From 9ff40baa4f0b005d50c4e3302b4103551160943f Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Wed, 07 Feb 2018 22:04:40 +0000
Subject: [PATCH] Fixes for training Yolo on small objects
---
src/data.c | 17 ++++++++++++-----
1 files changed, 12 insertions(+), 5 deletions(-)
diff --git a/src/data.c b/src/data.c
index ad9ef8b..71781aa 100644
--- a/src/data.c
+++ b/src/data.c
@@ -292,7 +292,7 @@
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)
{
char labelpath[4096];
find_replace(path, "images", "labels", labelpath);
@@ -305,6 +305,12 @@
find_replace(labelpath, ".JPEG", ".txt", labelpath);
int count = 0;
box_label *boxes = read_boxes(labelpath, &count);
+ if (small_object == 1) {
+ for (int i = 0; i < count; ++i) {
+ if (boxes[i].w < 0.01) boxes[i].w = 0.01;
+ if (boxes[i].h < 0.01) boxes[i].h = 0.01;
+ }
+ }
randomize_boxes(boxes, count);
correct_boxes(boxes, count, dx, dy, sx, sy, flip);
if(count > num_boxes) count = num_boxes;
@@ -319,7 +325,8 @@
h = boxes[i].h;
id = boxes[i].id;
- if ((w < .01 || h < .01)) continue;
+ // not detect small objects
+ if ((w < 0.01 || h < 0.01)) continue;
truth[i*5+0] = x;
truth[i*5+1] = y;
@@ -661,7 +668,7 @@
return d;
}
-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)
+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)
{
char **random_paths = get_random_paths(paths, n, m);
int i;
@@ -704,7 +711,7 @@
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);
+ fill_truth_detection(random_paths[i], boxes, d.y.vals[i], classes, flip, dx, dy, 1./sx, 1./sy, small_object);
free_image(orig);
free_image(cropped);
@@ -734,7 +741,7 @@
} 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.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);
} 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){
--
Gitblit v1.10.0