From ea09a6e0b38e1ddf43ffcd81d27f0506411eb8e4 Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Tue, 09 Jan 2018 19:26:54 +0000
Subject: [PATCH] Command line for example of usage DLL/SO
---
src/data.c | 598 +++++++++++++++++++++++++++++++++++++++++++++--------------
1 files changed, 450 insertions(+), 148 deletions(-)
diff --git a/src/data.c b/src/data.c
index 8d76276..ad9ef8b 100644
--- a/src/data.c
+++ b/src/data.c
@@ -7,7 +7,7 @@
#include <stdlib.h>
#include <string.h>
-unsigned int data_seed;
+pthread_mutex_t mutex = PTHREAD_MUTEX_INITIALIZER;
list *get_paths(char *filename)
{
@@ -22,15 +22,36 @@
return lines;
}
+/*
+char **get_random_paths_indexes(char **paths, int n, int m, int *indexes)
+{
+ char **random_paths = calloc(n, sizeof(char*));
+ int i;
+ pthread_mutex_lock(&mutex);
+ for(i = 0; i < n; ++i){
+ int index = random_gen()%m;
+ indexes[i] = index;
+ random_paths[i] = paths[index];
+ if(i == 0) printf("%s\n", paths[index]);
+ }
+ pthread_mutex_unlock(&mutex);
+ return random_paths;
+}
+*/
+
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;
+ pthread_mutex_lock(&mutex);
+ //printf("n = %d \n", n);
+ for(i = 0; i < n; ++i){
+ int index = random_gen() % m;
random_paths[i] = paths[index];
- if(i == 0) printf("%s\n", paths[index]);
+ //if(i == 0) printf("%s\n", paths[index]);
+ //printf("grp: %s\n", paths[index]);
}
+ pthread_mutex_unlock(&mutex);
return random_paths;
}
@@ -39,7 +60,8 @@
char **replace_paths = calloc(n, sizeof(char*));
int i;
for(i = 0; i < n; ++i){
- char *replaced = find_replace(paths[i], find, replace);
+ char replaced[4096];
+ find_replace(paths[i], find, replace, replaced);
replace_paths[i] = copy_string(replaced);
}
return replace_paths;
@@ -82,6 +104,34 @@
return X;
}
+matrix load_image_augment_paths(char **paths, int n, int min, int max, int size, float angle, float aspect, float hue, float saturation, float exposure)
+{
+ 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], 0, 0);
+ image crop = random_augment_image(im, angle, aspect, min, max, size);
+ int flip = random_gen()%2;
+ if (flip) flip_image(crop);
+ random_distort_image(crop, hue, saturation, exposure);
+
+ /*
+ show_image(im, "orig");
+ show_image(crop, "crop");
+ cvWaitKey(0);
+ */
+ free_image(im);
+ X.vals[i] = crop.data;
+ X.cols = crop.h*crop.w*crop.c;
+ }
+ return X;
+}
+
+
box_label *read_boxes(char *filename, int *n)
{
box_label *boxes = calloc(1, sizeof(box_label));
@@ -113,7 +163,7 @@
int i;
for(i = 0; i < n; ++i){
box_label swap = b[i];
- int index = rand_r(&data_seed)%n;
+ int index = random_gen()%n;
b[i] = b[index];
b[index] = swap;
}
@@ -123,6 +173,13 @@
{
int i;
for(i = 0; i < n; ++i){
+ if(boxes[i].x == 0 && boxes[i].y == 0) {
+ boxes[i].x = 999999;
+ boxes[i].y = 999999;
+ boxes[i].w = 999999;
+ boxes[i].h = 999999;
+ continue;
+ }
boxes[i].left = boxes[i].left * sx - dx;
boxes[i].right = boxes[i].right * sx - dx;
boxes[i].top = boxes[i].top * sy - dy;
@@ -151,12 +208,13 @@
void fill_truth_swag(char *path, float *truth, int classes, int flip, float dx, float dy, float sx, float sy)
{
- char *labelpath = find_replace(path, "images", "labels");
- labelpath = find_replace(labelpath, "JPEGImages", "labels");
+ char labelpath[4096];
+ find_replace(path, "images", "labels", labelpath);
+ find_replace(labelpath, "JPEGImages", "labels", labelpath);
+ find_replace(labelpath, ".jpg", ".txt", labelpath);
+ find_replace(labelpath, ".JPG", ".txt", labelpath);
+ find_replace(labelpath, ".JPEG", ".txt", labelpath);
- labelpath = find_replace(labelpath, ".jpg", ".txt");
- 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);
@@ -188,12 +246,14 @@
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");
+ char labelpath[4096];
+ find_replace(path, "images", "labels", labelpath);
+ find_replace(labelpath, "JPEGImages", "labels", labelpath);
- labelpath = find_replace(labelpath, ".jpg", ".txt");
- labelpath = find_replace(labelpath, ".JPG", ".txt");
- labelpath = find_replace(labelpath, ".JPEG", ".txt");
+ find_replace(labelpath, ".jpg", ".txt", labelpath);
+ find_replace(labelpath, ".png", ".txt", labelpath);
+ find_replace(labelpath, ".JPG", ".txt", labelpath);
+ find_replace(labelpath, ".JPEG", ".txt", labelpath);
int count = 0;
box_label *boxes = read_boxes(labelpath, &count);
randomize_boxes(boxes, count);
@@ -232,78 +292,40 @@
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)
+void fill_truth_detection(char *path, int num_boxes, float *truth, int classes, int flip, 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");
+ char labelpath[4096];
+ find_replace(path, "images", "labels", labelpath);
+ find_replace(labelpath, "JPEGImages", "labels", labelpath);
+
+ find_replace(labelpath, "raw", "labels", labelpath);
+ find_replace(labelpath, ".jpg", ".txt", labelpath);
+ find_replace(labelpath, ".png", ".txt", labelpath);
+ find_replace(labelpath, ".JPG", ".txt", labelpath);
+ find_replace(labelpath, ".JPEG", ".txt", labelpath);
int count = 0;
box_label *boxes = read_boxes(labelpath, &count);
randomize_boxes(boxes, count);
+ correct_boxes(boxes, count, dx, dy, sx, sy, flip);
+ if(count > num_boxes) count = num_boxes;
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;
+
+ 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(flip){
- float swap = left;
- left = 1. - right;
- right = 1. - swap;
- }
+ if ((w < .01 || h < .01)) continue;
- 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;
+ truth[i*5+0] = x;
+ truth[i*5+1] = y;
+ truth[i*5+2] = w;
+ truth[i*5+3] = h;
+ truth[i*5+4] = id;
}
free(boxes);
}
@@ -338,7 +360,7 @@
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;
+ data d = {0};
d.shallow = 0;
d.X = load_image_paths(paths, n, w, h);
d.y = make_matrix(n, k*NUMCHARS);
@@ -353,7 +375,7 @@
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;
+ data d = {0};
d.shallow = 0;
d.X = load_image_paths(paths, n, w, h);
d.X.cols = 17100;
@@ -376,16 +398,79 @@
if(count != 1) printf("Too many or too few labels: %d, %s\n", count, path);
}
-matrix load_labels_paths(char **paths, int n, char **labels, int k)
+void fill_hierarchy(float *truth, int k, tree *hierarchy)
+{
+ int j;
+ for(j = 0; j < k; ++j){
+ if(truth[j]){
+ int parent = hierarchy->parent[j];
+ while(parent >= 0){
+ truth[parent] = 1;
+ parent = hierarchy->parent[parent];
+ }
+ }
+ }
+ int i;
+ int count = 0;
+ for(j = 0; j < hierarchy->groups; ++j){
+ //printf("%d\n", count);
+ int mask = 1;
+ for(i = 0; i < hierarchy->group_size[j]; ++i){
+ if(truth[count + i]){
+ mask = 0;
+ break;
+ }
+ }
+ if (mask) {
+ for(i = 0; i < hierarchy->group_size[j]; ++i){
+ truth[count + i] = SECRET_NUM;
+ }
+ }
+ count += hierarchy->group_size[j];
+ }
+}
+
+matrix load_labels_paths(char **paths, int n, char **labels, int k, tree *hierarchy)
{
matrix y = make_matrix(n, k);
int i;
for(i = 0; i < n && labels; ++i){
fill_truth(paths[i], labels, k, y.vals[i]);
+ if(hierarchy){
+ fill_hierarchy(y.vals[i], k, hierarchy);
+ }
}
return y;
}
+matrix load_tags_paths(char **paths, int n, int k)
+{
+ matrix y = make_matrix(n, k);
+ int i;
+ int count = 0;
+ for(i = 0; i < n; ++i){
+ char label[4096];
+ find_replace(paths[i], "imgs", "labels", label);
+ find_replace(label, "_iconl.jpeg", ".txt", label);
+ FILE *file = fopen(label, "r");
+ if(!file){
+ find_replace(label, "labels", "labels2", label);
+ file = fopen(label, "r");
+ if(!file) continue;
+ }
+ ++count;
+ int tag;
+ while(fscanf(file, "%d", &tag) == 1){
+ if(tag < k){
+ y.vals[i][tag] = 1;
+ }
+ }
+ fclose(file);
+ }
+ printf("%d/%d\n", count, n);
+ return y;
+}
+
char **get_labels(char *filename)
{
list *plist = get_paths(filename);
@@ -405,17 +490,18 @@
}
}
-data load_data_region(int n, char **paths, int m, int w, int h, int size, int classes, float jitter)
+data load_data_region(int n, char **paths, int m, int w, int h, int size, int classes, float jitter, float hue, float saturation, float exposure)
{
char **random_paths = get_random_paths(paths, n, m);
int i;
- data d;
+ data d = {0};
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){
@@ -427,10 +513,10 @@
int dw = (ow*jitter);
int dh = (oh*jitter);
- 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 pleft = rand_uniform(-dw, dw);
+ int pright = rand_uniform(-dw, dw);
+ int ptop = rand_uniform(-dh, dh);
+ int pbot = rand_uniform(-dh, dh);
int swidth = ow - pleft - pright;
int sheight = oh - ptop - pbot;
@@ -438,7 +524,7 @@
float sx = (float)swidth / ow;
float sy = (float)sheight / oh;
- int flip = rand_r(&data_seed)%2;
+ int flip = random_gen()%2;
image cropped = crop_image(orig, pleft, ptop, swidth, sheight);
float dx = ((float)pleft/ow)/sx;
@@ -446,6 +532,7 @@
image sized = resize_image(cropped, w, h);
if(flip) flip_image(sized);
+ random_distort_image(sized, hue, saturation, exposure);
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);
@@ -461,7 +548,7 @@
{
if(m) paths = get_random_paths(paths, 2*n, m);
int i,j;
- data d;
+ data d = {0};
d.shallow = 0;
d.X.rows = n;
@@ -481,22 +568,24 @@
int id;
float iou;
- char *imlabel1 = find_replace(paths[i*2], "imgs", "labels");
- imlabel1 = find_replace(imlabel1, "jpg", "txt");
+ char imlabel1[4096];
+ char imlabel2[4096];
+ find_replace(paths[i*2], "imgs", "labels", imlabel1);
+ find_replace(imlabel1, "jpg", "txt", imlabel1);
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");
+ find_replace(paths[i*2+1], "imgs", "labels", imlabel2);
+ find_replace(imlabel2, "jpg", "txt", imlabel2);
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;
@@ -521,14 +610,14 @@
data load_data_swag(char **paths, int n, int classes, float jitter)
{
- int index = rand_r(&data_seed)%n;
+ int index = random_gen()%n;
char *random_path = paths[index];
-
+
image orig = load_image_color(random_path, 0, 0);
int h = orig.h;
int w = orig.w;
- data d;
+ data d = {0};
d.shallow = 0;
d.w = w;
d.h = h;
@@ -543,10 +632,10 @@
int dw = w*jitter;
int dh = h*jitter;
- 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 pleft = rand_uniform(-dw, dw);
+ int pright = rand_uniform(-dw, dw);
+ int ptop = rand_uniform(-dh, dh);
+ int pbot = rand_uniform(-dh, dh);
int swidth = w - pleft - pright;
int sheight = h - ptop - pbot;
@@ -554,7 +643,7 @@
float sx = (float)swidth / w;
float sy = (float)sheight / h;
- int flip = rand_r(&data_seed)%2;
+ int flip = random_gen()%2;
image cropped = crop_image(orig, pleft, ptop, swidth, sheight);
float dx = ((float)pleft/w)/sx;
@@ -572,32 +661,31 @@
return d;
}
-data load_data_detection(int n, char **paths, int m, int classes, int w, int h, int num_boxes, int background)
+data load_data_detection(int n, char **paths, int m, int w, int h, int boxes, int classes, float jitter, float hue, float saturation, float exposure)
{
char **random_paths = get_random_paths(paths, n, m);
int i;
- data d;
+ data d = {0};
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);
+ d.y = make_matrix(n, 5*boxes);
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 dw = (ow*jitter);
+ int dh = (oh*jitter);
- 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 pleft = rand_uniform_strong(-dw, dw);
+ int pright = rand_uniform_strong(-dw, dw);
+ int ptop = rand_uniform_strong(-dh, dh);
+ int pbot = rand_uniform_strong(-dh, dh);
int swidth = ow - pleft - pright;
int sheight = oh - ptop - pbot;
@@ -605,14 +693,7 @@
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;
+ int flip = random_gen()%2;
image cropped = crop_image(orig, pleft, ptop, swidth, sheight);
float dx = ((float)pleft/ow)/sx;
@@ -620,9 +701,10 @@
image sized = resize_image(cropped, w, h);
if(flip) flip_image(sized);
+ random_distort_image(sized, hue, saturation, exposure);
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);
+ fill_truth_detection(random_paths[i], boxes, d.y.vals[i], classes, flip, dx, dy, 1./sx, 1./sy);
free_image(orig);
free_image(cropped);
@@ -631,24 +713,28 @@
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));
+ //srand(time(0));
+ //printf("Loading data: %d\n", random_gen());
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);
+ if(a.exposure == 0) a.exposure = 1;
+ if(a.saturation == 0) a.saturation = 1;
+ if(a.aspect == 0) a.aspect = 1;
+
+ if (a.type == OLD_CLASSIFICATION_DATA){
+ *a.d = load_data_old(a.paths, a.n, a.m, a.labels, a.classes, a.w, a.h);
+ } else if (a.type == CLASSIFICATION_DATA){
+ *a.d = load_data_augment(a.paths, a.n, a.m, a.labels, a.classes, a.hierarchy, a.min, a.max, a.size, a.angle, a.aspect, a.hue, a.saturation, a.exposure);
+ } else if (a.type == SUPER_DATA){
+ *a.d = load_data_super(a.paths, a.n, a.m, a.w, a.h, a.scale);
} else if (a.type == WRITING_DATA){
*a.d = load_data_writing(a.paths, a.n, a.m, a.w, a.h, a.out_w, a.out_h);
} 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, a.jitter);
+ *a.d = load_data_region(a.n, a.paths, a.m, a.w, a.h, a.num_boxes, a.classes, a.jitter, a.hue, a.saturation, a.exposure);
+ } else if (a.type == DETECTION_DATA){
+ *a.d = load_data_detection(a.n, a.paths, a.m, a.w, a.h, a.num_boxes, a.classes, a.jitter, a.hue, a.saturation, a.exposure);
} else if (a.type == SWAG_DATA){
*a.d = load_data_swag(a.paths, a.n, a.classes, a.jitter);
} else if (a.type == COMPARE_DATA){
@@ -656,6 +742,8 @@
} 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);
+ } else if (a.type == TAG_DATA){
+ *a.d = load_data_tag(a.paths, a.n, a.m, a.classes, a.min, a.max, a.size, a.angle, a.aspect, a.hue, a.saturation, a.exposure);
}
free(ptr);
return 0;
@@ -670,11 +758,50 @@
return thread;
}
+void *load_threads(void *ptr)
+{
+ //srand(time(0));
+ int i;
+ load_args args = *(load_args *)ptr;
+ if (args.threads == 0) args.threads = 1;
+ data *out = args.d;
+ int total = args.n;
+ free(ptr);
+ data *buffers = calloc(args.threads, sizeof(data));
+ pthread_t *threads = calloc(args.threads, sizeof(pthread_t));
+ for(i = 0; i < args.threads; ++i){
+ args.d = buffers + i;
+ args.n = (i+1) * total/args.threads - i * total/args.threads;
+ threads[i] = load_data_in_thread(args);
+ }
+ for(i = 0; i < args.threads; ++i){
+ pthread_join(threads[i], 0);
+ }
+ *out = concat_datas(buffers, args.threads);
+ out->shallow = 0;
+ for(i = 0; i < args.threads; ++i){
+ buffers[i].shallow = 1;
+ free_data(buffers[i]);
+ }
+ free(buffers);
+ free(threads);
+ return 0;
+}
+
+pthread_t load_data(load_args args)
+{
+ pthread_t thread;
+ struct load_args *ptr = calloc(1, sizeof(struct load_args));
+ *ptr = args;
+ if(pthread_create(&thread, 0, load_threads, ptr)) error("Thread creation failed");
+ return thread;
+}
+
data load_data_writing(char **paths, int n, int m, int w, int h, int out_w, int out_h)
{
if(m) paths = get_random_paths(paths, n, m);
char **replace_paths = find_replace_paths(paths, n, ".png", "-label.png");
- data d;
+ data d = {0};
d.shallow = 0;
d.X = load_image_paths(paths, n, w, h);
d.y = load_image_paths_gray(replace_paths, n, out_w, out_h);
@@ -685,13 +812,81 @@
return d;
}
-data load_data(char **paths, int n, int m, char **labels, int k, int w, int h)
+data load_data_old(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;
+ data d = {0};
d.shallow = 0;
d.X = load_image_paths(paths, n, w, h);
- d.y = load_labels_paths(paths, n, labels, k);
+ d.y = load_labels_paths(paths, n, labels, k, 0);
+ if(m) free(paths);
+ return d;
+}
+
+/*
+ data load_data_study(char **paths, int n, int m, char **labels, int k, int min, int max, int size, float angle, float aspect, float hue, float saturation, float exposure)
+ {
+ data d = {0};
+ d.indexes = calloc(n, sizeof(int));
+ if(m) paths = get_random_paths_indexes(paths, n, m, d.indexes);
+ d.shallow = 0;
+ d.X = load_image_augment_paths(paths, n, min, max, size, angle, aspect, hue, saturation, exposure);
+ d.y = load_labels_paths(paths, n, labels, k);
+ if(m) free(paths);
+ return d;
+ }
+ */
+
+data load_data_super(char **paths, int n, int m, int w, int h, int scale)
+{
+ if(m) paths = get_random_paths(paths, n, m);
+ data d = {0};
+ d.shallow = 0;
+
+ int i;
+ d.X.rows = n;
+ d.X.vals = calloc(n, sizeof(float*));
+ d.X.cols = w*h*3;
+
+ d.y.rows = n;
+ d.y.vals = calloc(n, sizeof(float*));
+ d.y.cols = w*scale * h*scale * 3;
+
+ for(i = 0; i < n; ++i){
+ image im = load_image_color(paths[i], 0, 0);
+ image crop = random_crop_image(im, w*scale, h*scale);
+ int flip = random_gen()%2;
+ if (flip) flip_image(crop);
+ image resize = resize_image(crop, w, h);
+ d.X.vals[i] = resize.data;
+ d.y.vals[i] = crop.data;
+ free_image(im);
+ }
+
+ if(m) free(paths);
+ return d;
+}
+
+data load_data_augment(char **paths, int n, int m, char **labels, int k, tree *hierarchy, int min, int max, int size, float angle, float aspect, float hue, float saturation, float exposure)
+{
+ if(m) paths = get_random_paths(paths, n, m);
+ data d = {0};
+ d.shallow = 0;
+ d.X = load_image_augment_paths(paths, n, min, max, size, angle, aspect, hue, saturation, exposure);
+ d.y = load_labels_paths(paths, n, labels, k, hierarchy);
+ if(m) free(paths);
+ return d;
+}
+
+data load_data_tag(char **paths, int n, int m, int k, int min, int max, int size, float angle, float aspect, float hue, float saturation, float exposure)
+{
+ if(m) paths = get_random_paths(paths, n, m);
+ data d = {0};
+ d.w = size;
+ d.h = size;
+ d.shallow = 0;
+ d.X = load_image_augment_paths(paths, n, min, max, size, angle, aspect, hue, saturation, exposure);
+ d.y = load_tags_paths(paths, n, k);
if(m) free(paths);
return d;
}
@@ -714,16 +909,28 @@
data concat_data(data d1, data d2)
{
- data d;
+ data d = {0};
d.shallow = 1;
d.X = concat_matrix(d1.X, d2.X);
d.y = concat_matrix(d1.y, d2.y);
return d;
}
+data concat_datas(data *d, int n)
+{
+ int i;
+ data out = {0};
+ for(i = 0; i < n; ++i){
+ data new = concat_data(d[i], out);
+ free_data(out);
+ out = new;
+ }
+ return out;
+}
+
data load_categorical_data_csv(char *filename, int target, int k)
{
- data d;
+ data d = {0};
d.shallow = 0;
matrix X = csv_to_matrix(filename);
float *truth_1d = pop_column(&X, target);
@@ -740,7 +947,7 @@
data load_cifar10_data(char *filename)
{
- data d;
+ data d = {0};
d.shallow = 0;
long i,j;
matrix X = make_matrix(10000, 3072);
@@ -759,8 +966,8 @@
X.vals[i][j] = (double)bytes[j+1];
}
}
- translate_data_rows(d, -128);
- scale_data_rows(d, 1./128);
+ //translate_data_rows(d, -128);
+ scale_data_rows(d, 1./255);
//normalize_data_rows(d);
fclose(fp);
return d;
@@ -770,7 +977,7 @@
{
int j;
for(j = 0; j < n; ++j){
- int index = rand_r(&data_seed)%d.X.rows;
+ int index = random_gen()%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));
}
@@ -786,10 +993,21 @@
}
}
+void smooth_data(data d)
+{
+ int i, j;
+ float scale = 1. / d.y.cols;
+ float eps = .1;
+ for(i = 0; i < d.y.rows; ++i){
+ for(j = 0; j < d.y.cols; ++j){
+ d.y.vals[i][j] = eps * scale + (1-eps) * d.y.vals[i][j];
+ }
+ }
+}
data load_all_cifar10()
{
- data d;
+ data d = {0};
d.shallow = 0;
int i,j,b;
matrix X = make_matrix(50000, 3072);
@@ -800,7 +1018,7 @@
for(b = 0; b < 5; ++b){
char buff[256];
- sprintf(buff, "data/cifar10/data_batch_%d.bin", b+1);
+ sprintf(buff, "data/cifar/cifar-10-batches-bin/data_batch_%d.bin", b+1);
FILE *fp = fopen(buff, "rb");
if(!fp) file_error(buff);
for(i = 0; i < 10000; ++i){
@@ -815,16 +1033,64 @@
fclose(fp);
}
//normalize_data_rows(d);
- translate_data_rows(d, -128);
- scale_data_rows(d, 1./128);
+ //translate_data_rows(d, -128);
+ scale_data_rows(d, 1./255);
+ smooth_data(d);
return d;
}
+data load_go(char *filename)
+{
+ FILE *fp = fopen(filename, "rb");
+ matrix X = make_matrix(3363059, 361);
+ matrix y = make_matrix(3363059, 361);
+ int row, col;
+
+ if(!fp) file_error(filename);
+ char *label;
+ int count = 0;
+ while((label = fgetl(fp))){
+ int i;
+ if(count == X.rows){
+ X = resize_matrix(X, count*2);
+ y = resize_matrix(y, count*2);
+ }
+ sscanf(label, "%d %d", &row, &col);
+ char *board = fgetl(fp);
+
+ int index = row*19 + col;
+ y.vals[count][index] = 1;
+
+ for(i = 0; i < 19*19; ++i){
+ float val = 0;
+ if(board[i] == '1') val = 1;
+ else if(board[i] == '2') val = -1;
+ X.vals[count][i] = val;
+ }
+ ++count;
+ free(label);
+ free(board);
+ }
+ X = resize_matrix(X, count);
+ y = resize_matrix(y, count);
+
+ data d = {0};
+ d.shallow = 0;
+ d.X = X;
+ d.y = y;
+
+
+ fclose(fp);
+
+ return d;
+}
+
+
void randomize_data(data d)
{
int i;
for(i = d.X.rows-1; i > 0; --i){
- int index = rand_r(&data_seed)%i;
+ int index = random_gen()%i;
float *swap = d.X.vals[index];
d.X.vals[index] = d.X.vals[i];
d.X.vals[i] = swap;
@@ -859,6 +1125,42 @@
}
}
+data get_data_part(data d, int part, int total)
+{
+ data p = {0};
+ p.shallow = 1;
+ p.X.rows = d.X.rows * (part + 1) / total - d.X.rows * part / total;
+ p.y.rows = d.y.rows * (part + 1) / total - d.y.rows * part / total;
+ p.X.cols = d.X.cols;
+ p.y.cols = d.y.cols;
+ p.X.vals = d.X.vals + d.X.rows * part / total;
+ p.y.vals = d.y.vals + d.y.rows * part / total;
+ return p;
+}
+
+data get_random_data(data d, int num)
+{
+ data r = {0};
+ r.shallow = 1;
+
+ r.X.rows = num;
+ r.y.rows = num;
+
+ r.X.cols = d.X.cols;
+ r.y.cols = d.y.cols;
+
+ r.X.vals = calloc(num, sizeof(float *));
+ r.y.vals = calloc(num, sizeof(float *));
+
+ int i;
+ for(i = 0; i < num; ++i){
+ int index = random_gen()%d.X.rows;
+ r.X.vals[i] = d.X.vals[index];
+ r.y.vals[i] = d.y.vals[index];
+ }
+ return r;
+}
+
data *split_data(data d, int part, int total)
{
data *split = calloc(2, sizeof(data));
--
Gitblit v1.10.0