From d97331b88ff3d50035b1e22c9d0eb671b61227e3 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Wed, 15 Apr 2015 07:32:32 +0000
Subject: [PATCH] level adjustment for images
---
src/data.c | 97 ++++++++++++++++++++++++------------------------
1 files changed, 48 insertions(+), 49 deletions(-)
diff --git a/src/data.c b/src/data.c
index 71d52d4..012d7cf 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;
@@ -40,14 +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;
@@ -56,7 +58,7 @@
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;
}
@@ -100,7 +102,7 @@
int i;
for(i = 0; i < n; ++i){
box swap = b[i];
- int index = rand()%n;
+ int index = rand_r(&data_seed)%n;
b[i] = b[index];
b[index] = swap;
}
@@ -108,8 +110,9 @@
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);
@@ -206,12 +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){
@@ -221,12 +224,12 @@
return d;
}
-data load_data_captcha_encode(char **paths, int n, int m, int h, int w)
+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, h, w);
+ d.X = load_image_paths(paths, n, w, h);
d.X.cols = 17100;
d.y = d.X;
if(m) free(paths);
@@ -257,21 +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);
@@ -291,10 +279,8 @@
}
}
-data load_data_detection_jitter_random(int n, char **paths, int m, int classes, int h, int w, int num_boxes, int background)
+data load_data_detection_jitter_random(int n, char **paths, int m, int classes, int w, int h, 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;
@@ -308,26 +294,43 @@
d.y = make_matrix(n, k);
for(i = 0; i < n; ++i){
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 pleft = (rand_uniform() * 64. - 32.);
- int pright = (rand_uniform() * 64. - 32.);
- int ptop = (rand_uniform() * 64. - 32.);
- int pbot = (rand_uniform() * 64. - 32.);
+
+ 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()%2;
- image cropped = crop_image(orig, ptop, pleft, sheight, swidth);
+ 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, h, w);
+ image sized = resize_image(cropped, w, h);
free_image(cropped);
if(flip) flip_image(sized);
d.X.vals[i] = sized.data;
@@ -340,16 +343,14 @@
void *load_detection_thread(void *ptr)
{
- printf("Loading data: %d\n", rand());
+ 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.num_boxes, a.background);
- 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 background, 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));
@@ -370,12 +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;
@@ -384,14 +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));
@@ -447,7 +446,7 @@
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);
@@ -458,7 +457,7 @@
{
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));
}
@@ -503,7 +502,7 @@
fclose(fp);
}
//normalize_data_rows(d);
- translate_data_rows(d, -144);
+ translate_data_rows(d, -128);
scale_data_rows(d, 1./128);
return d;
}
@@ -512,7 +511,7 @@
{
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