From 028696bf15efeca3acb3db8c42a96f7b9e0f55ff Mon Sep 17 00:00:00 2001
From: iovodov <b@ovdv.ru>
Date: Thu, 03 May 2018 13:33:46 +0000
Subject: [PATCH] Output improvements for detector results: When printing detector results, output was done in random order, obfuscating results for interpreting. Now: 1. Text output includes coordinates of rects in (left,right,top,bottom in pixels) along with label and score 2. Text output is sorted by rect lefts to simplify finding appropriate rects on image 3. If several class probs are > thresh for some detection, the most probable is written first and coordinates for others are not repeated 4. Rects are imprinted in image in order by their best class prob, so most probable rects are always on top and not overlayed by less probable ones 5. Most probable label for rect is always written first Also: 6. Message about low GPU memory include required amount
---
src/image.c | 168 +++++++++++++++++++++++++++++++++++++++----------------
1 files changed, 118 insertions(+), 50 deletions(-)
diff --git a/src/image.c b/src/image.c
index d29f0c1..a397dea 100644
--- a/src/image.c
+++ b/src/image.c
@@ -37,6 +37,35 @@
return r;
}
+static float get_pixel(image m, int x, int y, int c)
+{
+ assert(x < m.w && y < m.h && c < m.c);
+ return m.data[c*m.h*m.w + y*m.w + x];
+}
+static float get_pixel_extend(image m, int x, int y, int c)
+{
+ if (x < 0 || x >= m.w || y < 0 || y >= m.h) return 0;
+ /*
+ if(x < 0) x = 0;
+ if(x >= m.w) x = m.w-1;
+ if(y < 0) y = 0;
+ if(y >= m.h) y = m.h-1;
+ */
+ if (c < 0 || c >= m.c) return 0;
+ return get_pixel(m, x, y, c);
+}
+static void set_pixel(image m, int x, int y, int c, float val)
+{
+ if (x < 0 || y < 0 || c < 0 || x >= m.w || y >= m.h || c >= m.c) return;
+ assert(x < m.w && y < m.h && c < m.c);
+ m.data[c*m.h*m.w + y*m.w + x] = val;
+}
+static void add_pixel(image m, int x, int y, int c, float val)
+{
+ assert(x < m.w && y < m.h && c < m.c);
+ m.data[c*m.h*m.w + y*m.w + x] += val;
+}
+
void composite_image(image source, image dest, int dx, int dy)
{
int x,y,k;
@@ -200,28 +229,73 @@
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) {
+
+// Creates array of detections with prob > thresh and fills best_class for them
+detection** get_actual_detections(detection *dets, int dets_num, int classes, float thresh, int* selected_detections_num)
+{
+ int selected_num = 0;
+ detection** result_arr = calloc(dets_num, sizeof(detection*));
+ for (int i = 0; i < dets_num; ++i) {
+ dets[i].best_class = -1;
+ for (int j = 0; j < classes; ++j) {
if (dets[i].prob[j] > thresh) {
- if (class_id < 0) {
- strcat(labelstr, names[j]);
- class_id = j;
+ if (dets[i].best_class < 0 || dets[i].prob[dets[i].best_class] < dets[i].prob[j]) {
+ dets[i].best_class = j;
}
- else {
- strcat(labelstr, ", ");
- strcat(labelstr, names[j]);
- }
- printf("%s: %.0f%%\n", names[j], dets[i].prob[j] * 100);
}
}
- if (class_id >= 0) {
+ if (dets[i].best_class >= 0) {
+ result_arr[selected_num] = &(dets[i]);
+ ++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, const void *b) {
+ const float delta = ((*(detection**)a)->bbox.x - (*(detection**)a)->bbox.w / 2) - ((*(detection**)b)->bbox.x - (*(detection**)b)->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* a = *(detection**)a_ptr;
+ const detection* b = *(detection**)b_ptr;
+ float delta = a->prob[a->best_class] - b->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 selected_detections_num;
+ detection** selected_detections = get_actual_detections(dets, num, classes, 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%%\t(left: %.0f\ttop: %.0f\tw: %0.f\th: %0.f)\n", names[best_class],
+ selected_detections[i]->prob[best_class] * 100,
+ (selected_detections[i]->bbox.x - selected_detections[i]->bbox.w / 2)*im.w,
+ (selected_detections[i]->bbox.y - selected_detections[i]->bbox.h / 2)*im.h,
+ selected_detections[i]->bbox.w*im.w, selected_detections[i]->bbox.h*im.h);
+ for (int j = 0; j < classes; ++j) {
+ if (selected_detections[i]->prob[j] > thresh && j != best_class) {
+ printf("%s: %.0f%%\n", names[j], selected_detections[i]->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;
/*
if(0){
@@ -230,8 +304,8 @@
}
*/
- //printf("%d %s: %.0f%%\n", i, names[class_id], prob*100);
- int offset = class_id * 123457 % classes;
+ //printf("%d %s: %.0f%%\n", i, names[dets[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);
@@ -242,7 +316,7 @@
rgb[0] = red;
rgb[1] = green;
rgb[2] = blue;
- box b = dets[i].bbox;
+ box b = selected_detections[i]->bbox;
//printf("%f %f %f %f\n", b.x, b.y, b.w, b.h);
int left = (b.x - b.w / 2.)*im.w;
@@ -255,14 +329,28 @@
if (top < 0) top = 0;
if (bot > im.h - 1) bot = im.h - 1;
+ //int b_x_center = (left + right) / 2;
+ //int b_y_center = (top + bot) / 2;
+ //int b_width = right - left;
+ //int b_height = bot - top;
+ //sprintf(labelstr, "%d x %d - w: %d, h: %d", b_x_center, b_y_center, b_width, b_height);
+
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]->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]->mask) {
+ image mask = float_to_image(14, 14, 1, selected_detections[i]->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);
@@ -270,8 +358,8 @@
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)
@@ -393,6 +481,12 @@
if (top < 0) top = 0;
if (bot > show_img->height - 1) bot = show_img->height - 1;
+ //int b_x_center = (left + right) / 2;
+ //int b_y_center = (top + bot) / 2;
+ //int b_width = right - left;
+ //int b_height = bot - top;
+ //sprintf(labelstr, "%d x %d - w: %d, h: %d", b_x_center, b_y_center, b_width, b_height);
+
float const font_size = show_img->height / 1000.F;
CvPoint pt1, pt2, pt_text, pt_text_bg1, pt_text_bg2;
pt1.x = left;
@@ -418,7 +512,7 @@
black_color.val[0] = 0;
CvFont font;
cvInitFont(&font, CV_FONT_HERSHEY_SIMPLEX, font_size, font_size, 0, font_size * 3, 8);
- cvPutText(show_img, names[class_id], pt_text, &font, black_color);
+ cvPutText(show_img, labelstr, pt_text, &font, black_color);
}
}
}
@@ -560,7 +654,7 @@
cvPutText(img, char_buff, pt1, &font, CV_RGB(0, 0, 0));
cvShowImage("average loss", img);
int k = cvWaitKey(20);
- if (k == 's') cvSaveImage("chart.jpg", img, 0);
+ if (k == 's' || current_batch == (max_batches-1)) cvSaveImage("chart.jpg", img, 0);
}
#endif // OPENCV
@@ -1629,32 +1723,6 @@
return out;
}
-float get_pixel(image m, int x, int y, int c)
-{
- assert(x < m.w && y < m.h && c < m.c);
- return m.data[c*m.h*m.w + y*m.w + x];
-}
-float get_pixel_extend(image m, int x, int y, int c)
-{
- if(x < 0) x = 0;
- if(x >= m.w) x = m.w-1;
- if(y < 0) y = 0;
- if(y >= m.h) y = m.h-1;
- if(c < 0 || c >= m.c) return 0;
- return get_pixel(m, x, y, c);
-}
-void set_pixel(image m, int x, int y, int c, float val)
-{
- if (x < 0 || y < 0 || c < 0 || x >= m.w || y >= m.h || c >= m.c) return;
- assert(x < m.w && y < m.h && c < m.c);
- m.data[c*m.h*m.w + y*m.w + x] = val;
-}
-void add_pixel(image m, int x, int y, int c, float val)
-{
- assert(x < m.w && y < m.h && c < m.c);
- m.data[c*m.h*m.w + y*m.w + x] += val;
-}
-
void print_image(image m)
{
int i, j, k;
--
Gitblit v1.10.0