From b5936b499abc94c0efffbcc99b5698574b59d860 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Sat, 05 Sep 2015 00:52:44 +0000
Subject: [PATCH] lots of stuff
---
src/data.c | 634 +++++++++++++++++++++++++++++++++++++++++++++++++++++----
1 files changed, 586 insertions(+), 48 deletions(-)
diff --git a/src/data.c b/src/data.c
index 846b950..003338e 100644
--- a/src/data.c
+++ b/src/data.c
@@ -1,11 +1,14 @@
#include "data.h"
#include "utils.h"
#include "image.h"
+#include "cuda.h"
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
+unsigned int data_seed;
+
list *get_paths(char *filename)
{
char *path;
@@ -19,45 +22,330 @@
return lines;
}
+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){
+ int index = rand_r(&data_seed)%m;
+ random_paths[i] = paths[index];
+ if(i == 0) printf("%s\n", paths[index]);
+ }
+ return random_paths;
+}
+
+char **find_replace_paths(char **paths, int n, char *find, char *replace)
+{
+ char **replace_paths = calloc(n, sizeof(char*));
+ int i;
+ for(i = 0; i < n; ++i){
+ char *replaced = find_replace(paths[i], find, replace);
+ replace_paths[i] = copy_string(replaced);
+ }
+ return replace_paths;
+}
+
+matrix load_image_paths_gray(char **paths, int n, int w, int h)
+{
+ int i;
+ 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(paths[i], w, h, 1);
+ X.vals[i] = im.data;
+ X.cols = im.h*im.w*im.c;
+ }
+ return X;
+}
+
+matrix load_image_paths(char **paths, int n, int w, int h)
+{
+ int i;
+ 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], w, h);
+ X.vals[i] = im.data;
+ X.cols = im.h*im.w*im.c;
+ }
+ return X;
+}
+
+box_label *read_boxes(char *filename, int *n)
+{
+ 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){
+ 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 correct_boxes(box_label *boxes, int n, float dx, float dy, float sx, float sy, int flip)
+{
+ int i;
+ for(i = 0; i < n; ++i){
+ boxes[i].left = boxes[i].left * sx - dx;
+ boxes[i].right = boxes[i].right * sx - dx;
+ boxes[i].top = boxes[i].top * sy - dy;
+ boxes[i].bottom = boxes[i].bottom* sy - dy;
+
+ if(flip){
+ float swap = boxes[i].left;
+ boxes[i].left = 1. - boxes[i].right;
+ boxes[i].right = 1. - swap;
+ }
+
+ boxes[i].left = constrain(0, 1, boxes[i].left);
+ boxes[i].right = constrain(0, 1, boxes[i].right);
+ boxes[i].top = constrain(0, 1, boxes[i].top);
+ boxes[i].bottom = constrain(0, 1, boxes[i].bottom);
+
+ boxes[i].x = (boxes[i].left+boxes[i].right)/2;
+ boxes[i].y = (boxes[i].top+boxes[i].bottom)/2;
+ boxes[i].w = (boxes[i].right - boxes[i].left);
+ boxes[i].h = (boxes[i].bottom - boxes[i].top);
+
+ boxes[i].w = constrain(0, 1, boxes[i].w);
+ boxes[i].h = constrain(0, 1, boxes[i].h);
+ }
+}
+
+void fill_truth_region(char *path, float *truth, int classes, int num_boxes, int flip, float dx, float dy, float sx, float sy)
+{
+ char *labelpath = find_replace(path, "images", "labels");
+ labelpath = find_replace(labelpath, "JPEGImages", "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);
+ correct_boxes(boxes, count, dx, dy, sx, sy, flip);
+ float x,y,w,h;
+ int id;
+ int i;
+
+ for (i = 0; i < count; ++i) {
+ x = boxes[i].x;
+ y = boxes[i].y;
+ w = boxes[i].w;
+ h = boxes[i].h;
+ id = boxes[i].id;
+
+ if (w < .01 || h < .01) continue;
+
+ int col = (int)(x*num_boxes);
+ int row = (int)(y*num_boxes);
+
+ x = x*num_boxes - col;
+ y = y*num_boxes - row;
+
+ int index = (col+row*num_boxes)*(5+classes);
+ if (truth[index]) continue;
+ truth[index++] = 1;
+ if (classes) truth[index+id] = 1;
+ index += classes;
+ truth[index++] = x;
+ truth[index++] = y;
+ truth[index++] = w;
+ truth[index++] = h;
+ }
+ free(boxes);
+}
+
+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, "JPEGImages", "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 col = (int)(x*num_boxes);
+ int row = (int)(y*num_boxes);
+
+ x = x*num_boxes - col;
+ y = y*num_boxes - row;
+
+ /*
+ 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 < .01 || h < .01) continue;
+ if(1){
+ w = pow(w, 1./2.);
+ h = pow(h, 1./2.);
+ }
+
+ int index = (col+row*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
+
+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 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.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 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)
{
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("Too many or too few labels: %d, %s\n", count, path);
}
-data load_data_image_paths(char **paths, int n, char **labels, int k, int h, int w)
+matrix load_labels_paths(char **paths, int n, char **labels, int k)
{
+ matrix y = make_matrix(n, k);
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);
-
- for(i = 0; i < n; ++i){
- image im = load_image(paths[i], h, w);
- d.X.vals[i] = im.data;
- d.X.cols = im.h*im.w*im.c;
- fill_truth(paths[i], labels, k, d.y.vals[i]);
+ for(i = 0; i < n && labels; ++i){
+ fill_truth(paths[i], labels, k, y.vals[i]);
}
- return d;
+ return y;
}
-data load_data_image_pathfile(char *filename, char **labels, int k, int h, int w)
+char **get_labels(char *filename)
{
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);
- free_list_contents(plist);
+ char **labels = (char **)list_to_array(plist);
free_list(plist);
- free(paths);
- return d;
+ return labels;
}
void free_data(data d)
@@ -71,38 +359,267 @@
}
}
-data load_data_image_pathfile_part(char *filename, int part, int total, char **labels, int k, int h, int w)
+data load_data_region(int n, char **paths, int m, int w, int h, int size, int classes)
{
- 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);
+ char **random_paths = get_random_paths(paths, n, m);
+ int i;
+ data d;
+ d.shallow = 0;
+
+ d.X.rows = n;
+ d.X.vals = calloc(d.X.rows, sizeof(float*));
+ d.X.cols = h*w*3;
+
+ int k = size*size*(5+classes);
+ 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_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;
+
+ image sized = resize_image(cropped, w, h);
+ if(flip) flip_image(sized);
+ d.X.vals[i] = sized.data;
+
+ fill_truth_region(random_paths[i], d.y.vals[i], classes, size, flip, dx, dy, 1./sx, 1./sy);
+
+ free_image(orig);
+ free_image(cropped);
+ }
+ free(random_paths);
return d;
}
-data load_data_image_pathfile_random(char *filename, int n, char **labels, int k, int h, int w)
+data load_data_compare(int n, char **paths, int m, int classes, int w, int h)
{
- int i;
- list *plist = get_paths(filename);
- char **paths = (char **)list_to_array(plist);
- char **random_paths = calloc(n, sizeof(char*));
+ if(m) paths = get_random_paths(paths, 2*n, m);
+ int i,j;
+ data d;
+ d.shallow = 0;
+
+ d.X.rows = n;
+ d.X.vals = calloc(d.X.rows, sizeof(float*));
+ d.X.cols = h*w*6;
+
+ int k = 2*(classes);
+ d.y = make_matrix(n, k);
for(i = 0; i < n; ++i){
- int index = rand()%plist->size;
- random_paths[i] = paths[index];
- if(i == 0) printf("%s\n", paths[index]);
+ image im1 = load_image_color(paths[i*2], w, h);
+ image im2 = load_image_color(paths[i*2+1], w, h);
+
+ d.X.vals[i] = calloc(d.X.cols, sizeof(float));
+ memcpy(d.X.vals[i], im1.data, h*w*3*sizeof(float));
+ memcpy(d.X.vals[i] + h*w*3, im2.data, h*w*3*sizeof(float));
+
+ int id;
+ float iou;
+
+ char *imlabel1 = find_replace(paths[i*2], "imgs", "labels");
+ imlabel1 = find_replace(imlabel1, "jpg", "txt");
+ FILE *fp1 = fopen(imlabel1, "r");
+
+ while(fscanf(fp1, "%d %f", &id, &iou) == 2){
+ if (d.y.vals[i][2*id] < iou) d.y.vals[i][2*id] = iou;
+ }
+
+ char *imlabel2 = find_replace(paths[i*2+1], "imgs", "labels");
+ imlabel2 = find_replace(imlabel2, "jpg", "txt");
+ FILE *fp2 = fopen(imlabel2, "r");
+
+ while(fscanf(fp2, "%d %f", &id, &iou) == 2){
+ if (d.y.vals[i][2*id + 1] < iou) d.y.vals[i][2*id + 1] = iou;
+ }
+
+ for (j = 0; j < classes; ++j){
+ if (d.y.vals[i][2*j] > .5 && d.y.vals[i][2*j+1] < .5){
+ d.y.vals[i][2*j] = 1;
+ d.y.vals[i][2*j+1] = 0;
+ } else if (d.y.vals[i][2*j] < .5 && d.y.vals[i][2*j+1] > .5){
+ d.y.vals[i][2*j] = 0;
+ d.y.vals[i][2*j+1] = 1;
+ } else {
+ d.y.vals[i][2*j] = SECRET_NUM;
+ d.y.vals[i][2*j+1] = SECRET_NUM;
+ }
+ }
+ fclose(fp1);
+ fclose(fp2);
+
+ free_image(im1);
+ free_image(im2);
}
- data d = load_data_image_paths(random_paths, n, labels, k, h, w);
- free_list_contents(plist);
- free_list(plist);
- free(paths);
+ if(m) free(paths);
+ return d;
+}
+
+data load_data_detection(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.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;
+
+ /*
+ 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;
+
+ image sized = resize_image(cropped, w, h);
+ 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_image(orig);
+ free_image(cropped);
+ }
free(random_paths);
return d;
}
+void *load_thread(void *ptr)
+{
+
+#ifdef GPU
+ cudaError_t status = cudaSetDevice(gpu_index);
+ check_error(status);
+#endif
+
+ printf("Loading data: %d\n", rand_r(&data_seed));
+ load_args a = *(struct load_args*)ptr;
+ if (a.type == CLASSIFICATION_DATA){
+ *a.d = load_data(a.paths, a.n, a.m, a.labels, a.classes, a.w, a.h);
+ } else if (a.type == DETECTION_DATA){
+ *a.d = load_data_detection(a.n, a.paths, a.m, a.classes, a.w, a.h, a.num_boxes, a.background);
+ } else if (a.type == REGION_DATA){
+ *a.d = load_data_region(a.n, a.paths, a.m, a.w, a.h, a.num_boxes, a.classes);
+ } else if (a.type == COMPARE_DATA){
+ *a.d = load_data_compare(a.n, a.paths, a.m, a.classes, a.w, a.h);
+ } else if (a.type == IMAGE_DATA){
+ *(a.im) = load_image_color(a.path, 0, 0);
+ *(a.resized) = resize_image(*(a.im), a.w, a.h);
+ }
+ free(ptr);
+ return 0;
+}
+
+pthread_t load_data_in_thread(load_args args)
+{
+ pthread_t thread;
+ struct load_args *ptr = calloc(1, sizeof(struct load_args));
+ *ptr = args;
+ if(pthread_create(&thread, 0, load_thread, ptr)) {
+ error("Thread creation failed");
+ }
+ return thread;
+}
+
+data load_data_writing(char **paths, int n, int m, int w, int h)
+{
+ if(m) paths = get_random_paths(paths, n, m);
+ char **replace_paths = find_replace_paths(paths, n, ".png", "-label.png");
+ data d;
+ d.shallow = 0;
+ d.X = load_image_paths(paths, n, w, h);
+ d.y = load_image_paths_gray(replace_paths, n, w/8, h/8);
+ if(m) free(paths);
+ int i;
+ for(i = 0; i < n; ++i) free(replace_paths[i]);
+ free(replace_paths);
+ return d;
+}
+
+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, w, h);
+ d.y = load_labels_paths(paths, n, labels, k);
+ if(m) free(paths);
+ return d;
+}
+
+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;
@@ -141,13 +658,34 @@
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, -128);
+ scale_data_rows(d, 1./128);
+ //normalize_data_rows(d);
fclose(fp);
return d;
}
+void get_random_batch(data d, int n, float *X, float *y)
+{
+ int j;
+ for(j = 0; j < n; ++j){
+ 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));
+ }
+}
+
+void get_next_batch(data d, int n, int offset, float *X, float *y)
+{
+ int j;
+ for(j = 0; j < n; ++j){
+ int index = offset + j;
+ 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));
+ }
+}
+
+
data load_all_cifar10()
{
data d;
@@ -158,7 +696,7 @@
d.X = X;
d.y = y;
-
+
for(b = 0; b < 5; ++b){
char buff[256];
sprintf(buff, "data/cifar10/data_batch_%d.bin", b+1);
@@ -176,8 +714,8 @@
fclose(fp);
}
//normalize_data_rows(d);
- translate_data_rows(d, -144);
- scale_data_rows(d, 1./128);
+ translate_data_rows(d, -128);
+ scale_data_rows(d, 1./128);
return d;
}
@@ -185,7 +723,7 @@
{
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