From f39160f6e8f4465e9325e235e18f0d9413d1f672 Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Sun, 04 Mar 2018 00:09:40 +0000
Subject: [PATCH] Added: calc_anchors
---
src/detector.c | 163 ++++++++++++++++++++++++++++++++++++++++++++++++-----
1 files changed, 146 insertions(+), 17 deletions(-)
diff --git a/src/detector.c b/src/detector.c
index ce259fd..8eaffce 100644
--- a/src/detector.c
+++ b/src/detector.c
@@ -10,7 +10,9 @@
#ifdef OPENCV
#include "opencv2/highgui/highgui_c.h"
#include "opencv2/core/core_c.h"
+//#include "opencv2/core/core.hpp"
#include "opencv2/core/version.hpp"
+#include "opencv2/imgproc/imgproc_c.h"
#ifndef CV_VERSION_EPOCH
#include "opencv2/videoio/videoio_c.h"
@@ -245,8 +247,8 @@
if (ymax > h) ymax = h;
for(j = 0; j < classes; ++j){
- int class = j;
- if (probs[i][class]) fprintf(fp, "%d %d %f %f %f %f %f\n", id, j+1, probs[i][class],
+ int class_id = j;
+ if (probs[i][class_id]) fprintf(fp, "%d %d %f %f %f %f %f\n", id, j+1, probs[i][class_id],
xmin, ymin, xmax, ymax);
}
}
@@ -495,7 +497,7 @@
return 0;
}
-void validate_detector_map(char *datacfg, char *cfgfile, char *weightfile)
+void validate_detector_map(char *datacfg, char *cfgfile, char *weightfile, float thresh_calc_avg_iou)
{
int j;
list *options = read_data_cfg(datacfg);
@@ -552,9 +554,14 @@
args.h = net.h;
args.type = IMAGE_DATA;
+ //const float thresh_calc_avg_iou = 0.24;
+ float avg_iou = 0;
+ int tp_for_thresh = 0;
+ int fp_for_thresh = 0;
+
box_prob *detections = calloc(1, sizeof(box_prob));
int detections_count = 0;
- int unique_truth_index = 0;
+ int unique_truth_count = 0;
int *truth_classes_count = calloc(classes, sizeof(int));
@@ -642,7 +649,7 @@
if (current_iou > iou_thresh && class_id == truth[j].id) {
if (current_iou > max_iou) {
max_iou = current_iou;
- truth_index = unique_truth_index + j;
+ truth_index = unique_truth_count + j;
}
}
}
@@ -659,14 +666,25 @@
float current_iou = box_iou(boxes[i], t);
if (current_iou > iou_thresh && class_id == truth_dif[j].id) {
--detections_count;
+ break;
}
}
}
+
+ // calc avg IoU, true-positives, false-positives for required Threshold
+ if (prob > thresh_calc_avg_iou) {
+ if (truth_index > -1) {
+ avg_iou += max_iou;
+ ++tp_for_thresh;
+ }
+ else
+ fp_for_thresh++;
+ }
}
}
}
- unique_truth_index += num_labels;
+ unique_truth_count += num_labels;
free(id);
free_image(val[t]);
@@ -674,6 +692,8 @@
}
}
+ avg_iou = avg_iou / (tp_for_thresh + fp_for_thresh);
+
// SORT(detections)
qsort(detections, detections_count, sizeof(box_prob), detections_comparator);
@@ -689,10 +709,10 @@
for (i = 0; i < classes; ++i) {
pr[i] = calloc(detections_count, sizeof(pr_t));
}
- printf("detections_count = %d, unique_truth_index = %d \n", detections_count, unique_truth_index);
+ printf("detections_count = %d, unique_truth_count = %d \n", detections_count, unique_truth_count);
- int *truth_flags = calloc(unique_truth_index, sizeof(int));
+ int *truth_flags = calloc(unique_truth_count, sizeof(int));
int rank;
for (rank = 0; rank < detections_count; ++rank) {
@@ -754,15 +774,24 @@
}
}
}
- //printf("point = %d, cur_recall = %.4f, cur_precision = %.4f \n", point, cur_recall, cur_precision);
+ //printf("class_id = %d, point = %d, cur_recall = %.4f, cur_precision = %.4f \n", i, point, cur_recall, cur_precision);
avg_precision += cur_precision;
}
avg_precision = avg_precision / 11;
- printf("class = %d, name = %s, \t ap = %2.2f %% \n", i, names[i], avg_precision*100);
+ printf("class_id = %d, name = %s, \t ap = %2.2f %% \n", i, names[i], avg_precision*100);
mean_average_precision += avg_precision;
}
+ const float cur_precision = (float)tp_for_thresh / ((float)tp_for_thresh + (float)fp_for_thresh);
+ const float cur_recall = (float)tp_for_thresh / ((float)tp_for_thresh + (float)(unique_truth_count - tp_for_thresh));
+ const float f1_score = 2.F * cur_precision * cur_recall / (cur_precision + cur_recall);
+ printf(" for thresh = %1.2f, precision = %1.2f, recall = %1.2f, F1-score = %1.2f \n",
+ thresh_calc_avg_iou, cur_precision, cur_recall, f1_score);
+
+ printf(" for thresh = %0.2f, TP = %d, FP = %d, FN = %d, average IoU = %2.2f %% \n",
+ thresh_calc_avg_iou, tp_for_thresh, fp_for_thresh, unique_truth_count - tp_for_thresh, avg_iou * 100);
+
mean_average_precision = mean_average_precision / classes;
printf("\n mean average precision (mAP) = %f, or %2.2f %% \n", mean_average_precision, mean_average_precision*100);
@@ -777,7 +806,96 @@
fprintf(stderr, "Total Detection Time: %f Seconds\n", (double)(time(0) - start));
}
-void test_detector(char *datacfg, char *cfgfile, char *weightfile, char *filename, float thresh)
+#ifdef OPENCV
+void calc_anchors(char *datacfg, int num_of_clusters, int final_width, int final_height)
+{
+ printf("\n num_of_clusters = %d, final_width = %d, final_height = %d \n", num_of_clusters, final_width, final_height);
+
+ //float pointsdata[] = { 1,1, 2,2, 6,6, 5,5, 10,10 };
+ float *rel_width_height_array = calloc(1000, sizeof(float));
+
+ list *options = read_data_cfg(datacfg);
+ char *train_images = option_find_str(options, "train", "data/train.list");
+ list *plist = get_paths(train_images);
+ int number_of_images = plist->size;
+ char **paths = (char **)list_to_array(plist);
+
+ int number_of_boxes = 0;
+ printf(" read labels from %d images \n", number_of_images);
+
+ int i, j;
+ for (i = 0; i < number_of_images; ++i) {
+ char *path = paths[i];
+ char labelpath[4096];
+ find_replace(path, "images", "labels", labelpath);
+ find_replace(labelpath, "JPEGImages", "labels", labelpath);
+ find_replace(labelpath, ".jpg", ".txt", labelpath);
+ find_replace(labelpath, ".JPEG", ".txt", labelpath);
+ find_replace(labelpath, ".png", ".txt", labelpath);
+ int num_labels = 0;
+ box_label *truth = read_boxes(labelpath, &num_labels);
+ //printf(" new path: %s \n", labelpath);
+ for (j = 0; j < num_labels; ++j)
+ {
+ number_of_boxes++;
+ rel_width_height_array = realloc(rel_width_height_array, 2 * number_of_boxes * sizeof(float));
+ rel_width_height_array[number_of_boxes * 2 - 2] = truth[j].w * final_width;
+ rel_width_height_array[number_of_boxes * 2 - 1] = truth[j].h * final_height;
+ printf("\r loaded \t image: %d \t box: %d", i+1, number_of_boxes);
+ }
+ }
+ printf("\n all loaded. \n");
+
+ //int number_of_boxes = 10;
+ CvMat* points = cvCreateMat(number_of_boxes, 2, CV_32FC1);
+ CvMat* centers = cvCreateMat(num_of_clusters, 2, CV_32FC1);
+ CvMat* labels = cvCreateMat(number_of_boxes, 1, CV_32SC1);
+
+ for (i = 0; i < number_of_boxes; ++i) {
+ points->data.fl[i * 2] = rel_width_height_array[i * 2];
+ points->data.fl[i * 2 + 1] = rel_width_height_array[i * 2 + 1];
+ //cvSet1D(points, i * 2, cvScalar(rel_width_height_array[i * 2], 0, 0, 0));
+ //cvSet1D(points, i * 2 + 1, cvScalar(rel_width_height_array[i * 2 + 1], 0, 0, 0));
+ }
+
+
+ const int attemps = 1000;
+ double compactness;
+
+ enum {
+ KMEANS_RANDOM_CENTERS = 0,
+ KMEANS_USE_INITIAL_LABELS = 1,
+ KMEANS_PP_CENTERS = 2
+ };
+
+ printf("\n calculating k-means++ ...");
+ // Should be used: distance(box, centroid) = 1 - IoU(box, centroid)
+ cvKMeans2(points, num_of_clusters, labels,
+ cvTermCriteria(CV_TERMCRIT_EPS+CV_TERMCRIT_ITER, 1000, 0), attemps,
+ 0, KMEANS_RANDOM_CENTERS,
+ centers, &compactness);
+
+ printf("\n");
+ printf("anchors = ");
+ for (i = 0; i < num_of_clusters; ++i) {
+ printf("%2.2f,%2.2f, ", centers->data.fl[i * 2], centers->data.fl[i * 2 + 1]);
+ }
+
+ //for (i = 0; i < number_of_boxes; ++i)
+ // printf("%2.2f,%2.2f, ", points->data.fl[i * 2], points->data.fl[i * 2 + 1]);
+
+ free(rel_width_height_array);
+ cvReleaseMat(&points);
+ cvReleaseMat(¢ers);
+ cvReleaseMat(&labels);
+}
+#else
+void calc_anchors(char *datacfg, int num_of_clusters, int final_width, int final_height) {
+ printf(" k-means++ can't be used without OpenCV, because there is used cvKMeans2 implementation \n");
+}
+#endif // OPENCV
+
+void test_detector(char *datacfg, char *cfgfile, char *weightfile, char *filename, float thresh, int dont_show)
{
list *options = read_data_cfg(datacfg);
char *name_list = option_find_str(options, "names", "data/names.list");
@@ -822,15 +940,19 @@
if (nms) do_nms_sort(boxes, probs, l.w*l.h*l.n, l.classes, nms);
draw_detections(im, l.w*l.h*l.n, thresh, boxes, probs, names, alphabet, l.classes);
save_image(im, "predictions");
- show_image(im, "predictions");
+ if (!dont_show) {
+ show_image(im, "predictions");
+ }
free_image(im);
free_image(sized);
free(boxes);
free_ptrs((void **)probs, l.w*l.h*l.n);
#ifdef OPENCV
- cvWaitKey(0);
- cvDestroyAllWindows();
+ if (!dont_show) {
+ cvWaitKey(0);
+ cvDestroyAllWindows();
+ }
#endif
if (filename) break;
}
@@ -838,11 +960,16 @@
void run_detector(int argc, char **argv)
{
+ int dont_show = find_arg(argc, argv, "-dont_show");
+ int http_stream_port = find_int_arg(argc, argv, "-http_port", -1);
char *out_filename = find_char_arg(argc, argv, "-out_filename", 0);
char *prefix = find_char_arg(argc, argv, "-prefix", 0);
float thresh = find_float_arg(argc, argv, "-thresh", .24);
int cam_index = find_int_arg(argc, argv, "-c", 0);
int frame_skip = find_int_arg(argc, argv, "-s", 0);
+ int num_of_clusters = find_int_arg(argc, argv, "-num_of_clusters", 5);
+ int final_width = find_int_arg(argc, argv, "-final_width", 13);
+ int final_heigh = find_int_arg(argc, argv, "-final_heigh", 13);
if(argc < 4){
fprintf(stderr, "usage: %s %s [train/test/valid] [cfg] [weights (optional)]\n", argv[0], argv[1]);
return;
@@ -878,11 +1005,12 @@
if(weights)
if (weights[strlen(weights) - 1] == 0x0d) weights[strlen(weights) - 1] = 0;
char *filename = (argc > 6) ? argv[6]: 0;
- if(0==strcmp(argv[2], "test")) test_detector(datacfg, cfg, weights, filename, thresh);
+ if(0==strcmp(argv[2], "test")) test_detector(datacfg, cfg, weights, filename, thresh, dont_show);
else if(0==strcmp(argv[2], "train")) train_detector(datacfg, cfg, weights, gpus, ngpus, clear);
else if(0==strcmp(argv[2], "valid")) validate_detector(datacfg, cfg, weights);
else if(0==strcmp(argv[2], "recall")) validate_detector_recall(datacfg, cfg, weights);
- else if(0==strcmp(argv[2], "map")) validate_detector_map(datacfg, cfg, weights);
+ else if(0==strcmp(argv[2], "map")) validate_detector_map(datacfg, cfg, weights, thresh);
+ else if(0==strcmp(argv[2], "calc_anchors")) calc_anchors(datacfg, num_of_clusters, final_width, final_heigh);
else if(0==strcmp(argv[2], "demo")) {
list *options = read_data_cfg(datacfg);
int classes = option_find_int(options, "classes", 20);
@@ -890,6 +1018,7 @@
char **names = get_labels(name_list);
if(filename)
if (filename[strlen(filename) - 1] == 0x0d) filename[strlen(filename) - 1] = 0;
- demo(cfg, weights, thresh, cam_index, filename, names, classes, frame_skip, prefix, out_filename);
+ demo(cfg, weights, thresh, cam_index, filename, names, classes, frame_skip, prefix, out_filename,
+ http_stream_port, dont_show);
}
}
--
Gitblit v1.10.0