From a723e1c62a27aeb39aaf7fcdeb3beb4e89fba32d Mon Sep 17 00:00:00 2001
From: Alexey <AlexeyAB@users.noreply.github.com>
Date: Wed, 15 Aug 2018 20:52:09 +0000
Subject: [PATCH] Merge pull request #766 from HotChick91/AlexeyAB-mask
---
src/data.c | 303 +++++++++++++++++++++++++++++---------------------
1 files changed, 175 insertions(+), 128 deletions(-)
diff --git a/src/data.c b/src/data.c
index 1bb333a..2a0a7e9 100644
--- a/src/data.c
+++ b/src/data.c
@@ -44,12 +44,15 @@
char **random_paths = calloc(n, sizeof(char*));
int i;
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]);
- //printf("grp: %s\n", paths[index]);
+ //printf("n = %d \n", n);
+ for(i = 0; i < n; ++i){
+ do {
+ int index = random_gen() % m;
+ random_paths[i] = paths[index];
+ //if(i == 0) printf("%s\n", paths[index]);
+ //printf("grp: %s\n", paths[index]);
+ if (strlen(random_paths[i]) <= 4) printf(" Very small path to the image: %s \n", random_paths[i]);
+ } while (strlen(random_paths[i]) == 0);
}
pthread_mutex_unlock(&mutex);
return random_paths;
@@ -104,7 +107,7 @@
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)
+matrix load_image_augment_paths(char **paths, int n, int use_flip, int min, int max, int size, float angle, float aspect, float hue, float saturation, float exposure)
{
int i;
matrix X;
@@ -115,8 +118,9 @@
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);
+ int flip = use_flip ? random_gen() % 2 : 0;
+ if (flip)
+ flip_image(crop);
random_distort_image(crop, hue, saturation, exposure);
/*
@@ -136,7 +140,18 @@
{
box_label *boxes = calloc(1, sizeof(box_label));
FILE *file = fopen(filename, "r");
- if(!file) file_error(filename);
+ if (!file) {
+ printf("Can't open label file. (This can be normal only if you use MSCOCO) \n");
+ //file_error(filename);
+ FILE* fw = fopen("bad.list", "a");
+ fwrite(filename, sizeof(char), strlen(filename), fw);
+ char *new_line = "\n";
+ fwrite(new_line, sizeof(char), strlen(new_line), fw);
+ fclose(fw);
+
+ *n = 0;
+ return boxes;
+ }
float x, y, h, w;
int id;
int count = 0;
@@ -209,11 +224,7 @@
void fill_truth_swag(char *path, float *truth, int classes, int flip, float dx, float dy, float sx, float sy)
{
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);
+ replace_image_to_label(path, labelpath);
int count = 0;
box_label *boxes = read_boxes(labelpath, &count);
@@ -247,13 +258,8 @@
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[4096];
- find_replace(path, "images", "labels", labelpath);
- find_replace(labelpath, "JPEGImages", "labels", labelpath);
+ replace_image_to_label(path, 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);
@@ -292,45 +298,78 @@
free(boxes);
}
-void fill_truth_detection(char *path, int num_boxes, float *truth, int classes, int flip, float dx, float dy, float sx, float sy,
- int small_object, int net_w, int net_h)
+void fill_truth_detection(char *path, int num_boxes, float *truth, int classes, int flip, float dx, float dy, float sx, float sy,
+ int small_object, int net_w, int net_h)
{
char labelpath[4096];
- find_replace(path, "images", "labels", labelpath);
- find_replace(labelpath, "JPEGImages", "labels", labelpath);
+ replace_image_to_label(path, 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;
- int i;
+ int i;
box_label *boxes = read_boxes(labelpath, &count);
- if (small_object == 1) {
- float lowest_w = 1.F / net_w;
- float lowest_h = 1.F / net_h;
- printf(" lowest_w = %f, lowest_h = %f \n", lowest_w, lowest_h);
- for (i = 0; i < count; ++i) {
- if (boxes[i].w < lowest_w) boxes[i].w = lowest_w;
- if (boxes[i].h < lowest_h) boxes[i].h = lowest_h;
- }
- }
+ float lowest_w = 1.F / net_w;
+ float lowest_h = 1.F / net_h;
+ if (small_object == 1) {
+ for (i = 0; i < count; ++i) {
+ if (boxes[i].w < lowest_w) boxes[i].w = lowest_w;
+ if (boxes[i].h < lowest_h) boxes[i].h = lowest_h;
+ }
+ }
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;
+ if (count > num_boxes) count = num_boxes;
+ float x, y, w, h;
int id;
for (i = 0; i < count; ++i) {
- x = boxes[i].x;
- y = boxes[i].y;
- w = boxes[i].w;
- h = boxes[i].h;
+ x = boxes[i].x;
+ y = boxes[i].y;
+ w = boxes[i].w;
+ h = boxes[i].h;
id = boxes[i].id;
- // not detect small objects
- if ((w < 0.001F || h < 0.001F)) continue;
+ // not detect small objects
+ //if ((w < 0.001F || h < 0.001F)) continue;
+ // if truth (box for object) is smaller than 1x1 pix
+ char buff[256];
+ if (id >= classes) {
+ printf("\n Wrong annotation: class_id = %d. But class_id should be [from 0 to %d] \n", id, classes);
+ sprintf(buff, "echo %s \"Wrong annotation: class_id = %d. But class_id should be [from 0 to %d]\" >> bad_label.list", labelpath, id, classes);
+ system(buff);
+ getchar();
+ continue;
+ }
+ if ((w < lowest_w || h < lowest_h)) {
+ //sprintf(buff, "echo %s \"Very small object: w < lowest_w OR h < lowest_h\" >> bad_label.list", labelpath);
+ //system(buff);
+ continue;
+ }
+ if (x == 999999 || y == 999999) {
+ printf("\n Wrong annotation: x = 0, y = 0 \n");
+ sprintf(buff, "echo %s \"Wrong annotation: x = 0 or y = 0\" >> bad_label.list", labelpath);
+ system(buff);
+ continue;
+ }
+ if (x <= 0 || x > 1 || y <= 0 || y > 1) {
+ printf("\n Wrong annotation: x = %f, y = %f \n", x, y);
+ sprintf(buff, "echo %s \"Wrong annotation: x = %f, y = %f\" >> bad_label.list", labelpath, x, y);
+ system(buff);
+ continue;
+ }
+ if (w > 1) {
+ printf("\n Wrong annotation: w = %f \n", w);
+ sprintf(buff, "echo %s \"Wrong annotation: w = %f\" >> bad_label.list", labelpath, w);
+ system(buff);
+ w = 1;
+ }
+ if (h > 1) {
+ printf("\n Wrong annotation: h = %f \n", h);
+ sprintf(buff, "echo %s \"Wrong annotation: h = %f\" >> bad_label.list", labelpath, h);
+ system(buff);
+ h = 1;
+ }
+ if (x == 0) x += lowest_w;
+ if (y == 0) y += lowest_h;
truth[i*5+0] = x;
truth[i*5+1] = y;
@@ -482,14 +521,20 @@
return y;
}
-char **get_labels(char *filename)
+char **get_labels_custom(char *filename, int *size)
{
list *plist = get_paths(filename);
+ if(size) *size = plist->size;
char **labels = (char **)list_to_array(plist);
free_list(plist);
return labels;
}
+char **get_labels(char *filename)
+{
+ return get_labels_custom(filename, NULL);
+}
+
void free_data(data d)
{
if(!d.shallow){
@@ -683,8 +728,9 @@
#include "http_stream.h"
-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, int small_object)
+data load_data_detection(int n, char **paths, int m, int w, int h, int c, int boxes, int classes, int use_flip, float jitter, float hue, float saturation, float exposure, int small_object)
{
+ c = c ? c : 3;
char **random_paths = get_random_paths(paths, n, m);
int i;
data d = {0};
@@ -692,26 +738,26 @@
d.X.rows = n;
d.X.vals = calloc(d.X.rows, sizeof(float*));
- d.X.cols = h*w*3;
+ d.X.cols = h*w*c;
d.y = make_matrix(n, 5*boxes);
for(i = 0; i < n; ++i){
- const char *filename = random_paths[i];
+ const char *filename = random_paths[i];
- int flag = 1;
- IplImage *src;
- if ((src = cvLoadImage(filename, flag)) == 0)
- {
- fprintf(stderr, "Cannot load image \"%s\"\n", filename);
- char buff[256];
- sprintf(buff, "echo %s >> bad.list", filename);
- system(buff);
- continue;
- //exit(0);
- }
+ int flag = (c >= 3);
+ IplImage *src;
+ if ((src = cvLoadImage(filename, flag)) == 0)
+ {
+ fprintf(stderr, "Cannot load image \"%s\"\n", filename);
+ char buff[256];
+ sprintf(buff, "echo %s >> bad.list", filename);
+ system(buff);
+ continue;
+ //exit(0);
+ }
- int oh = src->height;
- int ow = src->width;
+ int oh = src->height;
+ int ow = src->width;
int dw = (ow*jitter);
int dh = (oh*jitter);
@@ -727,85 +773,86 @@
float sx = (float)swidth / ow;
float sy = (float)sheight / oh;
- int flip = random_gen()%2;
+ int flip = use_flip ? random_gen()%2 : 0;
float dx = ((float)pleft/ow)/sx;
float dy = ((float)ptop /oh)/sy;
- float dhue = rand_uniform_strong(-hue, hue);
- float dsat = rand_scale(saturation);
- float dexp = rand_scale(exposure);
+ float dhue = rand_uniform_strong(-hue, hue);
+ float dsat = rand_scale(saturation);
+ float dexp = rand_scale(exposure);
- image ai = image_data_augmentation(src, w, h, pleft, ptop, swidth, sheight, flip, jitter, dhue, dsat, dexp);
- d.X.vals[i] = ai.data;
-
- //show_image(ai, "aug");
- //cvWaitKey(0);
+ image ai = image_data_augmentation(src, w, h, pleft, ptop, swidth, sheight, flip, jitter, dhue, dsat, dexp);
+ d.X.vals[i] = ai.data;
+
+ //show_image(ai, "aug");
+ //cvWaitKey(0);
fill_truth_detection(filename, boxes, d.y.vals[i], classes, flip, dx, dy, 1./sx, 1./sy, small_object, w, h);
- cvReleaseImage(&src);
+ cvReleaseImage(&src);
}
free(random_paths);
return d;
}
-#else // OPENCV
-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, int small_object)
+#else // OPENCV
+data load_data_detection(int n, char **paths, int m, int w, int h, int c, int boxes, int classes, int use_flip, float jitter, float hue, float saturation, float exposure, int small_object)
{
- char **random_paths = get_random_paths(paths, n, m);
- int i;
- data d = { 0 };
- d.shallow = 0;
+ c = c ? c : 3;
+ char **random_paths = get_random_paths(paths, n, m);
+ int i;
+ 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;
+ d.X.rows = n;
+ d.X.vals = calloc(d.X.rows, sizeof(float*));
+ d.X.cols = h*w*c;
- d.y = make_matrix(n, 5 * boxes);
- for (i = 0; i < n; ++i) {
- image orig = load_image_color(random_paths[i], 0, 0);
+ d.y = make_matrix(n, 5 * boxes);
+ for (i = 0; i < n; ++i) {
+ image orig = load_image(random_paths[i], 0, 0, c);
- int oh = orig.h;
- int ow = orig.w;
+ int oh = orig.h;
+ int ow = orig.w;
- int dw = (ow*jitter);
- int dh = (oh*jitter);
+ int dw = (ow*jitter);
+ int dh = (oh*jitter);
- 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 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;
+ int swidth = ow - pleft - pright;
+ int sheight = oh - ptop - pbot;
- float sx = (float)swidth / ow;
- float sy = (float)sheight / oh;
+ float sx = (float)swidth / ow;
+ float sy = (float)sheight / oh;
- int flip = random_gen() % 2;
- image cropped = crop_image(orig, pleft, ptop, swidth, sheight);
+ int flip = use_flip ? random_gen() % 2 : 0;
+ image cropped = crop_image(orig, pleft, ptop, swidth, sheight);
- float dx = ((float)pleft / ow) / sx;
- float dy = ((float)ptop / oh) / sy;
+ float dx = ((float)pleft / ow) / sx;
+ float dy = ((float)ptop / oh) / sy;
- 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;
+ 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], boxes, d.y.vals[i], classes, flip, dx, dy, 1. / sx, 1. / sy, small_object, w, h);
+ fill_truth_detection(random_paths[i], boxes, d.y.vals[i], classes, flip, dx, dy, 1. / sx, 1. / sy, small_object, w, h);
- free_image(orig);
- free_image(cropped);
- }
- free(random_paths);
- return d;
+ free_image(orig);
+ free_image(cropped);
+ }
+ free(random_paths);
+ return d;
}
-#endif // OPENCV
+#endif // OPENCV
void *load_thread(void *ptr)
{
- //srand(time(0));
+ //srand(time(0));
//printf("Loading data: %d\n", random_gen());
load_args a = *(struct load_args*)ptr;
if(a.exposure == 0) a.exposure = 1;
@@ -815,7 +862,7 @@
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);
+ *a.d = load_data_augment(a.paths, a.n, a.m, a.labels, a.classes, a.hierarchy, a.flip, 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){
@@ -823,19 +870,19 @@
} 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.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, a.small_object);
+ *a.d = load_data_detection(a.n, a.paths, a.m, a.w, a.h, a.c, a.num_boxes, a.classes, a.flip, a.jitter, a.hue, a.saturation, a.exposure, a.small_object);
} 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){
*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.im) = load_image(a.path, 0, 0, a.c);
*(a.resized) = resize_image(*(a.im), a.w, a.h);
- }else if (a.type == LETTERBOX_DATA) {
- *(a.im) = load_image_color(a.path, 0, 0);
- *(a.resized) = letterbox_image(*(a.im), a.w, a.h);
+ }else if (a.type == LETTERBOX_DATA) {
+ *(a.im) = load_image(a.path, 0, 0, a.c);
+ *(a.resized) = letterbox_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);
+ *a.d = load_data_tag(a.paths, a.n, a.m, a.classes, a.flip, a.min, a.max, a.size, a.angle, a.aspect, a.hue, a.saturation, a.exposure);
}
free(ptr);
return 0;
@@ -852,7 +899,7 @@
void *load_threads(void *ptr)
{
- //srand(time(0));
+ //srand(time(0));
int i;
load_args args = *(load_args *)ptr;
if (args.threads == 0) args.threads = 1;
@@ -922,7 +969,7 @@
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.X = load_image_augment_paths(paths, n, flip, min, max, size, angle, aspect, hue, saturation, exposure);
d.y = load_labels_paths(paths, n, labels, k);
if(m) free(paths);
return d;
@@ -959,25 +1006,25 @@
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)
+data load_data_augment(char **paths, int n, int m, char **labels, int k, tree *hierarchy, int use_flip, 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.X = load_image_augment_paths(paths, n, use_flip, 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)
+data load_data_tag(char **paths, int n, int m, int k, int use_flip, 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.X = load_image_augment_paths(paths, n, use_flip, min, max, size, angle, aspect, hue, saturation, exposure);
d.y = load_tags_paths(paths, n, k);
if(m) free(paths);
return d;
--
Gitblit v1.10.0