From 0948df52b850b908e7a74cb589d19fa29eb30368 Mon Sep 17 00:00:00 2001
From: Alexey <AlexeyAB@users.noreply.github.com>
Date: Tue, 08 May 2018 14:27:45 +0000
Subject: [PATCH] Merge pull request #741 from IlyaOvodov/Fix_detector_output
---
src/image.c | 105 ++++++++++++++++++++++++++++++++++++++++------------
1 files changed, 81 insertions(+), 24 deletions(-)
diff --git a/src/image.c b/src/image.c
index 499306b..467b95c 100644
--- a/src/image.c
+++ b/src/image.c
@@ -230,27 +230,76 @@
return alphabets;
}
-void draw_detections_v3(image im, detection *dets, int num, float thresh, char **names, image **alphabet, int classes)
-{
- int i, j;
- for (i = 0; i < num; ++i) {
- char labelstr[4096] = { 0 };
- int class_id = -1;
- for (j = 0; j < classes; ++j) {
- if (dets[i].prob[j] > thresh) {
- if (class_id < 0) {
- strcat(labelstr, names[j]);
- class_id = j;
- }
- else {
- strcat(labelstr, ", ");
- strcat(labelstr, names[j]);
- }
- printf("%s: %.0f%%\n", names[j], dets[i].prob[j] * 100);
+
+// Creates array of detections with prob > thresh and fills best_class for them
+detection_with_class* get_actual_detections(detection *dets, int dets_num, float thresh, int* selected_detections_num)
+{
+ int selected_num = 0;
+ detection_with_class* result_arr = calloc(dets_num, sizeof(detection_with_class));
+ for (int i = 0; i < dets_num; ++i) {
+ int best_class = -1;
+ float best_class_prob = thresh;
+ for (int j = 0; j < dets[i].classes; ++j) {
+ if (dets[i].prob[j] > best_class_prob ) {
+ best_class = j;
+ best_class_prob = dets[i].prob[j];
}
}
- if (class_id >= 0) {
+ if (best_class >= 0) {
+ result_arr[selected_num].det = dets[i];
+ result_arr[selected_num].best_class = best_class;
+ ++selected_num;
+ }
+ }
+ if (selected_detections_num)
+ *selected_detections_num = selected_num;
+ return result_arr;
+}
+
+// compare to sort detection** by bbox.x
+int compare_by_lefts(const void *a_ptr, const void *b_ptr) {
+ const detection_with_class* a = (detection_with_class*)a_ptr;
+ const detection_with_class* b = (detection_with_class*)b_ptr;
+ const float delta = (a->det.bbox.x - a->det.bbox.w/2) - (b->det.bbox.x - b->det.bbox.w/2);
+ return delta < 0 ? -1 : delta > 0 ? 1 : 0;
+}
+
+// compare to sort detection** by best_class probability
+int compare_by_probs(const void *a_ptr, const void *b_ptr) {
+ const detection_with_class* a = (detection_with_class*)a_ptr;
+ const detection_with_class* b = (detection_with_class*)b_ptr;
+ float delta = a->det.prob[a->best_class] - b->det.prob[b->best_class];
+ return delta < 0 ? -1 : delta > 0 ? 1 : 0;
+}
+
+void draw_detections_v3(image im, detection *dets, int num, float thresh, char **names, image **alphabet, int classes, int ext_output)
+{
+ int selected_detections_num;
+ detection_with_class* selected_detections = get_actual_detections(dets, num, thresh, &selected_detections_num);
+
+ // text output
+ qsort(selected_detections, selected_detections_num, sizeof(*selected_detections), compare_by_lefts);
+ for (int i = 0; i < selected_detections_num; ++i) {
+ const int best_class = selected_detections[i].best_class;
+ printf("%s: %.0f%%", names[best_class], selected_detections[i].det.prob[best_class] * 100);
+ if (ext_output)
+ printf("\t(left: %.0f\ttop: %.0f\tw: %0.f\th: %0.f)\n",
+ (selected_detections[i].det.bbox.x - selected_detections[i].det.bbox.w / 2)*im.w,
+ (selected_detections[i].det.bbox.y - selected_detections[i].det.bbox.h / 2)*im.h,
+ selected_detections[i].det.bbox.w*im.w, selected_detections[i].det.bbox.h*im.h);
+ else
+ printf("\n");
+ for (int j = 0; j < classes; ++j) {
+ if (selected_detections[i].det.prob[j] > thresh && j != best_class) {
+ printf("%s: %.0f%%\n", names[j], selected_detections[i].det.prob[j] * 100);
+ }
+ }
+ }
+
+ // image output
+ qsort(selected_detections, selected_detections_num, sizeof(*selected_detections), compare_by_probs);
+ for (int i = 0; i < selected_detections_num; ++i) {
int width = im.h * .006;
if (width < 1)
width = 1;
@@ -262,8 +311,8 @@
}
*/
- //printf("%d %s: %.0f%%\n", i, names[class_id], prob*100);
- int offset = class_id * 123457 % classes;
+ //printf("%d %s: %.0f%%\n", i, names[selected_detections[i].best_class], prob*100);
+ int offset = selected_detections[i].best_class * 123457 % classes;
float red = get_color(2, offset, classes);
float green = get_color(1, offset, classes);
float blue = get_color(0, offset, classes);
@@ -274,7 +323,7 @@
rgb[0] = red;
rgb[1] = green;
rgb[2] = blue;
- box b = dets[i].bbox;
+ box b = selected_detections[i].det.bbox;
//printf("%f %f %f %f\n", b.x, b.y, b.w, b.h);
int left = (b.x - b.w / 2.)*im.w;
@@ -295,12 +344,20 @@
draw_box_width(im, left, top, right, bot, width, red, green, blue);
if (alphabet) {
+ char labelstr[4096] = { 0 };
+ strcat(labelstr, names[selected_detections[i].best_class]);
+ for (int j = 0; j < classes; ++j) {
+ if (selected_detections[i].det.prob[j] > thresh && j != selected_detections[i].best_class) {
+ strcat(labelstr, ", ");
+ strcat(labelstr, names[j]);
+ }
+ }
image label = get_label_v3(alphabet, labelstr, (im.h*.03));
draw_label(im, top + width, left, label, rgb);
free_image(label);
}
- if (dets[i].mask) {
- image mask = float_to_image(14, 14, 1, dets[i].mask);
+ if (selected_detections[i].det.mask) {
+ image mask = float_to_image(14, 14, 1, selected_detections[i].det.mask);
image resized_mask = resize_image(mask, b.w*im.w, b.h*im.h);
image tmask = threshold_image(resized_mask, .5);
embed_image(tmask, im, left, top);
@@ -308,8 +365,8 @@
free_image(resized_mask);
free_image(tmask);
}
- }
}
+ free(selected_detections);
}
void draw_detections(image im, int num, float thresh, box *boxes, float **probs, char **names, image **alphabet, int classes)
--
Gitblit v1.10.0