From 23cb35e6c8eae8b59fab161036ae3f417a55c8db Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Fri, 30 Mar 2018 11:46:51 +0000
Subject: [PATCH] Changed small_object
---
src/data.c | 117 ++++++++++++++++++++++++++++++++++++++++++++++++++--------
1 files changed, 101 insertions(+), 16 deletions(-)
diff --git a/src/data.c b/src/data.c
index 6187b34..1bb333a 100644
--- a/src/data.c
+++ b/src/data.c
@@ -269,7 +269,7 @@
h = boxes[i].h;
id = boxes[i].id;
- if (w < .01 || h < .01) continue;
+ if (w < .001 || h < .001) continue;
int col = (int)(x*num_boxes);
int row = (int)(y*num_boxes);
@@ -292,7 +292,8 @@
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, int small_object)
+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);
@@ -307,9 +308,12 @@
int i;
box_label *boxes = read_boxes(labelpath, &count);
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 < 0.01) boxes[i].w = 0.01;
- if (boxes[i].h < 0.01) boxes[i].h = 0.01;
+ if (boxes[i].w < lowest_w) boxes[i].w = lowest_w;
+ if (boxes[i].h < lowest_h) boxes[i].h = lowest_h;
}
}
randomize_boxes(boxes, count);
@@ -326,7 +330,7 @@
id = boxes[i].id;
// not detect small objects
- if ((w < 0.001 || h < 0.001)) { printf("small w = %f, h = %f \n", w, h); continue; }
+ if ((w < 0.001F || h < 0.001F)) continue;
truth[i*5+0] = x;
truth[i*5+1] = y;
@@ -668,6 +672,17 @@
return d;
}
+#ifdef OPENCV
+#include "opencv2/highgui/highgui_c.h"
+#include "opencv2/imgproc/imgproc_c.h"
+#include "opencv2/core/version.hpp"
+#ifndef CV_VERSION_EPOCH
+#include "opencv2/videoio/videoio_c.h"
+#include "opencv2/imgcodecs/imgcodecs_c.h"
+#endif
+
+#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)
{
char **random_paths = get_random_paths(paths, n, m);
@@ -681,10 +696,22 @@
d.y = make_matrix(n, 5*boxes);
for(i = 0; i < n; ++i){
- image orig = load_image_color(random_paths[i], 0, 0);
+ const char *filename = random_paths[i];
- int oh = orig.h;
- int ow = orig.w;
+ int flag = 1;
+ IplImage *src;
+ if ((src = cvLoadImage(filename, flag)) == 0)
+ {
+ fprintf(stderr, "Cannot load image \"%s\"\n", filename);
+ char buff[256];
+ sprintf(buff, "echo %s >> bad.list", filename);
+ system(buff);
+ continue;
+ //exit(0);
+ }
+
+ int oh = src->height;
+ int ow = src->width;
int dw = (ow*jitter);
int dh = (oh*jitter);
@@ -701,25 +728,80 @@
float sy = (float)sheight / oh;
int flip = random_gen()%2;
- image cropped = crop_image(orig, pleft, ptop, swidth, sheight);
float dx = ((float)pleft/ow)/sx;
float dy = ((float)ptop /oh)/sy;
- 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;
+ float dhue = rand_uniform_strong(-hue, hue);
+ float dsat = rand_scale(saturation);
+ float dexp = rand_scale(exposure);
- fill_truth_detection(random_paths[i], boxes, d.y.vals[i], classes, flip, dx, dy, 1./sx, 1./sy, small_object);
+ image ai = image_data_augmentation(src, w, h, pleft, ptop, swidth, sheight, flip, jitter, dhue, dsat, dexp);
+ d.X.vals[i] = ai.data;
+
+ //show_image(ai, "aug");
+ //cvWaitKey(0);
- free_image(orig);
- free_image(cropped);
+ fill_truth_detection(filename, boxes, d.y.vals[i], classes, flip, dx, dy, 1./sx, 1./sy, small_object, w, h);
+
+ cvReleaseImage(&src);
}
free(random_paths);
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)
+{
+ char **random_paths = get_random_paths(paths, n, m);
+ int i;
+ data d = { 0 };
+ d.shallow = 0;
+ d.X.rows = n;
+ d.X.vals = calloc(d.X.rows, sizeof(float*));
+ d.X.cols = h*w * 3;
+
+ 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*jitter);
+ int dh = (oh*jitter);
+
+ int pleft = rand_uniform_strong(-dw, dw);
+ int pright = rand_uniform_strong(-dw, dw);
+ int ptop = rand_uniform_strong(-dh, dh);
+ int pbot = rand_uniform_strong(-dh, dh);
+
+ int swidth = ow - pleft - pright;
+ int sheight = oh - ptop - pbot;
+
+ float sx = (float)swidth / ow;
+ float sy = (float)sheight / oh;
+
+ int flip = random_gen() % 2;
+ image cropped = crop_image(orig, pleft, ptop, swidth, sheight);
+
+ float dx = ((float)pleft / ow) / sx;
+ float dy = ((float)ptop / oh) / sy;
+
+ 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], boxes, d.y.vals[i], classes, flip, dx, dy, 1. / sx, 1. / sy, small_object, w, h);
+
+ free_image(orig);
+ free_image(cropped);
+ }
+ free(random_paths);
+ return d;
+}
+#endif // OPENCV
void *load_thread(void *ptr)
{
@@ -749,6 +831,9 @@
} else if (a.type == IMAGE_DATA){
*(a.im) = load_image_color(a.path, 0, 0);
*(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.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);
}
--
Gitblit v1.10.0