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 | 377 ++++++++++++++++++++++++++++++++++++++++++++---------
1 files changed, 312 insertions(+), 65 deletions(-)
diff --git a/src/data.c b/src/data.c
index 9b57391..6a05d41 100644
--- a/src/data.c
+++ b/src/data.c
@@ -6,6 +6,22 @@
#include <stdlib.h>
#include <string.h>
+struct load_args{
+ char **paths;
+ int n;
+ int m;
+ char **labels;
+ int k;
+ int h;
+ int w;
+ int nh;
+ int nw;
+ int num_boxes;
+ int classes;
+ int background;
+ data *d;
+};
+
list *get_paths(char *filename)
{
char *path;
@@ -19,39 +35,16 @@
return lines;
}
-void fill_truth_detection(char *path, float *truth, int height, int width, int num_height, int num_width, float scale)
+char **get_random_paths(char **paths, int n, int m)
{
- int box_height = height/num_height;
- int box_width = width/num_width;
- char *labelpath = find_replace(path, "imgs", "det");
- labelpath = find_replace(labelpath, ".JPEG", ".txt");
- FILE *file = fopen(labelpath, "r");
- int x, y, h, w;
- while(fscanf(file, "%d %d %d %d", &x, &y, &w, &h) == 4){
- int i = x/box_width;
- int j = y/box_height;
- float dh = (float)(x%box_width)/box_height;
- float dw = (float)(y%box_width)/box_width;
- float sh = h/scale;
- float sw = w/scale;
- int index = (i+j*num_width)*5;
- truth[index++] = 1;
- truth[index++] = dh;
- truth[index++] = dw;
- truth[index++] = sh;
- truth[index++] = sw;
- }
-}
-
-void fill_truth(char *path, char **labels, int k, float *truth)
-{
+ char **random_paths = calloc(n, sizeof(char*));
int i;
- memset(truth, 0, k*sizeof(float));
- for(i = 0; i < k; ++i){
- if(strstr(path, labels[i])){
- truth[i] = 1;
- }
+ for(i = 0; i < n; ++i){
+ int index = rand()%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)
@@ -70,27 +63,201 @@
return X;
}
+typedef struct box{
+ int id;
+ float x,y,w,h;
+ float left, right, top, bottom;
+} box;
+
+box *read_boxes(char *filename, int *n)
+{
+ box *boxes = calloc(1, sizeof(box));
+ 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){
+ boxes = realloc(boxes, (count+1)*sizeof(box));
+ 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 *b, int n)
+{
+ int i;
+ for(i = 0; i < n; ++i){
+ box swap = b[i];
+ int index = rand()%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 *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++] = y;
+ truth[index++] = x;
+ truth[index++] = h;
+ truth[index++] = w;
+ }
+ free(boxes);
+}
+
+#define NUMCHARS 37
+
+void print_letters(float *pred, int n)
+{
+ int i;
+ for(i = 0; i < n; ++i){
+ int index = max_index(pred+i*NUMCHARS, NUMCHARS);
+ printf("%c", int_to_alphanum(index));
+ }
+ printf("\n");
+}
+
+void fill_truth_captcha(char *path, int n, float *truth)
+{
+ char *begin = strrchr(path, '/');
+ ++begin;
+ int i;
+ for(i = 0; i < strlen(begin) && i < n && begin[i] != '.'; ++i){
+ int index = alphanum_to_int(begin[i]);
+ if(index > 35) printf("Bad %c\n", begin[i]);
+ truth[i*NUMCHARS+index] = 1;
+ }
+ for(;i < n; ++i){
+ truth[i*NUMCHARS + NUMCHARS-1] = 1;
+ }
+}
+
+data load_data_captcha(char **paths, int n, int m, int k, int h, int w)
+{
+ if(m) paths = get_random_paths(paths, n, m);
+ data d;
+ d.shallow = 0;
+ d.X = load_image_paths(paths, n, h, w);
+ d.y = make_matrix(n, k*NUMCHARS);
+ int i;
+ for(i = 0; i < n; ++i){
+ fill_truth_captcha(paths[i], k, d.y.vals[i]);
+ }
+ if(m) free(paths);
+ return d;
+}
+
+data load_data_captcha_encode(char **paths, int n, int m, int h, int w)
+{
+ 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.cols = 17100;
+ d.y = d.X;
+ if(m) free(paths);
+ return d;
+}
+
+void fill_truth(char *path, char **labels, int k, float *truth)
+{
+ int i;
+ memset(truth, 0, k*sizeof(float));
+ int count = 0;
+ for(i = 0; i < k; ++i){
+ if(strstr(path, labels[i])){
+ truth[i] = 1;
+ ++count;
+ }
+ }
+ if(count != 1) printf("%d, %s\n", count, path);
+}
+
matrix load_labels_paths(char **paths, int n, char **labels, int k)
{
matrix y = make_matrix(n, k);
int i;
- for(i = 0; i < n; ++i){
+ for(i = 0; i < n && labels; ++i){
fill_truth(paths[i], labels, k, y.vals[i]);
}
return y;
}
-matrix load_labels_detection(char **paths, int n, int height, int width, int num_height, int num_width, float scale)
-{
- int k = num_height*num_width*5;
- matrix y = make_matrix(n, k);
- int i;
- for(i = 0; i < n; ++i){
- fill_truth_detection(paths[i], y.vals[i], height, width, num_height, num_width, scale);
- }
- return y;
-}
-
data load_data_image_pathfile(char *filename, char **labels, int k, int h, int w)
{
list *plist = get_paths(filename);
@@ -125,44 +292,124 @@
}
}
-data load_data_detection_random(int n, char **paths, int m, char **labels, int h, int w, int nh, int nw, float scale)
+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 = calloc(n, sizeof(char*));
+ char **random_paths = get_random_paths(paths, n, m);
int i;
- for(i = 0; i < n; ++i){
- int index = rand()%m;
- random_paths[i] = paths[index];
- if(i == 0) printf("%s\n", paths[index]);
- }
data d;
d.shallow = 0;
- d.X = load_image_paths(random_paths, n, h, w);
- d.y = load_labels_detection(random_paths, n, h, w, nh, nw, scale);
+
+ 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){
+ 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;
+ 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);
+ }
free(random_paths);
return d;
}
-data load_data(char **paths, int n, char **labels, int k, int h, int w)
+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.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 background, data *d)
+{
+ pthread_t thread;
+ struct load_args *args = calloc(1, sizeof(struct load_args));
+ args->n = n;
+ args->paths = paths;
+ args->m = m;
+ args->h = h;
+ args->w = w;
+ args->nh = nh;
+ args->nw = nw;
+ args->num_boxes = nw;
+ args->classes = classes;
+ args->background = background;
+ args->d = d;
+ if(pthread_create(&thread, 0, load_detection_thread, args)) {
+ error("Thread creation failed");
+ }
+ return thread;
+}
+
+data load_data(char **paths, int n, int m, char **labels, int k, int h, int w)
+{
+ if(m) paths = get_random_paths(paths, n, m);
data d;
d.shallow = 0;
d.X = load_image_paths(paths, n, h, w);
d.y = load_labels_paths(paths, n, labels, k);
+ if(m) free(paths);
return d;
}
-data load_data_random(int n, char **paths, int m, char **labels, int k, int h, int w)
+void *load_in_thread(void *ptr)
{
- char **random_paths = calloc(n, sizeof(char*));
- int i;
- for(i = 0; i < n; ++i){
- int index = rand()%m;
- random_paths[i] = paths[index];
- if(i == 0) printf("%s\n", paths[index]);
+ 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);
+ 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 thread;
+ struct load_args *args = calloc(1, sizeof(struct load_args));
+ args->n = n;
+ args->paths = paths;
+ args->m = m;
+ args->labels = labels;
+ args->k = k;
+ args->h = h;
+ args->w = w;
+ args->d = d;
+ if(pthread_create(&thread, 0, load_in_thread, args)) {
+ error("Thread creation failed");
}
- data d = load_data(random_paths, n, labels, k, h, w);
- free(random_paths);
- return d;
+ return thread;
}
data load_categorical_data_csv(char *filename, int target, int k)
@@ -203,9 +450,9 @@
X.vals[i][j] = (double)bytes[j+1];
}
}
- translate_data_rows(d, -144);
- scale_data_rows(d, 1./128);
- //normalize_data_rows(d);
+ translate_data_rows(d, -144);
+ scale_data_rows(d, 1./128);
+ //normalize_data_rows(d);
fclose(fp);
return d;
}
--
Gitblit v1.10.0