From 989ab8c38a02fa7ea9c25108151736c62e81c972 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Fri, 24 Apr 2015 17:27:50 +0000
Subject: [PATCH] IOU loss function
---
src/data.c | 300 +++++++++++++++++++++++++++++++++++++++++++----------------
1 files changed, 217 insertions(+), 83 deletions(-)
diff --git a/src/data.c b/src/data.c
index 0c93597..f1f5b80 100644
--- a/src/data.c
+++ b/src/data.c
@@ -6,6 +6,8 @@
#include <stdlib.h>
#include <string.h>
+unsigned int data_seed;
+
struct load_args{
char **paths;
int n;
@@ -16,8 +18,9 @@
int w;
int nh;
int nw;
- int jitter;
+ int num_boxes;
int classes;
+ int background;
data *d;
};
@@ -39,14 +42,14 @@
char **random_paths = calloc(n, sizeof(char*));
int i;
for(i = 0; i < n; ++i){
- int index = rand()%m;
+ int index = rand_r(&data_seed)%m;
random_paths[i] = paths[index];
if(i == 0) printf("%s\n", paths[index]);
}
return random_paths;
}
-matrix load_image_paths(char **paths, int n, int h, int w)
+matrix load_image_paths(char **paths, int n, int w, int h)
{
int i;
matrix X;
@@ -55,55 +58,128 @@
X.cols = 0;
for(i = 0; i < n; ++i){
- image im = load_image_color(paths[i], h, w);
+ image im = load_image_color(paths[i], w, h);
X.vals[i] = im.data;
X.cols = im.h*im.w*im.c;
}
return X;
}
-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)
+typedef struct{
+ int id;
+ float x,y,w,h;
+ float left, right, top, bottom;
+} box_label;
+
+box_label *read_boxes(char *filename, int *n)
{
- 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");
- FILE *file = fopen(labelpath, "r");
- if(!file) file_error(labelpath);
+ box_label *boxes = calloc(1, sizeof(box_label));
+ FILE *file = fopen(filename, "r");
+ if(!file) file_error(filename);
float x, y, h, w;
int id;
+ int count = 0;
while(fscanf(file, "%d %f %f %f %f", &id, &x, &y, &w, &h) == 5){
- 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 = (x - i*box_width)/box_width;
- float dh = (y - j*box_height)/box_height;
- //printf("%d %d %d %f %f\n", id, i, j, dh, dw);
- int index = (i+j*num_width)*(4+classes);
- truth[index+id] = 1;
- index += classes;
- truth[index++] = dh;
- truth[index++] = dw;
- truth[index++] = h*(height+jitter)/height;
- truth[index++] = w*(width+jitter)/width;
- }
- int i, j;
- for(i = 0; i < num_height*num_width*(4+classes); i += 4+classes){
- int background = 1;
- for(j = i; j < i+classes; ++j) if (truth[j]) background = 0;
- truth[i+classes-1] = background;
+ boxes = realloc(boxes, (count+1)*sizeof(box_label));
+ boxes[count].id = id;
+ boxes[count].x = x;
+ boxes[count].y = y;
+ boxes[count].h = h;
+ boxes[count].w = w;
+ boxes[count].left = x - w/2;
+ boxes[count].right = x + w/2;
+ boxes[count].top = y - h/2;
+ boxes[count].bottom = y + h/2;
+ ++count;
}
fclose(file);
+ *n = count;
+ return boxes;
+}
+
+void randomize_boxes(box_label *b, int n)
+{
+ int i;
+ for(i = 0; i < n; ++i){
+ box_label swap = b[i];
+ int index = rand_r(&data_seed)%n;
+ b[i] = b[index];
+ b[index] = swap;
+ }
+}
+
+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, "detection_images", "labels");
+ labelpath = find_replace(labelpath, ".jpg", ".txt");
+ labelpath = find_replace(labelpath, ".JPEG", ".txt");
+ int count = 0;
+ box_label *boxes = read_boxes(labelpath, &count);
+ randomize_boxes(boxes, count);
+ float x,y,w,h;
+ float left, top, right, bot;
+ int id;
+ int i;
+ if(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){
+ 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 swap = left;
+ left = 1. - right;
+ right = 1. - swap;
+ }
+
+ 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++] = x;
+ truth[index++] = y;
+ truth[index++] = w;
+ truth[index++] = h;
+ }
+ free(boxes);
}
#define NUMCHARS 37
@@ -133,12 +209,12 @@
}
}
-data load_data_captcha(char **paths, int n, int m, int k, int h, int w)
+data load_data_captcha(char **paths, int n, int m, int k, int w, int h)
{
if(m) paths = get_random_paths(paths, n, m);
data d;
d.shallow = 0;
- d.X = load_image_paths(paths, n, h, w);
+ d.X = load_image_paths(paths, n, w, h);
d.y = make_matrix(n, k*NUMCHARS);
int i;
for(i = 0; i < n; ++i){
@@ -148,6 +224,17 @@
return d;
}
+data load_data_captcha_encode(char **paths, int n, int m, int w, int h)
+{
+ if(m) paths = get_random_paths(paths, n, m);
+ data d;
+ d.shallow = 0;
+ d.X = load_image_paths(paths, n, w, h);
+ d.X.cols = 17100;
+ d.y = d.X;
+ if(m) free(paths);
+ return d;
+}
void fill_truth(char *path, char **labels, int k, float *truth)
{
@@ -173,21 +260,6 @@
return y;
}
-data load_data_image_pathfile(char *filename, char **labels, int k, int h, int w)
-{
- list *plist = get_paths(filename);
- char **paths = (char **)list_to_array(plist);
- int n = plist->size;
- data d;
- d.shallow = 0;
- d.X = load_image_paths(paths, n, h, w);
- d.y = load_labels_paths(paths, n, labels, k);
- free_list_contents(plist);
- free_list(plist);
- free(paths);
- return d;
-}
-
char **get_labels(char *filename)
{
list *plist = get_paths(filename);
@@ -207,40 +279,78 @@
}
}
-data load_data_detection_jitter_random(int n, char **paths, int m, int classes, int h, int w, int nh, int nw, int jitter)
+data load_data_detection_jitter_random(int n, char **paths, int m, int classes, int w, int h, 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);
- int k = nh*nw*(4+classes);
+
+ 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;
- 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);
- 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 orig = load_image_color(random_paths[i], 0, 0);
+ float exposure = rand_uniform()+1;
+ if(rand_uniform() > .5) exposure = 1/exposure;
+
+ float saturation = rand_uniform()+1;
+ if(rand_uniform() > .5) saturation = 1/saturation;
+
+ 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;
+
+ /*
+ float angle = rand_uniform()*.1 - .05;
+ image rot = rotate_image(orig, angle);
+ free_image(orig);
+ orig = rot;
+ */
+
+ int flip = rand_r(&data_seed)%2;
+ image cropped = crop_image(orig, pleft, ptop, swidth, sheight);
+ float dx = ((float)pleft/ow)/sx;
+ float dy = ((float)ptop /oh)/sy;
+
+ free_image(orig);
+ image sized = resize_image(cropped, w, h);
+ 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;
}
void *load_detection_thread(void *ptr)
{
+ printf("Loading data: %d\n", rand_r(&data_seed));
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);
- translate_data_rows(*a.d, -128);
- scale_data_rows(*a.d, 1./128);
+ *a.d = load_data_detection_jitter_random(a.n, a.paths, a.m, a.classes, a.w, a.h, a.num_boxes, a.background);
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, data *d)
+pthread_t load_data_detection_thread(int n, char **paths, int m, int classes, int w, int h, int nh, int nw, int background, data *d)
{
pthread_t thread;
struct load_args *args = calloc(1, sizeof(struct load_args));
@@ -251,8 +361,9 @@
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)) {
error("Thread creation failed");
@@ -260,12 +371,12 @@
return thread;
}
-data load_data(char **paths, int n, int m, char **labels, int k, int h, int w)
+data load_data(char **paths, int n, int m, char **labels, int k, int w, int h)
{
if(m) paths = get_random_paths(paths, n, m);
data d;
d.shallow = 0;
- d.X = load_image_paths(paths, n, h, w);
+ d.X = load_image_paths(paths, n, w, h);
d.y = load_labels_paths(paths, n, labels, k);
if(m) free(paths);
return d;
@@ -274,14 +385,12 @@
void *load_in_thread(void *ptr)
{
struct load_args a = *(struct load_args*)ptr;
- *a.d = load_data(a.paths, a.n, a.m, a.labels, a.k, a.h, a.w);
- translate_data_rows(*a.d, -128);
- scale_data_rows(*a.d, 1./128);
+ *a.d = load_data(a.paths, a.n, a.m, a.labels, a.k, a.w, a.h);
free(ptr);
return 0;
}
-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_thread(char **paths, int n, int m, char **labels, int k, int w, int h, data *d)
{
pthread_t thread;
struct load_args *args = calloc(1, sizeof(struct load_args));
@@ -299,6 +408,31 @@
return thread;
}
+matrix concat_matrix(matrix m1, matrix m2)
+{
+ int i, count = 0;
+ matrix m;
+ m.cols = m1.cols;
+ m.rows = m1.rows+m2.rows;
+ m.vals = calloc(m1.rows + m2.rows, sizeof(float*));
+ for(i = 0; i < m1.rows; ++i){
+ m.vals[count++] = m1.vals[i];
+ }
+ for(i = 0; i < m2.rows; ++i){
+ m.vals[count++] = m2.vals[i];
+ }
+ return m;
+}
+
+data concat_data(data d1, data d2)
+{
+ data d;
+ d.shallow = 1;
+ d.X = concat_matrix(d1.X, d2.X);
+ d.y = concat_matrix(d1.y, d2.y);
+ return d;
+}
+
data load_categorical_data_csv(char *filename, int target, int k)
{
data d;
@@ -337,7 +471,7 @@
X.vals[i][j] = (double)bytes[j+1];
}
}
- translate_data_rows(d, -144);
+ translate_data_rows(d, -128);
scale_data_rows(d, 1./128);
//normalize_data_rows(d);
fclose(fp);
@@ -348,7 +482,7 @@
{
int j;
for(j = 0; j < n; ++j){
- int index = rand()%d.X.rows;
+ int index = rand_r(&data_seed)%d.X.rows;
memcpy(X+j*d.X.cols, d.X.vals[index], d.X.cols*sizeof(float));
memcpy(y+j*d.y.cols, d.y.vals[index], d.y.cols*sizeof(float));
}
@@ -393,7 +527,7 @@
fclose(fp);
}
//normalize_data_rows(d);
- translate_data_rows(d, -144);
+ translate_data_rows(d, -128);
scale_data_rows(d, 1./128);
return d;
}
@@ -402,7 +536,7 @@
{
int i;
for(i = d.X.rows-1; i > 0; --i){
- int index = rand()%i;
+ int index = rand_r(&data_seed)%i;
float *swap = d.X.vals[index];
d.X.vals[index] = d.X.vals[i];
d.X.vals[i] = swap;
--
Gitblit v1.10.0