From c62b4f35aa2c59d7db0fd177affeed14b1ba4bcb Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Thu, 08 Sep 2016 07:04:39 +0000
Subject: [PATCH] adding coco models
---
src/data.c | 187 +++++++++++++++++++++++++---------------------
1 files changed, 100 insertions(+), 87 deletions(-)
diff --git a/src/data.c b/src/data.c
index b0368ee..02dbac4 100644
--- a/src/data.c
+++ b/src/data.c
@@ -8,6 +8,7 @@
#include <string.h>
unsigned int data_seed;
+pthread_mutex_t mutex = PTHREAD_MUTEX_INITIALIZER;
list *get_paths(char *filename)
{
@@ -26,12 +27,14 @@
{
char **random_paths = calloc(n, sizeof(char*));
int i;
+ pthread_mutex_lock(&mutex);
for(i = 0; i < n; ++i){
int index = rand_r(&data_seed)%m;
indexes[i] = index;
random_paths[i] = paths[index];
if(i == 0) printf("%s\n", paths[index]);
}
+ pthread_mutex_unlock(&mutex);
return random_paths;
}
@@ -39,11 +42,13 @@
{
char **random_paths = calloc(n, sizeof(char*));
int i;
+ pthread_mutex_lock(&mutex);
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]);
}
+ pthread_mutex_unlock(&mutex);
return random_paths;
}
@@ -95,7 +100,7 @@
return X;
}
-matrix load_image_cropped_paths(char **paths, int n, int min, int max, int size)
+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;
@@ -105,9 +110,11 @@
for(i = 0; i < n; ++i){
image im = load_image_color(paths[i], 0, 0);
- image crop = random_crop_image(im, min, max, size);
+ image crop = random_augment_image(im, angle, aspect, min, max, size);
int flip = rand_r(&data_seed)%2;
if (flip) flip_image(crop);
+ random_distort_image(crop, hue, saturation, exposure);
+
/*
show_image(im, "orig");
show_image(crop, "crop");
@@ -231,6 +238,7 @@
labelpath = find_replace(labelpath, "JPEGImages", "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");
int count = 0;
@@ -271,78 +279,38 @@
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");
+ char *labelpath = find_replace(path, "images", "labels");
+ labelpath = find_replace(labelpath, "JPEGImages", "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");
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;
- }
-
- 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);
}
@@ -474,7 +442,7 @@
}
}
-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;
@@ -485,6 +453,7 @@
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){
@@ -515,6 +484,7 @@
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);
@@ -641,7 +611,7 @@
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;
@@ -652,16 +622,15 @@
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(-dw, dw);
int pright = rand_uniform(-dw, dw);
@@ -674,13 +643,6 @@
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);
@@ -689,9 +651,10 @@
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);
@@ -700,6 +663,7 @@
return d;
}
+
void *load_thread(void *ptr)
{
@@ -710,18 +674,24 @@
//printf("Loading data: %d\n", rand_r(&data_seed));
load_args a = *(struct load_args*)ptr;
+ 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(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.min, a.max, a.size);
+ *a.d = load_data_augment(a.paths, a.n, a.m, a.labels, a.classes, 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 == STUDY_DATA){
- *a.d = load_data_study(a.paths, a.n, a.m, a.labels, a.classes, a.min, a.max, a.size);
- } 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);
+ *a.d = load_data_study(a.paths, a.n, a.m, a.labels, a.classes, a.min, a.max, a.size, a.angle, a.aspect, a.hue, a.saturation, a.exposure);
} 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){
@@ -730,7 +700,7 @@
*(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.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(a.paths, a.n, a.m, a.labels, a.classes, a.w, a.h);
}
free(ptr);
@@ -772,37 +742,67 @@
return d;
}
-data load_data_study(char **paths, int n, int m, char **labels, int k, int min, int max, int size)
+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_cropped_paths(paths, n, min, max, size);
+ 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_augment(char **paths, int n, int m, char **labels, int k, int min, int max, int size)
+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;
- d.X = load_image_cropped_paths(paths, n, min, max, size);
+
+ 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 = rand_r(&data_seed)%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, 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);
if(m) free(paths);
return d;
}
-data load_data_tag(char **paths, int n, int m, int k, int min, int max, int size)
+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_cropped_paths(paths, n, min, max, size);
+ 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;
@@ -833,6 +833,19 @@
return d;
}
+data concat_datas(data *d, int n)
+{
+ int i;
+ data out = {0};
+ out.shallow = 1;
+ 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 = {0};
--
Gitblit v1.10.0