OrgLion-ML
/
darknet
mirror of https://github.com/AlexeyAB/darknet.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Fix issue #674: parameter "flip" is added to [net] parameters for classifier and detector 

flip=0 switches flip augmentation off.
Default is flip=1 which is consistent with a previous behaviour.
This commit is contained in:
iovodov 2018-04-19 19:31:09 +03:00 committed by Ilya Ovodov
parent 5d616450a4
commit 9207607a59
6 changed files with 26 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/classifier.c
View File

@ -87,6 +87,7 @@ void train_classifier(char *datacfg, char *cfgfile, char *weightfile, int *gpus,
args.min = net.min_crop;
args.max = net.max_crop;
args.flip = net.flip;
args.angle = net.angle;
args.aspect = net.aspect;
args.exposure = net.exposure;
@ -193,6 +194,7 @@ void train_classifier(char *datacfg, char *cfgfile, char *weightfile, int *gpus,
args.min = net.min_crop;
args.max = net.max_crop;
args.flip = net.flip;
args.angle = net.angle;
args.aspect = net.aspect;
args.exposure = net.exposure;

31
src/data.c
View File

@ -104,7 +104,7 @@ matrix load_image_paths(char **paths, int n, int w, int h)
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 +115,9 @@ matrix load_image_augment_paths(char **paths, int n, int min, int max, int size,
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);
/*
@ -685,7 +686,7 @@ data load_data_swag(char **paths, int n, int classes, float jitter)
#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 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;
@ -729,7 +730,7 @@ data load_data_detection(int n, char **paths, int m, int w, int h, int boxes, in
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;
@ -752,7 +753,7 @@ data load_data_detection(int n, char **paths, int m, int w, int h, int boxes, in
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 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;
@ -784,7 +785,7 @@ data load_data_detection(int n, char **paths, int m, int w, int h, int boxes, in
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;
@ -817,7 +818,7 @@ void *load_thread(void *ptr)
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){
@ -825,7 +826,7 @@ void *load_thread(void *ptr)
} 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.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){
@ -837,7 +838,7 @@ void *load_thread(void *ptr)
*(a.im) = load_image_color(a.path, 0, 0);
*(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;
@ -924,7 +925,7 @@ data load_data_old(char **paths, int n, int m, char **labels, int k, int w, int
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;
@ -961,25 +962,25 @@ data load_data_super(char **paths, int n, int m, int w, int h, int scale)
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;

9
src/data.h
View File

@ -55,6 +55,7 @@ typedef struct load_args{
int scale;
int small_object;
float jitter;
int flip;
float angle;
float aspect;
float saturation;
@ -83,11 +84,11 @@ void print_letters(float *pred, int n);
data load_data_captcha(char **paths, int n, int m, int k, int w, int h);
data load_data_captcha_encode(char **paths, int n, int m, int w, int h);
data load_data_old(char **paths, int n, int m, char **labels, int k, int w, int 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_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);
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);
data load_data_detection(int n, char **paths, int m, int w, int h, int boxes, int classes, int use_flip, float jitter, float hue, float saturation, float exposure, int small_object);
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);
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);
data load_data_super(char **paths, int n, int m, int w, int h, int scale);
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);
data load_go(char *filename);
box_label *read_boxes(char *filename, int *n);

1
src/detector.c
View File

@ -86,6 +86,7 @@ void train_detector(char *datacfg, char *cfgfile, char *weightfile, int *gpus, i
args.n = imgs;
args.m = plist->size;
args.classes = classes;
args.flip = net.flip;
args.jitter = jitter;
args.num_boxes = l.max_boxes;
args.small_object = net.small_object;

1
src/network.h
View File

@ -52,6 +52,7 @@ typedef struct network{
int h, w, c;
int max_crop;
int min_crop;
int flip; // horizontal flip 50% probability augmentaiont for classifier training (default = 1)
float angle;
float aspect;
float exposure;

1
src/parser.c
View File

@ -622,6 +622,7 @@ void parse_net_options(list *options, network *net)
net->inputs = option_find_int_quiet(options, "inputs", net->h * net->w * net->c);
net->max_crop = option_find_int_quiet(options, "max_crop",net->w*2);
net->min_crop = option_find_int_quiet(options, "min_crop",net->w);
net->flip = option_find_int_quiet(options, "flip", 1);
net->small_object = option_find_int_quiet(options, "small_object", 0);
net->angle = option_find_float_quiet(options, "angle", 0);