mirror/darknet
1
0
Fork 0
mirror of https://github.com/pjreddie/darknet.git synced 2023-08-10 21:13:14 +03:00
Code Issues Projects Releases Wiki Activity

CARLY RAE JEPSEN IS THE BEST POP ARTIST OF ALL TIME DON'T @ ME

Browse Source
This commit is contained in:
Joseph Redmon 2018-01-22 18:09:36 -08:00
parent e3931c75cd
commit b40bbdc7b2
10 changed files with 311 additions and 58 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
examples/classifier.c
View File

@ -44,11 +44,15 @@ void train_classifier(char *datacfg, char *cfgfile, char *weightfile, int *gpus,
list *options = read_data_cfg(datacfg);
char *backup_directory = option_find_str(options, "backup", "/backup/");
int tag = option_find_int_quiet(options, "tag", 0);
char *label_list = option_find_str(options, "labels", "data/labels.list");
char *train_list = option_find_str(options, "train", "data/train.list");
int classes = option_find_int(options, "classes", 2);
char **labels = get_labels(label_list);
char **labels;
if(!tag){
labels = get_labels(label_list);
}
list *plist = get_paths(train_list);
char **paths = (char **)list_to_array(plist);
printf("%d\n", plist->size);
@ -76,7 +80,11 @@ void train_classifier(char *datacfg, char *cfgfile, char *weightfile, int *gpus,
args.n = imgs;
args.m = N;
args.labels = labels;
if (tag){
args.type = TAG_DATA;
} else {
args.type = CLASSIFICATION_DATA;
}
data train;
data buffer;
@ -385,15 +393,13 @@ void validate_classifier_single(char *datacfg, char *filename, char *weightfile)
}
}
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);
image crop = center_crop_image(im, net->w, net->h);
//show_image(im, "orig");
//show_image(crop, "cropped");
//cvWaitKey(0);
float *pred = network_predict(net, crop.data);
if(net->hierarchy) hierarchy_predictions(pred, net->outputs, net->hierarchy, 1, 1);
if(resized.data != im.data) free_image(resized);
free_image(im);
free_image(crop);
top_k(pred, classes, topk, indexes);
@ -955,6 +961,8 @@ void gun_classifier(char *datacfg, char *cfgfile, char *weightfile, int cam_inde
void demo_classifier(char *datacfg, char *cfgfile, char *weightfile, int cam_index, const char *filename)
{
#ifdef OPENCV
char *base = basecfg(cfgfile);
image **alphabet = load_alphabet();
printf("Classifier Demo\n");
network *net = load_network(cfgfile, weightfile, 0);
set_batch_network(net, 1);
@ -988,8 +996,8 @@ void demo_classifier(char *datacfg, char *cfgfile, char *weightfile, int cam_ind
int *indexes = calloc(top, sizeof(int));
if(!cap) error("Couldn't connect to webcam.\n");
cvNamedWindow("Classifier", CV_WINDOW_NORMAL);
cvResizeWindow("Classifier", 512, 512);
cvNamedWindow(base, CV_WINDOW_NORMAL);
cvResizeWindow(base, 512, 512);
float fps = 0;
int i;
@ -998,8 +1006,8 @@ void demo_classifier(char *datacfg, char *cfgfile, char *weightfile, int cam_ind
gettimeofday(&tval_before, NULL);
image in = get_image_from_stream(cap);
image in_s = resize_image(in, net->w, net->h);
show_image(in, "Classifier");
//image in_s = resize_image(in, net->w, net->h);
image in_s = letterbox_image(in, net->w, net->h);
float *predictions = network_predict(net, in_s.data);
if(net->hierarchy) hierarchy_predictions(predictions, net->outputs, net->hierarchy, 1, 1);
@ -1009,11 +1017,24 @@ void demo_classifier(char *datacfg, char *cfgfile, char *weightfile, int cam_ind
printf("\033[1;1H");
printf("\nFPS:%.0f\n",fps);
int lh = in.h*.03;
int toph = 3*lh;
float rgb[3] = {1,1,1};
for(i = 0; i < top; ++i){
printf("%d\n", toph);
int index = indexes[i];
printf("%.1f%%: %s\n", predictions[index]*100, names[index]);
char buff[1024];
sprintf(buff, "%3.1f%%: %s\n", predictions[index]*100, names[index]);
image label = get_label(alphabet, buff, lh);
draw_label(in, toph, lh, label, rgb);
toph += 2*lh;
free_image(label);
}
show_image(in, base);
free_image(in_s);
free_image(in);

174
examples/detector.c
View File

@ -624,6 +624,177 @@ void test_detector(char *datacfg, char *cfgfile, char *weightfile, char *filenam
}
}
void censor_detector(char *datacfg, char *cfgfile, char *weightfile, int cam_index, const char *filename, int class, float thresh, int skip)
{
image **alphabet = load_alphabet();
char *base = basecfg(cfgfile);
network *net = load_network(cfgfile, weightfile, 0);
set_batch_network(net, 1);
list *options = read_data_cfg(datacfg);
srand(2222222);
CvCapture * cap;
int w = 1280;
int h = 720;
if(filename){
cap = cvCaptureFromFile(filename);
}else{
cap = cvCaptureFromCAM(cam_index);
}
if(w){
cvSetCaptureProperty(cap, CV_CAP_PROP_FRAME_WIDTH, w);
}
if(h){
cvSetCaptureProperty(cap, CV_CAP_PROP_FRAME_HEIGHT, h);
}
int top = option_find_int(options, "top", 1);
char *label_list = option_find_str(options, "labels", 0);
char *name_list = option_find_str(options, "names", label_list);
char **names = get_labels(name_list);
int *indexes = calloc(top, sizeof(int));
if(!cap) error("Couldn't connect to webcam.\n");
cvNamedWindow(base, CV_WINDOW_NORMAL);
cvResizeWindow(base, 512, 512);
float fps = 0;
int i;
int count = 0;
float nms = .45;
while(1){
image in = get_image_from_stream(cap);
//image in_s = resize_image(in, net->w, net->h);
image in_s = letterbox_image(in, net->w, net->h);
layer l = net->layers[net->n-1];
int nboxes = num_boxes(net);
float *X = in_s.data;
network_predict(net, X);
detection *dets = get_network_boxes(net, in.w, in.h, thresh, 0, 0, 0);
//if (nms) do_nms_obj(boxes, probs, l.w*l.h*l.n, l.classes, nms);
if (nms) do_nms_sort(dets, nboxes, l.classes, nms);
for(i = 0; i < nboxes; ++i){
if(dets[i].prob[class] > thresh){
box b = dets[i].bbox;
int left = b.x-b.w/2.;
int top = b.y-b.h/2.;
censor_image(in, left, top, b.w, b.h);
}
}
show_image(in, base);
cvWaitKey(10);
free_detections(dets, num_boxes(net));
free_image(in_s);
free_image(in);
float curr = 0;
fps = .9*fps + .1*curr;
for(i = 0; i < skip; ++i){
image in = get_image_from_stream(cap);
free_image(in);
}
}
}
void extract_detector(char *datacfg, char *cfgfile, char *weightfile, int cam_index, const char *filename, int class, float thresh, int skip)
{
image **alphabet = load_alphabet();
char *base = basecfg(cfgfile);
network *net = load_network(cfgfile, weightfile, 0);
set_batch_network(net, 1);
list *options = read_data_cfg(datacfg);
srand(2222222);
CvCapture * cap;
int w = 1280;
int h = 720;
if(filename){
cap = cvCaptureFromFile(filename);
}else{
cap = cvCaptureFromCAM(cam_index);
}
if(w){
cvSetCaptureProperty(cap, CV_CAP_PROP_FRAME_WIDTH, w);
}
if(h){
cvSetCaptureProperty(cap, CV_CAP_PROP_FRAME_HEIGHT, h);
}
int top = option_find_int(options, "top", 1);
char *label_list = option_find_str(options, "labels", 0);
char *name_list = option_find_str(options, "names", label_list);
char **names = get_labels(name_list);
int *indexes = calloc(top, sizeof(int));
if(!cap) error("Couldn't connect to webcam.\n");
cvNamedWindow(base, CV_WINDOW_NORMAL);
cvResizeWindow(base, 512, 512);
float fps = 0;
int i;
int count = 0;
float nms = .45;
while(1){
image in = get_image_from_stream(cap);
//image in_s = resize_image(in, net->w, net->h);
image in_s = letterbox_image(in, net->w, net->h);
layer l = net->layers[net->n-1];
int nboxes = num_boxes(net);
show_image(in, base);
float *X = in_s.data;
network_predict(net, X);
detection *dets = get_network_boxes(net, in.w, in.h, thresh, 0, 0, 1);
//if (nms) do_nms_obj(boxes, probs, l.w*l.h*l.n, l.classes, nms);
if (nms) do_nms_sort(dets, nboxes, l.classes, nms);
for(i = 0; i < nboxes; ++i){
if(dets[i].prob[class] > thresh){
box b = dets[i].bbox;
int size = b.w*in.w > b.h*in.h ? b.w*in.w : b.h*in.h;
int dx = b.x*in.w-size/2.;
int dy = b.y*in.h-size/2.;
image bim = crop_image(in, dx, dy, size, size);
char buff[2048];
sprintf(buff, "results/extract/%07d", count);
++count;
save_image(bim, buff);
free_image(bim);
}
}
free_detections(dets, num_boxes(net));
free_image(in_s);
free_image(in);
float curr = 0;
fps = .9*fps + .1*curr;
for(i = 0; i < skip; ++i){
image in = get_image_from_stream(cap);
free_image(in);
}
}
}
void network_detect(network *net, image im, float thresh, float hier_thresh, float nms, detection *dets)
{
network_predict_image(net, im);
@ -674,12 +845,15 @@ void run_detector(int argc, char **argv)
int width = find_int_arg(argc, argv, "-w", 0);
int height = find_int_arg(argc, argv, "-h", 0);
int fps = find_int_arg(argc, argv, "-fps", 0);
int class = find_int_arg(argc, argv, "-class", 0);
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, hier_thresh, outfile, fullscreen);
else if(0==strcmp(argv[2], "extract")) extract_detector(datacfg, cfg, weights, cam_index, filename, class, thresh, frame_skip);
else if(0==strcmp(argv[2], "censor")) censor_detector(datacfg, cfg, weights, cam_index, filename, class, thresh, frame_skip);
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, outfile);
else if(0==strcmp(argv[2], "valid2")) validate_detector_flip(datacfg, cfg, weights, outfile);

24
examples/regressor.c
View File

@ -32,6 +32,7 @@ void train_regressor(char *datacfg, char *cfgfile, char *weightfile, int *gpus,
char *backup_directory = option_find_str(options, "backup", "/backup/");
char *train_list = option_find_str(options, "train", "data/train.list");
int classes = option_find_int(options, "classes", 1);
list *plist = get_paths(train_list);
char **paths = (char **)list_to_array(plist);
@ -43,9 +44,10 @@ void train_regressor(char *datacfg, char *cfgfile, char *weightfile, int *gpus,
args.w = net->w;
args.h = net->h;
args.threads = 32;
args.classes = classes;
args.min = net->min_crop;
args.max = net->max_crop;
args.min = net->min_ratio*net->w;
args.max = net->max_ratio*net->w;
args.angle = net->angle;
args.aspect = net->aspect;
args.exposure = net->exposure;
@ -160,6 +162,10 @@ void demo_regressor(char *datacfg, char *cfgfile, char *weightfile, int cam_inde
}else{
cap = cvCaptureFromCAM(cam_index);
}
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);
if(!cap) error("Couldn't connect to webcam.\n");
cvNamedWindow("Regressor", CV_WINDOW_NORMAL);
@ -171,19 +177,23 @@ void demo_regressor(char *datacfg, char *cfgfile, char *weightfile, int cam_inde
gettimeofday(&tval_before, NULL);
image in = get_image_from_stream(cap);
image in_s = letterbox_image(in, net->w, net->h);
show_image(in, "Regressor");
image crop = center_crop_image(in, net->w, net->h);
grayscale_image_3c(crop);
show_image(crop, "Regressor");
float *predictions = network_predict(net, in_s.data);
float *predictions = network_predict(net, crop.data);
printf("\033[2J");
printf("\033[1;1H");
printf("\nFPS:%.0f\n",fps);
printf("People: %f\n", predictions[0]);
int i;
for(i = 0; i < classes; ++i){
printf("%s: %f\n", names[i], predictions[i]);
}
free_image(in_s);
free_image(in);
free_image(crop);
cvWaitKey(10);

4
include/darknet.h
View File

@ -637,6 +637,8 @@ float train_networks(network **nets, int n, data d, int interval);
void sync_nets(network **nets, int n, int interval);
void harmless_update_network_gpu(network *net);
#endif
image get_label(image **characters, char *string, int size);
void draw_label(image a, int r, int c, image label, const float *rgb);
void save_image_png(image im, const char *name);
void get_next_batch(data d, int n, int offset, float *X, float *y);
void grayscale_image_3c(image im);
@ -683,8 +685,10 @@ image load_image(char *filename, int w, int h, int c);
image load_image_color(char *filename, int w, int h);
image make_image(int w, int h, int c);
image resize_image(image im, int w, int h);
void censor_image(image im, int dx, int dy, int w, int h);
image letterbox_image(image im, int w, int h);
image crop_image(image im, int dx, int dy, int w, int h);
image center_crop_image(image im, int w, int h);
image resize_min(image im, int min);
image resize_max(image im, int max);
image threshold_image(image im, float thresh);

53
python/darknet.py
View File

@ -23,6 +23,15 @@ class BOX(Structure):
("w", c_float),
("h", c_float)]
class DETECTION(Structure):
_fields_ = [("bbox", BOX),
("classes", c_int),
("prob", POINTER(c_float)),
("mask", POINTER(c_float)),
("objectness", c_float),
("sort_class", c_int)]
class IMAGE(Structure):
_fields_ = [("w", c_int),
("h", c_int),
@ -53,9 +62,16 @@ make_image = lib.make_image
make_image.argtypes = [c_int, c_int, c_int]
make_image.restype = IMAGE
make_boxes = lib.make_boxes
make_boxes.argtypes = [c_void_p]
make_boxes.restype = POINTER(BOX)
get_network_boxes = lib.get_network_boxes
get_network_boxes.argtypes = [c_void_p, c_int, c_int, c_float, c_float, POINTER(c_int), c_int]
get_network_boxes.restype = POINTER(DETECTION)
make_network_boxes = lib.make_network_boxes
make_network_boxes.argtypes = [c_void_p]
make_network_boxes.restype = POINTER(DETECTION)
free_detections = lib.free_detections
free_detections.argtypes = [POINTER(DETECTION), c_int]
free_ptrs = lib.free_ptrs
free_ptrs.argtypes = [POINTER(c_void_p), c_int]
@ -64,12 +80,8 @@ num_boxes = lib.num_boxes
num_boxes.argtypes = [c_void_p]
num_boxes.restype = c_int
make_probs = lib.make_probs
make_probs.argtypes = [c_void_p]
make_probs.restype = POINTER(POINTER(c_float))
detect = lib.network_predict
detect.argtypes = [c_void_p, IMAGE, c_float, c_float, c_float, POINTER(BOX), POINTER(POINTER(c_float))]
network_predict = lib.network_predict
network_predict.argtypes = [c_void_p, POINTER(c_float)]
reset_rnn = lib.reset_rnn
reset_rnn.argtypes = [c_void_p]
@ -78,6 +90,12 @@ load_net = lib.load_network
load_net.argtypes = [c_char_p, c_char_p, c_int]
load_net.restype = c_void_p
do_nms_obj = lib.do_nms_obj
do_nms_obj.argtypes = [POINTER(DETECTION), c_int, c_int, c_float]
do_nms_sort = lib.do_nms_sort
do_nms_sort.argtypes = [POINTER(DETECTION), c_int, c_int, c_float]
free_image = lib.free_image
free_image.argtypes = [IMAGE]
@ -100,9 +118,6 @@ predict_image = lib.network_predict_image
predict_image.argtypes = [c_void_p, IMAGE]
predict_image.restype = POINTER(c_float)
network_detect = lib.network_detect
network_detect.argtypes = [c_void_p, IMAGE, c_float, c_float, c_float, POINTER(BOX), POINTER(POINTER(c_float))]
def classify(net, meta, im):
out = predict_image(net, im)
res = []
@ -113,18 +128,20 @@ def classify(net, meta, im):
def detect(net, meta, image, thresh=.5, hier_thresh=.5, nms=.45):
im = load_image(image, 0, 0)
boxes = make_boxes(net)
probs = make_probs(net)
num = num_boxes(net)
network_detect(net, im, thresh, hier_thresh, nms, boxes, probs)
predict_image(net, im)
dets = get_network_boxes(net, im.w, im.h, thresh, hier_thresh, None, 0)
if (nms): do_nms_obj(dets, num, meta.classes, nms);
res = []
for j in range(num):
for i in range(meta.classes):
if probs[j][i] > 0:
res.append((meta.names[i], probs[j][i], (boxes[j].x, boxes[j].y, boxes[j].w, boxes[j].h)))
if dets[j].prob[i] > 0:
b = dets[j].bbox
res.append((meta.names[i], dets[j].prob[i], (b.x, b.y, b.w, b.h)))
res = sorted(res, key=lambda x: -x[1])
free_image(im)
free_ptrs(cast(probs, POINTER(c_void_p)), num)
free_detections(dets, num)
return res
if __name__ == "__main__":

35
src/data.c
View File

@ -548,19 +548,22 @@ void fill_hierarchy(float *truth, int k, tree *hierarchy)
}
}
matrix load_regression_labels_paths(char **paths, int n)
matrix load_regression_labels_paths(char **paths, int n, int k)
{
matrix y = make_matrix(n, 1);
int i;
matrix y = make_matrix(n, k);
int i,j;
for(i = 0; i < n; ++i){
char labelpath[4096];
find_replace(paths[i], "images", "targets", labelpath);
find_replace(labelpath, "JPEGImages", "targets", labelpath);
find_replace(paths[i], "images", "labels", labelpath);
find_replace(labelpath, "JPEGImages", "labels", labelpath);
find_replace(labelpath, ".jpg", ".txt", labelpath);
find_replace(labelpath, ".JPG", ".txt", labelpath);
find_replace(labelpath, ".png", ".txt", labelpath);
FILE *file = fopen(labelpath, "r");
fscanf(file, "%f", &(y.vals[i][0]));
for(j = 0; j < k; ++j){
fscanf(file, "%f", &(y.vals[i][j]));
}
fclose(file);
}
return y;
@ -583,18 +586,14 @@ matrix load_tags_paths(char **paths, int n, int k)
{
matrix y = make_matrix(n, k);
int i;
int count = 0;
//int count = 0;
for(i = 0; i < n; ++i){
char label[4096];
find_replace(paths[i], "imgs", "labels", label);
find_replace(label, "_iconl.jpeg", ".txt", label);
find_replace(paths[i], "images", "labels", label);
find_replace(label, ".jpg", ".txt", label);
FILE *file = fopen(label, "r");
if(!file){
find_replace(label, "labels", "labels2", label);
file = fopen(label, "r");
if (!file) continue;
}
++count;
//++count;
int tag;
while(fscanf(file, "%d", &tag) == 1){
if(tag < k){
@ -603,7 +602,7 @@ matrix load_tags_paths(char **paths, int n, int k)
}
fclose(file);
}
printf("%d/%d\n", count, n);
//printf("%d/%d\n", count, n);
return y;
}
@ -1010,7 +1009,7 @@ void *load_thread(void *ptr)
if (a.type == OLD_CLASSIFICATION_DATA){
*a.d = load_data_old(a.paths, a.n, a.m, a.labels, a.classes, a.w, a.h);
} else if (a.type == REGRESSION_DATA){
*a.d = load_data_regression(a.paths, a.n, a.m, a.min, a.max, a.size, a.angle, a.aspect, a.hue, a.saturation, a.exposure);
*a.d = load_data_regression(a.paths, a.n, a.m, a.classes, a.min, a.max, a.size, a.angle, a.aspect, a.hue, a.saturation, a.exposure);
} else if (a.type == CLASSIFICATION_DATA){
*a.d = load_data_augment(a.paths, a.n, a.m, a.labels, a.classes, a.hierarchy, a.min, a.max, a.size, a.angle, a.aspect, a.hue, a.saturation, a.exposure, a.center);
} else if (a.type == SUPER_DATA){
@ -1166,13 +1165,13 @@ data load_data_super(char **paths, int n, int m, int w, int h, int scale)
return d;
}
data load_data_regression(char **paths, int n, int m, int min, int max, int size, float angle, float aspect, float hue, float saturation, float exposure)
data load_data_regression(char **paths, int n, int m, int k, int min, int max, int size, float angle, float aspect, float hue, float saturation, float exposure)
{
if(m) paths = get_random_paths(paths, n, m);
data d = {0};
d.shallow = 0;
d.X = load_image_augment_paths(paths, n, min, max, size, angle, aspect, hue, saturation, exposure, 0);
d.y = load_regression_labels_paths(paths, n);
d.y = load_regression_labels_paths(paths, n, k);
if(m) free(paths);
return d;
}

2
src/data.h
View File

@ -29,7 +29,7 @@ data load_data_tag(char **paths, int n, int m, int k, int min, int max, int size
matrix load_image_augment_paths(char **paths, int n, int min, int max, int size, float angle, float aspect, float hue, float saturation, float exposure, int center);
data load_data_super(char **paths, int n, int m, int w, int h, int scale);
data load_data_augment(char **paths, int n, int m, char **labels, int k, tree *hierarchy, int min, int max, int size, float angle, float aspect, float hue, float saturation, float exposure, int center);
data load_data_regression(char **paths, int n, int m, int min, int max, int size, float angle, float aspect, float hue, float saturation, float exposure);
data load_data_regression(char **paths, int n, int m, int classes, int min, int max, int size, float angle, float aspect, float hue, float saturation, float exposure);
data load_go(char *filename);

32
src/image.c
View File

@ -131,6 +131,7 @@ image tile_images(image a, image b, int dx)
image get_label(image **characters, char *string, int size)
{
size = size/10;
if(size > 7) size = 7;
image label = make_empty_image(0,0,0);
while(*string){
@ -291,7 +292,7 @@ void draw_detections(image im, detection *dets, int num, float thresh, char **na
draw_box_width(im, left, top, right, bot, width, red, green, blue);
if (alphabet) {
image label = get_label(alphabet, labelstr, (im.h*.03)/10);
image label = get_label(alphabet, labelstr, (im.h*.03));
draw_label(im, top + width, left, label, rgb);
free_image(label);
}
@ -395,6 +396,35 @@ void ghost_image(image source, image dest, int dx, int dy)
}
}
void blocky_image(image im, int s)
{
int i,j,k;
for(k = 0; k < im.c; ++k){
for(j = 0; j < im.h; ++j){
for(i = 0; i < im.w; ++i){
im.data[i + im.w*(j + im.h*k)] = im.data[i/s*s + im.w*(j/s*s + im.h*k)];
}
}
}
}
void censor_image(image im, int dx, int dy, int w, int h)
{
int i,j,k;
int s = 32;
if(dx < 0) dx = 0;
if(dy < 0) dy = 0;
for(k = 0; k < im.c; ++k){
for(j = dy; j < dy + h && j < im.h; ++j){
for(i = dx; i < dx + w && i < im.w; ++i){
im.data[i + im.w*(j + im.h*k)] = im.data[i/s*s + im.w*(j/s*s + im.h*k)];
//im.data[i + j*im.w + k*im.w*im.h] = 0;
}
}
}
}
void embed_image(image source, image dest, int dx, int dy)
{
int x,y,k;

2
src/image.h
View File

@ -22,12 +22,10 @@ void show_image_cv(image p, const char *name, IplImage *disp);
float get_color(int c, int x, int max);
void draw_box(image a, int x1, int y1, int x2, int y2, float r, float g, float b);
void draw_bbox(image a, box bbox, int w, float r, float g, float b);
void draw_label(image a, int r, int c, image label, const float *rgb);
void write_label(image a, int r, int c, image *characters, char *string, float *rgb);
image image_distance(image a, image b);
void scale_image(image m, float s);
image rotate_crop_image(image im, float rad, float s, int w, int h, float dx, float dy, float aspect);
image center_crop_image(image im, int w, int h);
image random_crop_image(image im, int w, int h);
image random_augment_image(image im, float angle, float aspect, int low, int high, int w, int h);
augment_args random_augment_args(image im, float angle, float aspect, int low, int high, int w, int h);

2
src/region_layer.c
View File

@ -582,7 +582,7 @@ void backward_region_layer_gpu(const layer l, network net)
gradient_array_gpu(l.output_gpu + index, (l.coords - 4)*l.w*l.h, LOGISTIC, l.delta_gpu + index);
}
index = entry_index(l, b, n*l.w*l.h, l.coords);
if(!l.background) gradient_array_gpu(l.output_gpu + index, l.w*l.h, LOGISTIC, l.delta_gpu + index);
//if(!l.background) gradient_array_gpu(l.output_gpu + index, l.w*l.h, LOGISTIC, l.delta_gpu + index);
}
}
axpy_gpu(l.batch*l.inputs, 1, l.delta_gpu, 1, net.delta_gpu, 1);