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

sides of box instead of coords

Browse Source
pull/5299/head
Joseph Redmon 10 years ago
parent 6553b3f0e3
commit ad59d7e68e
3 changed files with 65 additions and 54 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. 89
      src/data.c
  2. 2
      src/data.h
  3. 28
      src/detection.c

89
src/data.c
Unescape View File

@ -16,6 +16,7 @@ struct load_args{
int w;
int nh;
int nw;
int num_boxes;
int jitter;
int classes;
int background;
@ -106,56 +107,62 @@ void randomize_boxes(box *b, int n)
}
}
void fill_truth_detection(char *path, float *truth, int classes, int height, int width, int num_height, int num_width, int dy, int dx, int jitter, int flip, int background)
void fill_truth_detection(char *path, float *truth, int classes, int num_boxes, int flip, int background, float dx, float dy, float sx, float sy)
{
int box_height = height/num_height;
int box_width = width/num_width;
char *labelpath = find_replace(path, "VOC2012/JPEGImages", "labels");
labelpath = find_replace(labelpath, ".jpg", ".txt");
int count = 0;
box *boxes = read_boxes(labelpath, &count);
randomize_boxes(boxes, count);
float x, y, h, w;
float l,r,t,b;
int id;
int i;
if(background){
for(i = 0; i < num_height*num_width*(4+classes+background); i += 4+classes+background){
for(i = 0; i < num_boxes*num_boxes*(4+classes+background); i += 4+classes+background){
truth[i] = 1;
}
}
for(i = 0; i < count; ++i){
x = boxes[i].x;
y = boxes[i].y;
w = boxes[i].w;
h = boxes[i].h;
l = boxes[i].left;
r = boxes[i].right;
t = boxes[i].top;
b = boxes[i].bottom;
id = boxes[i].id;
if(flip) x = 1-x;
x *= width + jitter;
y *= height + jitter;
x -= dx;
y -= dy;
int i = x/box_width;
int j = y/box_height;
if(i < 0) i = 0;
if(i >= num_width) i = num_width-1;
if(j < 0) j = 0;
if(j >= num_height) j = num_height-1;
if(flip){
float left = l;
float right = r;
r = 1-left;
l = 1-right;
}
l = l*sx-dx;
r = r*sx-dx;
t = t*sy-dy;
b = b*sy-dy;
float dw = constrain(0,1, (x - i*box_width)/box_width );
float dh = constrain(0,1, (y - j*box_height)/box_height );
float th = constrain(0,1, h*(height+jitter)/height );
float tw = constrain(0,1, w*(width+jitter)/width );
float x = (l+r)/2.;
float y = (t+b)/2.;
int index = (i+j*num_width)*(4+classes+background);
if (x < 0 || x >= 1 || y < 0 || y >= 1) continue;
int i = (int)(x*num_boxes);
int j = (int)(y*num_boxes);
l = constrain(0, 1, l);
r = constrain(0, 1, r);
t = constrain(0, 1, t);
b = constrain(0, 1, b);
int index = (i+j*num_boxes)*(4+classes+background);
if(truth[index+classes+background+2]) continue;
if(background) truth[index++] = 0;
truth[index+id] = 1;
index += classes;
truth[index++] = dh;
truth[index++] = dw;
truth[index++] = th;
truth[index++] = tw;
truth[index++] = l;
truth[index++] = r;
truth[index++] = t;
truth[index++] = b;
}
free(boxes);
}
@ -272,23 +279,30 @@ void free_data(data d)
}
}
data load_data_detection_jitter_random(int n, char **paths, int m, int classes, int h, int w, int nh, int nw, int jitter, int background)
data load_data_detection_jitter_random(int n, char **paths, int m, int classes, int h, int w, int num_boxes, int jitter, int background)
{
char **random_paths = get_random_paths(paths, n, m);
int i;
data d;
d.shallow = 0;
d.X = load_image_paths(random_paths, n, h, w);
int k = nh*nw*(4+classes+background);
int k = num_boxes*num_boxes*(4+classes+background);
d.y = make_matrix(n, k);
for(i = 0; i < n; ++i){
int dx = rand()%jitter;
int dy = rand()%jitter;
int px = rand()%jitter;
px = 0;
int py = rand()%jitter;
py = 0;
float sy = (float) h / (h-jitter);
float sx = (float) w / (w-jitter);
float dy = (float) py / (h-jitter);
float dx = (float) px / (w-jitter);
int flip = rand()%2;
fill_truth_detection(random_paths[i], d.y.vals[i], classes, h-jitter, w-jitter, nh, nw, dy, dx, jitter, flip, background);
fill_truth_detection(random_paths[i], d.y.vals[i], classes, num_boxes, flip, background, dx, dy, sx, sy);
image a = float_to_image(h, w, 3, d.X.vals[i]);
if(flip) flip_image(a);
jitter_image(a,h-jitter,w-jitter,dy,dx);
jitter_image(a, h-jitter, w-jitter, py, px);
}
d.X.cols = (h-jitter)*(w-jitter)*3;
free(random_paths);
@ -299,7 +313,7 @@ void *load_detection_thread(void *ptr)
{
printf("Loading data: %d\n", rand());
struct load_args a = *(struct load_args*)ptr;
*a.d = load_data_detection_jitter_random(a.n, a.paths, a.m, a.classes, a.h, a.w, a.nh, a.nw, a.jitter, a.background);
*a.d = load_data_detection_jitter_random(a.n, a.paths, a.m, a.classes, a.h, a.w, a.num_boxes, a.jitter, a.background);
translate_data_rows(*a.d, -128);
scale_data_rows(*a.d, 1./128);
free(ptr);
@ -317,6 +331,7 @@ pthread_t load_data_detection_thread(int n, char **paths, int m, int classes, in
args->w = w;
args->nh = nh;
args->nw = nw;
args->num_boxes = nw;
args->classes = classes;
args->jitter = jitter;
args->background = background;

2
src/data.h
Unescape View File

@ -21,7 +21,7 @@ data load_data(char **paths, int n, int m, char **labels, int k, int h, int w);
pthread_t load_data_thread(char **paths, int n, int m, char **labels, int k, int h, int w, data *d);
pthread_t load_data_detection_thread(int n, char **paths, int m, int classes, int h, int w, int nh, int nw, int jitter, int background, data *d);
data load_data_detection_jitter_random(int n, char **paths, int m, int classes, int h, int w, int nh, int nw, int jitter, int background);
data load_data_detection_jitter_random(int n, char **paths, int m, int classes, int h, int w, int num_boxes, int jitter, int background);
data load_data_image_pathfile(char *filename, char **labels, int k, int h, int w);
data load_cifar10_data(char *filename);

28
src/detection.c
Unescape View File

@ -27,12 +27,11 @@ void draw_detection(image im, float *box, int side)
float blue = get_color(2,class,classes);
j += classes;
int d = im.w/side;
int y = r*d+box[j]*d;
int x = c*d+box[j+1]*d;
int h = box[j+2]*im.h;
int w = box[j+3]*im.w;
draw_box(im, x-w/2, y-h/2, x+w/2, y+h/2,red,green,blue);
int left = box[j] *im.w;
int right = box[j+1]*im.w;
int top = box[j+2]*im.h;
int bot = box[j+3]*im.h;
draw_box(im, left, top, right, bot, red, green, blue);
}
}
}
@ -138,17 +137,14 @@ void validate_detection(char *cfgfile, char *weightfile)
for(j = 0; j < pred.rows; ++j){
for(k = 0; k < pred.cols; k += classes+4+background+nuisance){
float scale = 1.;
if(nuisance) scale = 1.-pred.vals[j][k];
for(class = 0; class < classes; ++class){
int index = (k)/(classes+4+background+nuisance);
int r = index/7;
int c = index%7;
if (nuisance) scale = 1.-pred.vals[j][k];
for (class = 0; class < classes; ++class){
int ci = k+classes+background+nuisance;
float y = (r + pred.vals[j][ci + 0])/7.;
float x = (c + pred.vals[j][ci + 1])/7.;
float h = pred.vals[j][ci + 2];
float w = pred.vals[j][ci + 3];
printf("%d %d %f %f %f %f %f\n", (i-1)*m/splits + j, class, scale*pred.vals[j][k+class+background+nuisance], y, x, h, w);
float left = pred.vals[j][ci + 0];
float right = pred.vals[j][ci + 1];
float top = pred.vals[j][ci + 2];
float bot = pred.vals[j][ci + 3];
printf("%d %d %f %f %f %f %f\n", (i-1)*m/splits + j, class, scale*pred.vals[j][k+class+background+nuisance], left, right, top, bot);
}
}
}

Write Preview
Loading…
Cancel
Save