From 1b5afb45838e603fa6780762eb8cc59246dc2d81 Mon Sep 17 00:00:00 2001
From: IlyaOvodov <b@ovdv.ru>
Date: Tue, 08 May 2018 11:09:35 +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/detector.c | 116 ++++++++++++++++++++++++++++++++++++++--------------------
1 files changed, 76 insertions(+), 40 deletions(-)
diff --git a/src/detector.c b/src/detector.c
index a6a5a5d..a38ed18 100644
--- a/src/detector.c
+++ b/src/detector.c
@@ -86,12 +86,13 @@
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 +100,7 @@
args.hue = net.hue;
#ifdef OPENCV
+ args.threads = 3;
IplImage* img = NULL;
float max_img_loss = 5;
int number_of_lines = 100;
@@ -108,7 +110,7 @@
#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){
@@ -131,7 +133,7 @@
}
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 +155,9 @@
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 +168,11 @@
#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, %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)
@@ -291,11 +293,11 @@
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));
@@ -385,7 +387,7 @@
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);
}
@@ -414,11 +416,12 @@
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));
//list *plist = get_paths("data/coco_val_5k.list");
@@ -452,12 +455,15 @@
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, ".png", ".txt", labelpath);
+ find_replace(labelpath, ".bmp", ".txt", labelpath);
+ find_replace(labelpath, ".JPG", ".txt", labelpath);
find_replace(labelpath, ".JPEG", ".txt", labelpath);
int num_labels = 0;
@@ -482,7 +488,7 @@
++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);
@@ -521,11 +527,12 @@
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);
+ fuse_conv_batchnorm(net);
srand(time(0));
list *plist = get_paths(valid_images);
@@ -603,15 +610,18 @@
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);
+ find_replace(labelpath, ".bmp", ".txt", labelpath);
+ find_replace(labelpath, ".JPG", ".txt", labelpath);
+ find_replace(labelpath, ".JPEG", ".txt", labelpath);
int num_labels = 0;
box_label *truth = read_boxes(labelpath, &num_labels);
int i, j;
@@ -635,6 +645,8 @@
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;
@@ -685,7 +697,13 @@
// 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;
}
@@ -705,7 +723,8 @@
}
}
- 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)
@@ -837,6 +856,11 @@
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));
@@ -857,8 +881,10 @@
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);
+ find_replace(labelpath, ".bmp", ".txt", labelpath);
+ find_replace(labelpath, ".JPG", ".txt", labelpath);
+ find_replace(labelpath, ".JPEG", ".txt", labelpath);
int num_labels = 0;
box_label *truth = read_boxes(labelpath, &num_labels);
//printf(" new path: %s \n", labelpath);
@@ -1010,20 +1036,22 @@
}
#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)
{
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;
@@ -1031,7 +1059,8 @@
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);
@@ -1041,8 +1070,8 @@
}
image im = load_image_color(input,0,0);
int letterbox = 0;
- image sized = resize_image(im, net.w, net.h);
- //image sized = letterbox_image(im, net.w, net.h); letterbox = 1;
+ //image sized = resize_image(im, net.w, net.h);
+ image sized = letterbox_image(im, net.w, net.h); letterbox = 1;
layer l = net.layers[net.n-1];
//box *boxes = calloc(l.w*l.h*l.n, sizeof(box));
@@ -1050,16 +1079,17 @@
//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);
+ if (nms) do_nms_sort(dets, nboxes, l.classes, nms);
+ draw_detections_v3(im, dets, nboxes, thresh, names, alphabet, l.classes, ext_output);
free_detections(dets, nboxes);
save_image(im, "predictions");
if (!dont_show) {
@@ -1093,8 +1123,11 @@
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");
if(argc < 4){
fprintf(stderr, "usage: %s %s [train/test/valid] [cfg] [weights (optional)]\n", argv[0], argv[1]);
return;
@@ -1128,22 +1161,25 @@
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);
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);
}
+ else printf(" There isn't such command: %s", argv[2]);
}
--
Gitblit v1.10.0