From 1fd10265f8a63d1b1305f40111a97518f5541da2 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Tue, 07 Apr 2015 22:25:30 +0000
Subject: [PATCH] detection better?
---
src/data.c | 121 +++++++++++++++++++++++++---------------
1 files changed, 76 insertions(+), 45 deletions(-)
diff --git a/src/data.c b/src/data.c
index f3e0adc..6a05d41 100644
--- a/src/data.c
+++ b/src/data.c
@@ -17,7 +17,6 @@
int nh;
int nw;
int num_boxes;
- int jitter;
int classes;
int background;
data *d;
@@ -109,12 +108,14 @@
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)
{
- char *labelpath = find_replace(path, "VOC2012/JPEGImages", "labels");
+ char *labelpath = find_replace(path, "detection_images", "labels");
labelpath = find_replace(labelpath, ".jpg", ".txt");
+ labelpath = find_replace(labelpath, ".JPEG", ".txt");
int count = 0;
box *boxes = read_boxes(labelpath, &count);
randomize_boxes(boxes, count);
- float l,r,t,b;
+ float x,y,w,h;
+ float left, top, right, bot;
int id;
int i;
if(background){
@@ -123,46 +124,58 @@
}
}
for(i = 0; i < count; ++i){
- l = boxes[i].left;
- r = boxes[i].right;
- t = boxes[i].top;
- b = boxes[i].bottom;
+ left = boxes[i].left * sx - dx;
+ right = boxes[i].right * sx - dx;
+ top = boxes[i].top * sy - dy;
+ bot = boxes[i].bottom* sy - dy;
id = boxes[i].id;
if(flip){
- float left = l;
- float right = r;
- r = 1-left;
- l = 1-right;
+ float swap = left;
+ left = 1. - right;
+ right = 1. - swap;
}
- l = l*sx-dx;
- r = r*sx-dx;
- t = t*sy-dy;
- b = b*sy-dy;
-
- float x = (l+r)/2.;
- float y = (t+b)/2.;
+ left = constrain(0, 1, left);
+ right = constrain(0, 1, right);
+ top = constrain(0, 1, top);
+ bot = constrain(0, 1, bot);
- if (x < 0 || x >= 1 || y < 0 || y >= 1) continue;
+ x = (left+right)/2;
+ y = (top+bot)/2;
+ w = (right - left);
+ h = (bot - top);
+
+ 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);
+ x = x*num_boxes - i;
+ y = y*num_boxes - j;
+
+ /*
+ float maxwidth = distance_from_edge(i, num_boxes);
+ float maxheight = distance_from_edge(j, num_boxes);
+ w = w/maxwidth;
+ h = h/maxheight;
+ */
+
+ w = constrain(0, 1, w);
+ h = constrain(0, 1, h);
+ if (w == 0 || h == 0) continue;
+ w = sqrt(w);
+ h = sqrt(h);
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++] = l;
- truth[index++] = r;
- truth[index++] = t;
- truth[index++] = b;
+ truth[index++] = y;
+ truth[index++] = x;
+ truth[index++] = h;
+ truth[index++] = w;
}
free(boxes);
}
@@ -279,32 +292,51 @@
}
}
-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_detection_jitter_random(int n, char **paths, int m, int classes, int h, int w, int num_boxes, 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);
+
+ d.X.rows = n;
+ d.X.vals = calloc(d.X.rows, sizeof(float*));
+ d.X.cols = h*w*3;
+
int k = num_boxes*num_boxes*(4+classes+background);
d.y = make_matrix(n, k);
for(i = 0; i < n; ++i){
- 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);
+ image orig = load_image_color(random_paths[i], 0, 0);
+ int oh = orig.h;
+ int ow = orig.w;
+
+ int dw = ow/10;
+ int dh = oh/10;
+
+ int pleft = (rand_uniform() * 2*dw - dw);
+ int pright = (rand_uniform() * 2*dw - dw);
+ int ptop = (rand_uniform() * 2*dh - dh);
+ int pbot = (rand_uniform() * 2*dh - dh);
+
+ int swidth = ow - pleft - pright;
+ int sheight = oh - ptop - pbot;
+
+ float sx = (float)swidth / ow;
+ float sy = (float)sheight / oh;
int flip = rand()%2;
- 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, py, px);
+ image cropped = crop_image(orig, ptop, pleft, sheight, swidth);
+ float dx = ((float)pleft/ow)/sx;
+ float dy = ((float)ptop /oh)/sy;
+
+ free_image(orig);
+ image sized = resize_image(cropped, h, w);
+ free_image(cropped);
+ if(flip) flip_image(sized);
+ d.X.vals[i] = sized.data;
+
+ fill_truth_detection(random_paths[i], d.y.vals[i], classes, num_boxes, flip, background, dx, dy, 1./sx, 1./sy);
}
- d.X.cols = (h-jitter)*(w-jitter)*3;
free(random_paths);
return d;
}
@@ -313,14 +345,14 @@
{
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.num_boxes, 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.background);
translate_data_rows(*a.d, -128);
scale_data_rows(*a.d, 1./128);
free(ptr);
return 0;
}
-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)
+pthread_t load_data_detection_thread(int n, char **paths, int m, int classes, int h, int w, int nh, int nw, int background, data *d)
{
pthread_t thread;
struct load_args *args = calloc(1, sizeof(struct load_args));
@@ -333,7 +365,6 @@
args->nw = nw;
args->num_boxes = nw;
args->classes = classes;
- args->jitter = jitter;
args->background = background;
args->d = d;
if(pthread_create(&thread, 0, load_detection_thread, args)) {
--
Gitblit v1.10.0