From 89c11f83ed49c58c3031200d8ed053b4f671db09 Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Wed, 16 May 2018 12:05:46 +0000
Subject: [PATCH] Fixed darknet.py - uses batch=1 by default
---
src/data.c | 46 ++++++++++++++++++++++++++--------------------
1 files changed, 26 insertions(+), 20 deletions(-)
diff --git a/src/data.c b/src/data.c
index 1bb333a..4bb1b0f 100644
--- a/src/data.c
+++ b/src/data.c
@@ -104,7 +104,7 @@
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 +115,9 @@
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 +137,10 @@
{
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;
@@ -302,15 +306,15 @@
find_replace(labelpath, "raw", "labels", labelpath);
find_replace(labelpath, ".jpg", ".txt", labelpath);
find_replace(labelpath, ".png", ".txt", labelpath);
+ find_replace(labelpath, ".bmp", ".txt", labelpath);
find_replace(labelpath, ".JPG", ".txt", labelpath);
find_replace(labelpath, ".JPEG", ".txt", labelpath);
int count = 0;
int i;
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) {
- 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;
@@ -330,7 +334,9 @@
id = boxes[i].id;
// not detect small objects
- if ((w < 0.001F || h < 0.001F)) continue;
+ //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;
truth[i*5+0] = x;
truth[i*5+1] = y;
@@ -683,7 +689,7 @@
#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;
@@ -727,7 +733,7 @@
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;
@@ -750,7 +756,7 @@
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;
@@ -782,7 +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;
@@ -815,7 +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){
@@ -823,7 +829,7 @@
} 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){
@@ -835,7 +841,7 @@
*(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;
@@ -922,7 +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;
@@ -959,25 +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