From a05c4bd2e99eead9e553241246b54409dac07c87 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Wed, 01 Apr 2015 17:25:50 +0000
Subject: [PATCH] sqrt
---
src/data.c | 131 +++++++++++++++++++++++++++++--------------
1 files changed, 87 insertions(+), 44 deletions(-)
diff --git a/src/data.c b/src/data.c
index c1167da..71d52d4 100644
--- a/src/data.c
+++ b/src/data.c
@@ -16,7 +16,7 @@
int w;
int nh;
int nw;
- int jitter;
+ int num_boxes;
int classes;
int background;
data *d;
@@ -106,56 +106,75 @@
}
}
-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 x,y,w,h;
+ float left, top, right, bot;
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;
+ 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) 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;
-
- 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 );
+ if(flip){
+ float swap = left;
+ left = 1. - right;
+ right = 1. - swap;
+ }
- int index = (i+j*num_width)*(4+classes+background);
+ left = constrain(0, 1, left);
+ right = constrain(0, 1, right);
+ top = constrain(0, 1, top);
+ bot = constrain(0, 1, bot);
+
+ 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);
+
+ 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++] = dh;
- truth[index++] = dw;
- truth[index++] = th;
- truth[index++] = tw;
+ truth[index++] = y;
+ truth[index++] = x;
+ truth[index++] = h;
+ truth[index++] = w;
}
free(boxes);
}
@@ -272,25 +291,49 @@
}
}
-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 background)
{
+ //float minscale = 0.85;
+ //float maxscale = 1.15;
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);
+
+ 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 dx = rand()%jitter;
- int dy = rand()%jitter;
+ image orig = load_image_color(random_paths[i], 0, 0);
+ int oh = orig.h;
+ int ow = orig.w;
+ int pleft = (rand_uniform() * 64. - 32.);
+ int pright = (rand_uniform() * 64. - 32.);
+ int ptop = (rand_uniform() * 64. - 32.);
+ int pbot = (rand_uniform() * 64. - 32.);
+
+ 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, h-jitter, w-jitter, nh, nw, dy, dx, jitter, flip, background);
- 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);
+ 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;
}
@@ -299,14 +342,14 @@
{
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.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.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));
@@ -317,8 +360,8 @@
args->w = w;
args->nh = nh;
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