From aa5996d58e68edfbefe51061856aecd549dd09c4 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Tue, 13 Jan 2015 01:27:08 +0000
Subject: [PATCH] Faster
---
src/data.c | 222 ++++++++++++++++++++++++++++++++++++++++++++-----------
1 files changed, 178 insertions(+), 44 deletions(-)
diff --git a/src/data.c b/src/data.c
index b31a5aa..ec9f9a7 100644
--- a/src/data.c
+++ b/src/data.c
@@ -6,6 +6,20 @@
#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;
+ float scale;
+ data *d;
+};
+
list *get_paths(char *filename)
{
char *path;
@@ -19,43 +33,113 @@
return lines;
}
+void fill_truth_detection(char *path, float *truth, int height, int width, int num_height, int num_width, float scale, int dx, int dy)
+{
+ 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");
+ if(!file) file_error(labelpath);
+ int x, y, h, w;
+ while(fscanf(file, "%d %d %d %d", &x, &y, &w, &h) == 4){
+ 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 = (float)(x%box_width)/box_height;
+ float dh = (float)(y%box_width)/box_width;
+ float sh = h/scale;
+ float sw = w/scale;
+ //printf("%d %d %f %f\n", i, j, dh, dw);
+ int index = (i+j*num_width)*5;
+ truth[index++] = 1;
+ truth[index++] = dh;
+ truth[index++] = dw;
+ truth[index++] = sh;
+ truth[index++] = sw;
+ }
+ fclose(file);
+}
+
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);
}
-data load_data_image_paths(char **paths, int n, char **labels, int k, int h, int w)
+matrix load_image_paths(char **paths, int n, int h, int w)
{
int i;
- data d;
- d.shallow = 0;
- d.X.rows = n;
- d.X.vals = calloc(d.X.rows, sizeof(float*));
- d.X.cols = 0;
- d.y = make_matrix(n, k);
+ matrix X;
+ X.rows = n;
+ X.vals = calloc(X.rows, sizeof(float*));
+ X.cols = 0;
for(i = 0; i < n; ++i){
image im = load_image_color(paths[i], h, w);
- d.X.vals[i] = im.data;
- d.X.cols = im.h*im.w*im.c;
+ X.vals[i] = im.data;
+ X.cols = im.h*im.w*im.c;
}
+ return X;
+}
+
+char **get_random_paths(char **paths, int n, int m)
+{
+ char **random_paths = calloc(n, sizeof(char*));
+ int i;
for(i = 0; i < n; ++i){
- fill_truth(paths[i], labels, k, d.y.vals[i]);
+ int index = rand()%m;
+ random_paths[i] = paths[index];
+ if(i == 0) printf("%s\n", paths[index]);
}
- return d;
+ return random_paths;
+}
+
+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 && 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,0,0);
+ }
+ 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);
- data d = load_data_image_paths(paths, plist->size, labels, k, h, w);
+ 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);
@@ -81,52 +165,102 @@
}
}
-data load_data_image_pathfile_part(char *filename, int part, int total, char **labels, int k, int h, int w)
+data load_data_detection_jitter_random(int n, char **paths, int m, int h, int w, int nh, int nw, float scale)
{
- list *plist = get_paths(filename);
- char **paths = (char **)list_to_array(plist);
- int start = part*plist->size/total;
- int end = (part+1)*plist->size/total;
- data d = load_data_image_paths(paths+start, end-start, labels, k, h, w);
- free_list_contents(plist);
- free_list(plist);
- free(paths);
- return d;
-}
-
-data load_data_random(int n, char **paths, int m, char **labels, int k, int h, int w)
-{
- char **random_paths = calloc(n, sizeof(char*));
+ 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*5;
+ d.y = make_matrix(n, k);
for(i = 0; i < n; ++i){
- int index = rand()%m;
- random_paths[i] = paths[index];
- if(i == 0) printf("%s\n", paths[index]);
+ int dx = rand()%32;
+ int dy = rand()%32;
+ fill_truth_detection(random_paths[i], d.y.vals[i], 224, 224, nh, nw, scale, dx, dy);
+ image a = float_to_image(h, w, 3, d.X.vals[i]);
+ jitter_image(a,224,224,dy,dx);
}
- data d = load_data_image_paths(random_paths, n, labels, k, h, w);
+ d.X.cols = 224*224*3;
free(random_paths);
return d;
}
-data load_data_image_pathfile_random(char *filename, int n, char **labels, int k, int h, int w)
+void *load_detection_thread(void *ptr)
{
- int i;
- list *plist = get_paths(filename);
- char **paths = (char **)list_to_array(plist);
- char **random_paths = calloc(n, sizeof(char*));
- for(i = 0; i < n; ++i){
- int index = rand()%plist->size;
- 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_detection_jitter_random(a.n, a.paths, a.m, a.h, a.w, a.nh, a.nw, a.scale);
+ free(ptr);
+ return 0;
+}
+
+pthread_t load_data_detection_thread(int n, char **paths, int m, int h, int w, int nh, int nw, float scale, 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->scale = scale;
+ args->d = d;
+ if(pthread_create(&thread, 0, load_detection_thread, args)) {
+ error("Thread creation failed");
}
- data d = load_data_image_paths(random_paths, n, labels, k, h, w);
- free_list_contents(plist);
- free_list(plist);
- free(paths);
+ return thread;
+}
+
+data load_data_detection_random(int n, char **paths, int m, int h, int w, int nh, int nw, float scale)
+{
+ char **random_paths = get_random_paths(paths, n, m);
+ 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);
free(random_paths);
return d;
}
+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;
+}
+
+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);
+ 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");
+ }
+ return thread;
+}
+
data load_categorical_data_csv(char *filename, int target, int k)
{
data d;
--
Gitblit v1.10.0