From 0713fd9784bbd0c67eb82df6f6e2c072a53e09e8 Mon Sep 17 00:00:00 2001
From: Alexey <AlexeyAB@users.noreply.github.com>
Date: Thu, 31 May 2018 11:20:19 +0000
Subject: [PATCH] Merge pull request #936 from IlyaOvodov/Fix_GrayScale_PR
---
src/data.c | 127 ++++++++++++++++++++++--------------------
1 files changed, 66 insertions(+), 61 deletions(-)
diff --git a/src/data.c b/src/data.c
index abdb043..dc803f0 100644
--- a/src/data.c
+++ b/src/data.c
@@ -45,11 +45,13 @@
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]);
+ 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]);
+ } while (strlen(random_paths[i]) == 0);
}
pthread_mutex_unlock(&mutex);
return random_paths;
@@ -104,7 +106,7 @@
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 +117,9 @@
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 +139,10 @@
{
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. \n");
+ file_error(filename);
+ }
float x, y, h, w;
int id;
int count = 0;
@@ -209,11 +215,7 @@
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);
@@ -247,14 +249,9 @@
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;
+ int count = 0;
box_label *boxes = read_boxes(labelpath, &count);
randomize_boxes(boxes, count);
correct_boxes(boxes, count, dx, dy, sx, sy, flip);
@@ -292,21 +289,15 @@
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,
+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);
+ char labelpath[4096];
+ 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 count = 0;
int i;
- box_label *boxes = read_boxes(labelpath, &count);
+ box_label *boxes = read_boxes(labelpath, &count);
float lowest_w = 1.F / net_w;
float lowest_h = 1.F / net_h;
if (small_object == 1) {
@@ -315,23 +306,35 @@
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;
- int id;
+ 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;
+ int id;
- 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;
+ 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;
// not detect small objects
//if ((w < 0.001F || h < 0.001F)) continue;
// if truth (box for object) is smaller than 1x1 pix
if ((w < lowest_w || h < lowest_h)) continue;
+ if (x == 999999 || y == 999999) {
+ printf("\n Wrong annotation: x = 0, y = 0 \n");
+ continue;
+ }
+ if (x < 0 || x > 1 || y < 0 || y > 1) {
+ printf("\n Wrong annotation: x = %f, y = %f \n", x, y);
+ continue;
+ }
+ if (w > 1) printf("\n Wrong annotation: w = %f \n", w), w = 1;
+ if (h > 1) printf("\n Wrong annotation: h = %f \n", h), h = 1;
+ if (x == 0) x += lowest_w;
+ if (y == 0) y += lowest_h;
truth[i*5+0] = x;
truth[i*5+1] = y;
@@ -684,8 +687,9 @@
#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};
@@ -693,13 +697,13 @@
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];
- int flag = 1;
+ int flag = (c >= 3);
IplImage *src;
if ((src = cvLoadImage(filename, flag)) == 0)
{
@@ -728,7 +732,7 @@
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;
@@ -751,8 +755,9 @@
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)
+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 };
@@ -760,11 +765,11 @@
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) {
- image orig = load_image_color(random_paths[i], 0, 0);
+ image orig = load_image(random_paths[i], 0, 0, c);
int oh = orig.h;
int ow = orig.w;
@@ -783,7 +788,7 @@
float sx = (float)swidth / ow;
float sy = (float)sheight / oh;
- int flip = random_gen() % 2;
+ int flip = use_flip ? random_gen() % 2 : 0;
image cropped = crop_image(orig, pleft, ptop, swidth, sheight);
float dx = ((float)pleft / ow) / sx;
@@ -816,7 +821,7 @@
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){
@@ -824,19 +829,19 @@
} 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.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;
@@ -923,7 +928,7 @@
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;
@@ -960,25 +965,25 @@
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