *dets = get_network_boxes(&net, sized.w, sized.h, thresh, .5, 0, 1, &nboxes, letterbox);
if (nms) do_nms_obj_v3(dets, nboxes, 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);
find_replace(labelpath, ".png", ".txt", labelpath);
int num_labels = 0;
box_label *truth = read_boxes(labelpath, &num_labels);
truth_count += num_labels;
for(k = 0; k < l.w*l.h*l.n; ++k){
if(probs[k][0] > thresh){
for (k = 0; k < nboxes; ++k) {
if (dets[k].objectness > thresh) {
++proposals;
}
}
@ -482,8 +472,8 @@ void validate_detector_recall(char *datacfg, char *cfgfile, char *weightfile)
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) {
float iou = box_iou(dets[k].bbox, t);
if (dets[k].objectness > thresh && iou > best_iou) {
best_iou = iou;
}
}
@ -498,7 +488,6 @@ void validate_detector_recall(char *datacfg, char *cfgfile, char *weightfile)
free_image(orig);
free_image(sized);
}
printf("\n truth_count = %d \n", truth_count);
}
typedef struct {
@ -537,7 +526,6 @@ void validate_detector_map(char *datacfg, char *cfgfile, char *weightfile, float
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);
@ -553,10 +541,6 @@ void validate_detector_map(char *datacfg, char *cfgfile, char *weightfile, float
layer l = net.layers[net.n - 1];
int classes = l.classes;
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;
@ -576,6 +560,7 @@ void validate_detector_map(char *datacfg, char *cfgfile, char *weightfile, float
args.w = net.w;
args.h = net.h;
args.type = IMAGE_DATA;
//args.type = LETTERBOX_DATA;
//const float thresh_calc_avg_iou = 0.24;
float avg_iou = 0;
@ -614,8 +599,12 @@ void validate_detector_map(char *datacfg, char *cfgfile, char *weightfile, float
char *id = basecfg(path);
float *X = val_resized[t].data;
network_predict(net, X);
get_region_boxes(l, 1, 1, thresh, probs, boxes, 0, map);
if (nms) do_nms_sort(boxes, probs, l.w*l.h*l.n, classes, nms);
int nboxes = 0;
int letterbox = (args.type == LETTERBOX_DATA);
float hier_thresh = 0;
detection *dets = get_network_boxes(&net, 1, 1, thresh, hier_thresh, 0, 1, &nboxes, letterbox);
if (nms) do_nms_sort_v3(dets, nboxes, l.classes, nms);
char labelpath[4096];
find_replace(path, "images", "labels", labelpath);
@ -646,15 +635,15 @@ void validate_detector_map(char *datacfg, char *cfgfile, char *weightfile, float
truth_dif = read_boxes(labelpath_dif, &num_labels_dif);
}
for (i = 0; i < (l.w*l.h*l.n); ++i) {
for (i = 0; i < nboxes; ++i) {
int class_id;
for (class_id = 0; class_id < classes; ++class_id) {
float prob = probs[i][class_id];
float prob = dets[i].prob[class_id];
if (prob > 0) {
detections_count++;
detections = realloc(detections, detections_count * sizeof(box_prob));
detections[detections_count - 1].b = boxes[i];
detections[detections_count - 1].b = dets[i].bbox;
detections[detections_count - 1].p = prob;
detections[detections_count - 1].image_index = image_index;
detections[detections_count - 1].class_id = class_id;
@ -667,8 +656,8 @@ void validate_detector_map(char *datacfg, char *cfgfile, char *weightfile, float
{
box t = { truth[j].x, truth[j].y, truth[j].w, truth[j].h };
//printf(" IoU = %f, prob = %f, class_id = %d, truth[j].id = %d \n",
// box_iou(boxes[i], t), prob, class_id, truth[j].id);
float current_iou = box_iou(boxes[i], t);
// box_iou(dets[i].bbox, t), prob, class_id, truth[j].id);
float current_iou = box_iou(dets[i].bbox, t);
if (current_iou > iou_thresh && class_id == truth[j].id) {
if (current_iou > max_iou) {
max_iou = current_iou;
@ -686,7 +675,7 @@ void validate_detector_map(char *datacfg, char *cfgfile, char *weightfile, float
// if object is difficult then remove detection
for (j = 0; j < num_labels_dif; ++j) {
box t = { truth_dif[j].x, truth_dif[j].y, truth_dif[j].w, truth_dif[j].h };
float current_iou = box_iou(boxes[i], t);
float current_iou = box_iou(dets[i].bbox, t);
if (current_iou > iou_thresh && class_id == truth_dif[j].id) {
--detections_count;
break;
@ -709,6 +698,7 @@ void validate_detector_map(char *datacfg, char *cfgfile, char *weightfile, float
unique_truth_count += num_labels;
free_detections(dets, nboxes);
free(id);
free_image(val[t]);
free_image(val_resized[t]);
@ -830,9 +820,9 @@ void validate_detector_map(char *datacfg, char *cfgfile, char *weightfile, float
}
#ifdef OPENCV
void calc_anchors(char *datacfg, int num_of_clusters, int final_width, int final_height, int show)
void calc_anchors(char *datacfg, int num_of_clusters, int width, int height, int show)
{
printf("\n num_of_clusters = %d, final_width = %d, final_height = %d \n", num_of_clusters, final_width, final_height);
printf("\n num_of_clusters = %d, width = %d, height = %d \n", num_of_clusters, width, height);
//float pointsdata[] = { 1,1, 2,2, 6,6, 5,5, 10,10 };
float *rel_width_height_array = calloc(1000, sizeof(float));
@ -862,8 +852,8 @@ void calc_anchors(char *datacfg, int num_of_clusters, int final_width, int final
{
number_of_boxes++;
rel_width_height_array = realloc(rel_width_height_array, 2 * number_of_boxes * sizeof(float));
rel_width_height_array[number_of_boxes * 2 - 2] = truth[j].w * final_width;
rel_width_height_array[number_of_boxes * 2 - 1] = truth[j].h * final_height;
rel_width_height_array[number_of_boxes * 2 - 2] = truth[j].w * width;
rel_width_height_array[number_of_boxes * 2 - 1] = truth[j].h * height;
printf("\r loaded \t image: %d \t box: %d", i+1, number_of_boxes);
}
}
@ -967,15 +957,15 @@ void calc_anchors(char *datacfg, int num_of_clusters, int final_width, int final
for (j = 0; j < num_of_clusters; ++j) {
CvPoint pt1, pt2;
pt1.x = pt1.y = 0;
pt2.x = centers->data.fl[j * 2] * img_size / final_width;
pt2.y = centers->data.fl[j * 2 + 1] * img_size / final_height;
pt2.x = centers->data.fl[j * 2] * img_size / width;
pt2.y = centers->data.fl[j * 2 + 1] * img_size / height;
cvRectangle(img, pt1, pt2, CV_RGB(255, 255, 255), 1, 8, 0);
}
for (i = 0; i < number_of_boxes; ++i) {
CvPoint pt;
pt.x = points->data.fl[i * 2] * img_size / final_width;
pt.y = points->data.fl[i * 2 + 1] * img_size / final_height;
pt.x = points->data.fl[i * 2] * img_size / width;
pt.y = points->data.fl[i * 2 + 1] * img_size / height;
int cluster_idx = labels->data.i[i];
int red_id = (cluster_idx * (uint64_t)123 + 55) % 255;
int green_id = (cluster_idx * (uint64_t)321 + 33) % 255;
@ -995,7 +985,7 @@ void calc_anchors(char *datacfg, int num_of_clusters, int final_width, int final
cvReleaseMat(&labels);
}
#else
void calc_anchors(char *datacfg, int num_of_clusters, int final_width, int final_height, int show) {
void calc_anchors(char *datacfg, int num_of_clusters, int width, int height, int show) {
printf(" k-means++ can't be used without OpenCV, because there is used cvKMeans2 implementation \n");
}
#endif // OPENCV
@ -1030,9 +1020,9 @@ void test_detector(char *datacfg, char *cfgfile, char *weightfile, char *filenam
strtok(input, "\n");
}
image im = load_image_color(input,0,0);
int letter = 0;
int letterbox = 0;
image sized = resize_image(im, net.w, net.h);
//image sized = letterbox_image(im, net.w, net.h); letter = 1;
//image sized = letterbox_image(im, net.w, net.h); letterbox = 1;
layer l = net.layers[net.n-1];
//box *boxes = calloc(l.w*l.h*l.n, sizeof(box));
@ -1047,7 +1037,7 @@ void test_detector(char *datacfg, char *cfgfile, char *weightfile, char *filenam
// 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);
int nboxes = 0;
detection *dets = get_network_boxes(&net, im.w, im.h, thresh, hier_thresh, 0, 1, &nboxes, letter);
detection *dets = get_network_boxes(&net, im.w, im.h, thresh, hier_thresh, 0, 1, &nboxes, letterbox);
if (nms) do_nms_sort_v3(dets, nboxes, l.classes, nms);
draw_detections_v3(im, dets, nboxes, thresh, names, alphabet, l.classes);
free_detections(dets, nboxes);
@ -1076,14 +1066,15 @@ void run_detector(int argc, char **argv)
int show = find_arg(argc, argv, "-show");
int http_stream_port = find_int_arg(argc, argv, "-http_port", -1);
char *out_filename = find_char_arg(argc, argv, "-out_filename", 0);
char *outfile = find_char_arg(argc, argv, "-out", 0);
char *prefix = find_char_arg(argc, argv, "-prefix", 0);
float thresh = find_float_arg(argc, argv, "-thresh", .25); // 0.24
float hier_thresh = find_float_arg(argc, argv, "-hier", .5);
int cam_index = find_int_arg(argc, argv, "-c", 0);
int frame_skip = find_int_arg(argc, argv, "-s", 0);
int num_of_clusters = find_int_arg(argc, argv, "-num_of_clusters", 5);
int final_width = find_int_arg(argc, argv, "-final_width", 13);
int final_heigh = find_int_arg(argc, argv, "-final_heigh", 13);
int width = find_int_arg(argc, argv, "-width", 13);
int heigh = find_int_arg(argc, argv, "-heigh", 13);
if(argc < 4){
fprintf(stderr, "usage: %s %s [train/test/valid] [cfg] [weights (optional)]\n", argv[0], argv[1]);
return;
@ -1121,10 +1112,10 @@ void run_detector(int argc, char **argv)
char *filename = (argc > 6) ? argv[6]: 0;
if(0==strcmp(argv[2], "test")) test_detector(datacfg, cfg, weights, filename, thresh, hier_thresh, dont_show);
else if(0==strcmp(argv[2], "train")) train_detector(datacfg, cfg, weights, gpus, ngpus, clear, dont_show);
else if(0==strcmp(argv[2], "valid")) validate_detector(datacfg, cfg, weights);
else if(0==strcmp(argv[2], "valid")) validate_detector(datacfg, cfg, weights, outfile);
else if(0==strcmp(argv[2], "recall")) validate_detector_recall(datacfg, cfg, weights);
else if(0==strcmp(argv[2], "map")) validate_detector_map(datacfg, cfg, weights, thresh);
else if(0==strcmp(argv[2], "calc_anchors")) calc_anchors(datacfg, num_of_clusters, final_width, final_heigh, show);
else if(0==strcmp(argv[2], "calc_anchors")) calc_anchors(datacfg, num_of_clusters, width, heigh, show);
else if(0==strcmp(argv[2], "demo")) {
list *options = read_data_cfg(datacfg);
int classes = option_find_int(options, "classes", 20);

10
src/network.c
Unescape View File

@ -374,10 +374,14 @@ int resize_network(network *net, int w, int h)
resize_maxpool_layer(&l, w, h);
}else if(l.type == REGION){
resize_region_layer(&l, w, h);
}else if (l.type == YOLO) {
resize_yolo_layer(&l, w, h);
}else if(l.type == ROUTE){
resize_route_layer(&l, net);
}else if (l.type == SHORTCUT) {
resize_shortcut_layer(&l, w, h);
}else if (l.type == UPSAMPLE) {
resize_upsample_layer(&l, w, h);
}else if(l.type == REORG){
resize_reorg_layer(&l, w, h);
}else if(l.type == AVGPOOL){
@ -539,12 +543,14 @@ void custom_get_region_detections(layer l, int w, int h, int net_w, int net_h, f
float **probs = calloc(l.w*l.h*l.n, sizeof(float *));
int i, j;
for (j = 0; j < l.w*l.h*l.n; ++j) probs[j] = calloc(l.classes, sizeof(float *));
get_region_boxes(l, 1, 1, thresh, probs, boxes, 0, map);
get_region_boxes(l, w, h, thresh, probs, boxes, 0, map);
for (j = 0; j < l.w*l.h*l.n; ++j) {
dets[j].classes = l.classes;
dets[j].bbox = boxes[j];
dets[j].objectness = 1;
for (i = 0; i < l.classes; ++i) dets[j].prob[i] = probs[j][i];
for (i = 0; i < l.classes; ++i) {
dets[j].prob[i] = probs[j][i];
}
}
free(boxes);

21
src/yolo_layer.c
Unescape View File

@ -378,9 +378,26 @@ void forward_yolo_layer_gpu(const layer l, network_state state)
return;
}
cuda_pull_array(l.output_gpu, state.input, l.batch*l.inputs);
forward_yolo_layer(l, state);
//cuda_pull_array(l.output_gpu, state.input, l.batch*l.inputs);
float *in_cpu = calloc(l.batch*l.inputs, sizeof(float));
cuda_pull_array(l.output_gpu, in_cpu, l.batch*l.inputs);
float *truth_cpu = 0;
if (state.truth) {
int num_truth = l.batch*l.truths;
truth_cpu = calloc(num_truth, sizeof(float));
cuda_pull_array(state.truth, truth_cpu, num_truth);
}
network_state cpu_state = state;
cpu_state.net = state.net;
cpu_state.index = state.index;
cpu_state.train = state.train;
cpu_state.truth = truth_cpu;
cpu_state.input = in_cpu;
forward_yolo_layer(l, cpu_state);
//forward_yolo_layer(l, state);
cuda_push_array(l.delta_gpu, l.delta, l.batch*l.outputs);
free(in_cpu);
if (cpu_state.truth) free(cpu_state.truth);
}
void backward_yolo_layer_gpu(const layer l, network_state state)

Write Preview
Loading…
Cancel
Save