From f0abcfa02b2094396f955c743f7f11fcdb2e3d13 Mon Sep 17 00:00:00 2001
From: IlyaOvodov <b@ovdv.ru>
Date: Mon, 04 Jun 2018 15:57:15 +0000
Subject: [PATCH] Merge branch 'master' of https://github.com/AlexeyAB/darknet into Fix_get_color_depth
---
src/detector.c | 251 +++++++++++++++++++++++++++++++++++--------------
1 files changed, 179 insertions(+), 72 deletions(-)
diff --git a/src/detector.c b/src/detector.c
index 25968e6..e099e91 100644
--- a/src/detector.c
+++ b/src/detector.c
@@ -16,10 +16,10 @@
#ifndef CV_VERSION_EPOCH
#include "opencv2/videoio/videoio_c.h"
-#define OPENCV_VERSION CVAUX_STR(CV_VERSION_MAJOR)""CVAUX_STR(CV_VERSION_MINOR)""CVAUX_STR(CV_VERSION_REVISION)
+#define OPENCV_VERSION CVAUX_STR(CV_VERSION_MAJOR)"" CVAUX_STR(CV_VERSION_MINOR)"" CVAUX_STR(CV_VERSION_REVISION)
#pragma comment(lib, "opencv_world" OPENCV_VERSION ".lib")
#else
-#define OPENCV_VERSION CVAUX_STR(CV_VERSION_EPOCH)""CVAUX_STR(CV_VERSION_MAJOR)""CVAUX_STR(CV_VERSION_MINOR)
+#define OPENCV_VERSION CVAUX_STR(CV_VERSION_EPOCH)"" CVAUX_STR(CV_VERSION_MAJOR)"" CVAUX_STR(CV_VERSION_MINOR)
#pragma comment(lib, "opencv_core" OPENCV_VERSION ".lib")
#pragma comment(lib, "opencv_imgproc" OPENCV_VERSION ".lib")
#pragma comment(lib, "opencv_highgui" OPENCV_VERSION ".lib")
@@ -61,6 +61,11 @@
srand(time(0));
network net = nets[0];
+ if ((net.batch * net.subdivisions) == 1) {
+ printf("\n Error: You set incorrect value batch=1 for Training! You should set batch=64 subdivision=64 \n");
+ getchar();
+ }
+
int imgs = net.batch * net.subdivisions * ngpus;
printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
data train, buffer;
@@ -82,16 +87,18 @@
load_args args = {0};
args.w = net.w;
args.h = net.h;
- args.paths = paths;
+ args.c = net.c;
+ args.paths = paths;
args.n = imgs;
args.m = plist->size;
args.classes = classes;
+ args.flip = net.flip;
args.jitter = jitter;
args.num_boxes = l.max_boxes;
args.small_object = net.small_object;
args.d = &buffer;
args.type = DETECTION_DATA;
- args.threads = 64; // 8
+ args.threads = 16; // 64
args.angle = net.angle;
args.exposure = net.exposure;
@@ -99,6 +106,7 @@
args.hue = net.hue;
#ifdef OPENCV
+ args.threads = 3 * ngpus;
IplImage* img = NULL;
float max_img_loss = 5;
int number_of_lines = 100;
@@ -108,18 +116,30 @@
#endif //OPENCV
pthread_t load_thread = load_data(args);
- clock_t time;
+ double time;
int count = 0;
//while(i*imgs < N*120){
while(get_current_batch(net) < net.max_batches){
if(l.random && count++%10 == 0){
printf("Resizing\n");
- int dim = (rand() % 12 + (init_w/32 - 5)) * 32; // +-160
- //if (get_current_batch(net)+100 > net.max_batches) dim = 544;
+ //int dim = (rand() % 12 + (init_w/32 - 5)) * 32; // +-160
//int dim = (rand() % 4 + 16) * 32;
- printf("%d\n", dim);
- args.w = dim;
- args.h = dim;
+ //if (get_current_batch(net)+100 > net.max_batches) dim = 544;
+
+ //int random_val = rand() % 12;
+ //int dim_w = (random_val + (init_w / 32 - 5)) * 32; // +-160
+ //int dim_h = (random_val + (init_h / 32 - 5)) * 32; // +-160
+
+ float random_val = rand_scale(1.4); // *x or /x
+ int dim_w = roundl(random_val*init_w / 32) * 32;
+ int dim_h = roundl(random_val*init_h / 32) * 32;
+
+ if (dim_w < 32) dim_w = 32;
+ if (dim_h < 32) dim_h = 32;
+
+ printf("%d x %d \n", dim_w, dim_h);
+ args.w = dim_w;
+ args.h = dim_h;
pthread_join(load_thread, 0);
train = buffer;
@@ -127,11 +147,11 @@
load_thread = load_data(args);
for(i = 0; i < ngpus; ++i){
- resize_network(nets + i, dim, dim);
+ resize_network(nets + i, dim_w, dim_h);
}
net = nets[0];
}
- time=clock();
+ time=what_time_is_it_now();
pthread_join(load_thread, 0);
train = buffer;
load_thread = load_data(args);
@@ -153,9 +173,9 @@
save_image(im, "truth11");
*/
- printf("Loaded: %lf seconds\n", sec(clock()-time));
+ printf("Loaded: %lf seconds\n", (what_time_is_it_now()-time));
- time=clock();
+ time=what_time_is_it_now();
float loss = 0;
#ifdef GPU
if(ngpus == 1){
@@ -166,11 +186,11 @@
#else
loss = train_network(net, train);
#endif
- if (avg_loss < 0) avg_loss = loss;
+ if (avg_loss < 0 || avg_loss != avg_loss) avg_loss = loss; // if(-inf or nan)
avg_loss = avg_loss*.9 + loss*.1;
i = get_current_batch(net);
- printf("\n %d: %f, %f avg, %f rate, %lf seconds, %d images\n", get_current_batch(net), loss, avg_loss, get_current_rate(net), sec(clock()-time), i*imgs);
+ printf("\n %d: %f, %f avg loss, %f rate, %lf seconds, %d images\n", get_current_batch(net), loss, avg_loss, get_current_rate(net), (what_time_is_it_now()-time), i*imgs);
#ifdef OPENCV
if(!dont_show)
@@ -197,8 +217,25 @@
sprintf(buff, "%s/%s_final.weights", backup_directory, base);
save_weights(net, buff);
- //cvReleaseImage(&img);
- //cvDestroyAllWindows();
+#ifdef OPENCV
+ cvReleaseImage(&img);
+ cvDestroyAllWindows();
+#endif
+
+ // free memory
+ pthread_join(load_thread, 0);
+ free_data(buffer);
+
+ free(base);
+ free(paths);
+ free_list_contents(plist);
+ free_list(plist);
+
+ free_list_contents_kvp(options);
+ free_list(options);
+
+ free(nets);
+ free_network(net);
}
@@ -291,11 +328,11 @@
int *map = 0;
if (mapf) map = read_map(mapf);
- network net = parse_network_cfg_custom(cfgfile, 1);
+ network net = parse_network_cfg_custom(cfgfile, 1); // set batch=1
if (weightfile) {
load_weights(&net, weightfile);
}
- set_batch_network(&net, 1);
+ //set_batch_network(&net, 1);
fprintf(stderr, "Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
srand(time(0));
@@ -352,6 +389,7 @@
load_args args = { 0 };
args.w = net.w;
args.h = net.h;
+ args.c = net.c;
args.type = IMAGE_DATA;
//args.type = LETTERBOX_DATA;
@@ -385,7 +423,7 @@
int nboxes = 0;
int letterbox = (args.type == LETTERBOX_DATA);
detection *dets = get_network_boxes(&net, w, h, thresh, .5, map, 0, &nboxes, letterbox);
- if (nms) do_nms_sort_v3(dets, nboxes, classes, nms);
+ if (nms) do_nms_sort(dets, nboxes, classes, nms);
if (coco) {
print_cocos(fp, path, dets, nboxes, classes, w, h);
}
@@ -409,16 +447,16 @@
fprintf(fp, "\n]\n");
fclose(fp);
}
- fprintf(stderr, "Total Detection Time: %f Seconds\n", time(0) - start);
+ fprintf(stderr, "Total Detection Time: %f Seconds\n", (double)time(0) - start);
}
void validate_detector_recall(char *datacfg, char *cfgfile, char *weightfile)
{
- network net = parse_network_cfg_custom(cfgfile, 1);
+ network net = parse_network_cfg_custom(cfgfile, 1); // set batch=1
if (weightfile) {
load_weights(&net, weightfile);
}
- set_batch_network(&net, 1);
+ //set_batch_network(&net, 1);
fuse_conv_batchnorm(net);
srand(time(0));
@@ -446,20 +484,17 @@
for (i = 0; i < m; ++i) {
char *path = paths[i];
- image orig = load_image_color(path, 0, 0);
+ image orig = load_image(path, 0, 0, net.c);
image sized = resize_image(orig, net.w, net.h);
char *id = basecfg(path);
network_predict(net, sized.data);
int nboxes = 0;
int letterbox = 0;
detection *dets = get_network_boxes(&net, sized.w, sized.h, thresh, .5, 0, 1, &nboxes, letterbox);
- if (nms) do_nms_obj_v3(dets, nboxes, 1, nms);
+ if (nms) do_nms_obj(dets, nboxes, 1, nms);
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);
+ replace_image_to_label(path, labelpath);
int num_labels = 0;
box_label *truth = read_boxes(labelpath, &num_labels);
@@ -483,7 +518,7 @@
++correct;
}
}
-
+ //fprintf(stderr, " %s - %s - ", paths[i], labelpath);
fprintf(stderr, "%5d %5d %5d\tRPs/Img: %.2f\tIOU: %.2f%%\tRecall:%.2f%%\n", i, correct, total, (float)proposals / (i + 1), avg_iou * 100 / total, 100.*correct / total);
free(id);
free_image(orig);
@@ -521,12 +556,13 @@
char *mapf = option_find_str(options, "map", 0);
int *map = 0;
if (mapf) map = read_map(mapf);
+ FILE* reinforcement_fd = NULL;
- network net = parse_network_cfg_custom(cfgfile, 1);
+ network net = parse_network_cfg_custom(cfgfile, 1); // set batch=1
if (weightfile) {
load_weights(&net, weightfile);
}
- set_batch_network(&net, 1);
+ //set_batch_network(&net, 1);
fuse_conv_batchnorm(net);
srand(time(0));
@@ -561,6 +597,7 @@
load_args args = { 0 };
args.w = net.w;
args.h = net.h;
+ args.c = net.c;
args.type = IMAGE_DATA;
//args.type = LETTERBOX_DATA;
@@ -605,15 +642,12 @@
int nboxes = 0;
int letterbox = (args.type == LETTERBOX_DATA);
float hier_thresh = 0;
- detection *dets = get_network_boxes(&net, 1, 1, thresh, hier_thresh, 0, 1, &nboxes, letterbox);
- if (nms) do_nms_sort_v3(dets, nboxes, l.classes, nms);
+ detection *dets = get_network_boxes(&net, 1, 1, thresh, hier_thresh, 0, 0, &nboxes, letterbox);
+ //detection *dets = get_network_boxes(&net, val[t].w, val[t].h, thresh, hier_thresh, 0, 1, &nboxes, letterbox); // for letterbox=1
+ if (nms) do_nms_sort(dets, nboxes, l.classes, nms);
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);
+ replace_image_to_label(path, labelpath);
int num_labels = 0;
box_label *truth = read_boxes(labelpath, &num_labels);
int i, j;
@@ -629,14 +663,13 @@
char *path_dif = paths_dif[image_index];
char labelpath_dif[4096];
- find_replace(path_dif, "images", "labels", labelpath_dif);
- find_replace(labelpath_dif, "JPEGImages", "labels", labelpath_dif);
- find_replace(labelpath_dif, ".jpg", ".txt", labelpath_dif);
- find_replace(labelpath_dif, ".JPEG", ".txt", labelpath_dif);
- find_replace(labelpath_dif, ".png", ".txt", labelpath_dif);
+ replace_image_to_label(path_dif, labelpath_dif);
+
truth_dif = read_boxes(labelpath_dif, &num_labels_dif);
}
+ const int checkpoint_detections_count = detections_count;
+
for (i = 0; i < nboxes; ++i) {
int class_id;
@@ -687,7 +720,13 @@
// calc avg IoU, true-positives, false-positives for required Threshold
if (prob > thresh_calc_avg_iou) {
- if (truth_index > -1) {
+ int z, found = 0;
+ for (z = checkpoint_detections_count; z < detections_count-1; ++z)
+ if (detections[z].unique_truth_index == truth_index) {
+ found = 1; break;
+ }
+
+ if(truth_index > -1 && found == 0) {
avg_iou += max_iou;
++tp_for_thresh;
}
@@ -697,9 +736,18 @@
}
}
}
-
+
unique_truth_count += num_labels;
+ //static int previous_errors = 0;
+ //int total_errors = fp_for_thresh + (unique_truth_count - tp_for_thresh);
+ //int errors_in_this_image = total_errors - previous_errors;
+ //previous_errors = total_errors;
+ //if(reinforcement_fd == NULL) reinforcement_fd = fopen("reinforcement.txt", "wb");
+ //char buff[1000];
+ //sprintf(buff, "%s\n", path);
+ //if(errors_in_this_image > 0) fwrite(buff, sizeof(char), strlen(buff), reinforcement_fd);
+
free_detections(dets, nboxes);
free(id);
free_image(val[t]);
@@ -707,7 +755,8 @@
}
}
- avg_iou = avg_iou / (tp_for_thresh + fp_for_thresh);
+ if((tp_for_thresh + fp_for_thresh) > 0)
+ avg_iou = avg_iou / (tp_for_thresh + fp_for_thresh);
// SORT(detections)
@@ -819,6 +868,7 @@
free(truth_classes_count);
fprintf(stderr, "Total Detection Time: %f Seconds\n", (double)(time(0) - start));
+ if (reinforcement_fd != NULL) fclose(reinforcement_fd);
}
#ifdef OPENCV
@@ -839,6 +889,11 @@
void calc_anchors(char *datacfg, int num_of_clusters, int width, int height, int show)
{
printf("\n num_of_clusters = %d, width = %d, height = %d \n", num_of_clusters, width, height);
+ if (width < 0 || height < 0) {
+ printf("Usage: darknet detector calc_anchors data/voc.data -num_of_clusters 9 -width 416 -height 416 \n");
+ printf("Error: set width and height \n");
+ return;
+ }
//float pointsdata[] = { 1,1, 2,2, 6,6, 5,5, 10,10 };
float *rel_width_height_array = calloc(1000, sizeof(float));
@@ -856,11 +911,8 @@
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);
+ replace_image_to_label(path, labelpath);
+
int num_labels = 0;
box_label *truth = read_boxes(labelpath, &num_labels);
//printf(" new path: %s \n", labelpath);
@@ -1012,21 +1064,22 @@
}
#endif // OPENCV
-void test_detector(char *datacfg, char *cfgfile, char *weightfile, char *filename, float thresh, float hier_thresh, int dont_show)
+void test_detector(char *datacfg, char *cfgfile, char *weightfile, char *filename, float thresh,
+ float hier_thresh, int dont_show, int ext_output, int save_labels)
{
list *options = read_data_cfg(datacfg);
char *name_list = option_find_str(options, "names", "data/names.list");
char **names = get_labels(name_list);
image **alphabet = load_alphabet();
- network net = parse_network_cfg_custom(cfgfile, 1);
+ network net = parse_network_cfg_custom(cfgfile, 1); // set batch=1
if(weightfile){
load_weights(&net, weightfile);
}
- set_batch_network(&net, 1);
+ //set_batch_network(&net, 1);
fuse_conv_batchnorm(net);
srand(2222222);
- clock_t time;
+ double time;
char buff[256];
char *input = buff;
int j;
@@ -1034,7 +1087,8 @@
while(1){
if(filename){
strncpy(input, filename, 256);
- if (input[strlen(input) - 1] == 0x0d) input[strlen(input) - 1] = 0;
+ if(strlen(input) > 0)
+ if (input[strlen(input) - 1] == 0x0d) input[strlen(input) - 1] = 0;
} else {
printf("Enter Image Path: ");
fflush(stdout);
@@ -1042,7 +1096,7 @@
if(!input) return;
strtok(input, "\n");
}
- image im = load_image_color(input,0,0);
+ image im = load_image(input,0,0,net.c);
int letterbox = 0;
image sized = resize_image(im, net.w, net.h);
//image sized = letterbox_image(im, net.w, net.h); letterbox = 1;
@@ -1053,22 +1107,49 @@
//for(j = 0; j < l.w*l.h*l.n; ++j) probs[j] = calloc(l.classes, sizeof(float *));
float *X = sized.data;
- time=clock();
+ time= what_time_is_it_now();
network_predict(net, X);
- printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
+ //network_predict_image(&net, im); letterbox = 1;
+ printf("%s: Predicted in %f seconds.\n", input, (what_time_is_it_now()-time));
//get_region_boxes(l, 1, 1, thresh, probs, boxes, 0, 0);
- // if (nms) do_nms_sort(boxes, probs, l.w*l.h*l.n, l.classes, nms);
+ // if (nms) do_nms_sort_v2(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);
int nboxes = 0;
detection *dets = get_network_boxes(&net, im.w, im.h, thresh, hier_thresh, 0, 1, &nboxes, letterbox);
- if (nms) do_nms_sort_v3(dets, nboxes, l.classes, nms);
- draw_detections_v3(im, dets, nboxes, thresh, names, alphabet, l.classes);
- free_detections(dets, nboxes);
+ if (nms) do_nms_sort(dets, nboxes, l.classes, nms);
+ draw_detections_v3(im, dets, nboxes, thresh, names, alphabet, l.classes, ext_output);
save_image(im, "predictions");
if (!dont_show) {
show_image(im, "predictions");
}
+ // pseudo labeling concept - fast.ai
+ if(save_labels)
+ {
+ char labelpath[4096];
+ replace_image_to_label(input, labelpath);
+
+ FILE* fw = fopen(labelpath, "wb");
+ int i;
+ for (i = 0; i < nboxes; ++i) {
+ char buff[1024];
+ int class_id = -1;
+ float prob = 0;
+ for (j = 0; j < l.classes; ++j) {
+ if (dets[i].prob[j] > thresh && dets[i].prob[j] > prob) {
+ prob = dets[i].prob[j];
+ class_id = j;
+ }
+ }
+ if (class_id >= 0) {
+ sprintf(buff, "%d %2.4f %2.4f %2.4f %2.4f\n", class_id, dets[i].bbox.x, dets[i].bbox.y, dets[i].bbox.w, dets[i].bbox.h);
+ fwrite(buff, sizeof(char), strlen(buff), fw);
+ }
+ }
+ fclose(fw);
+ }
+
+ free_detections(dets, nboxes);
free_image(im);
free_image(sized);
//free(boxes);
@@ -1081,6 +1162,23 @@
#endif
if (filename) break;
}
+
+ // free memory
+ free_ptrs(names, net.layers[net.n - 1].classes);
+ free_list_contents_kvp(options);
+ free_list(options);
+
+ int i;
+ const int nsize = 8;
+ for (j = 0; j < nsize; ++j) {
+ for (i = 32; i < 127; ++i) {
+ free_image(alphabet[j][i]);
+ }
+ free(alphabet[j]);
+ }
+ free(alphabet);
+
+ free_network(net);
}
void run_detector(int argc, char **argv)
@@ -1096,8 +1194,12 @@
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 width = find_int_arg(argc, argv, "-width", 13);
- int heigh = find_int_arg(argc, argv, "-heigh", 13);
+ int width = find_int_arg(argc, argv, "-width", -1);
+ int height = find_int_arg(argc, argv, "-height", -1);
+ // extended output in test mode (output of rect bound coords)
+ // and for recall mode (extended output table-like format with results for best_class fit)
+ int ext_output = find_arg(argc, argv, "-ext_output");
+ int save_labels = find_arg(argc, argv, "-save_labels");
if(argc < 4){
fprintf(stderr, "usage: %s %s [train/test/valid] [cfg] [weights (optional)]\n", argv[0], argv[1]);
return;
@@ -1131,23 +1233,28 @@
char *cfg = argv[4];
char *weights = (argc > 5) ? argv[5] : 0;
if(weights)
- if (weights[strlen(weights) - 1] == 0x0d) weights[strlen(weights) - 1] = 0;
+ if(strlen(weights) > 0)
+ 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, hier_thresh, dont_show);
+ if(0==strcmp(argv[2], "test")) test_detector(datacfg, cfg, weights, filename, thresh, hier_thresh, dont_show, ext_output, save_labels);
else if(0==strcmp(argv[2], "train")) train_detector(datacfg, cfg, weights, gpus, ngpus, clear, dont_show);
else if(0==strcmp(argv[2], "valid")) validate_detector(datacfg, cfg, weights, outfile);
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, thresh);
- else if(0==strcmp(argv[2], "calc_anchors")) calc_anchors(datacfg, num_of_clusters, width, heigh, show);
+ else if(0==strcmp(argv[2], "calc_anchors")) calc_anchors(datacfg, num_of_clusters, width, height, show);
else if(0==strcmp(argv[2], "demo")) {
list *options = read_data_cfg(datacfg);
int classes = option_find_int(options, "classes", 20);
char *name_list = option_find_str(options, "names", "data/names.list");
char **names = get_labels(name_list);
if(filename)
- if (filename[strlen(filename) - 1] == 0x0d) filename[strlen(filename) - 1] = 0;
+ if(strlen(filename) > 0)
+ if (filename[strlen(filename) - 1] == 0x0d) filename[strlen(filename) - 1] = 0;
demo(cfg, weights, thresh, hier_thresh, cam_index, filename, names, classes, frame_skip, prefix, out_filename,
- http_stream_port, dont_show);
+ http_stream_port, dont_show, ext_output);
+
+ free_list_contents_kvp(options);
+ free_list(options);
}
else printf(" There isn't such command: %s", argv[2]);
}
--
Gitblit v1.10.0