From 01bec657080d123a5b44a10ec94ebe132e20b1f3 Mon Sep 17 00:00:00 2001
From: IlyaOvodov <b@ovdv.ru>
Date: Wed, 30 May 2018 16:51:55 +0000
Subject: [PATCH] "channel" parameter of [net] is used in detector when preparing images for net.
---
src/detector.c | 162 ++++++++++++++++++++++++++++++++++++-----------------
1 files changed, 110 insertions(+), 52 deletions(-)
diff --git a/src/detector.c b/src/detector.c
index e891cd7..202fbf9 100644
--- a/src/detector.c
+++ b/src/detector.c
@@ -1,8 +1,3 @@
-#ifdef _DEBUG
-#include <stdlib.h>
-#include <crtdbg.h>
-#endif
-
#include "network.h"
#include "region_layer.h"
#include "cost_layer.h"
@@ -21,10 +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")
@@ -66,6 +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;
@@ -87,7 +87,8 @@
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;
@@ -121,12 +122,24 @@
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;
@@ -134,7 +147,7 @@
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];
}
@@ -177,7 +190,7 @@
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), (what_time_is_it_now()-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)
@@ -204,8 +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);
}
@@ -359,6 +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;
@@ -416,7 +447,7 @@
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)
@@ -453,7 +484,7 @@
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);
@@ -463,13 +494,7 @@
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);
+ replace_image_to_label(path, labelpath);
int num_labels = 0;
box_label *truth = read_boxes(labelpath, &num_labels);
@@ -531,6 +556,7 @@
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); // set batch=1
if (weightfile) {
@@ -571,6 +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;
@@ -620,13 +647,7 @@
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, ".png", ".txt", labelpath);
- find_replace(labelpath, ".bmp", ".txt", 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);
int i, j;
@@ -642,11 +663,8 @@
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);
}
@@ -718,9 +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]);
@@ -841,6 +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
@@ -883,13 +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, ".png", ".txt", labelpath);
- find_replace(labelpath, ".bmp", ".txt", 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);
//printf(" new path: %s \n", labelpath);
@@ -1041,7 +1064,8 @@
}
#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");
@@ -1072,7 +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;
@@ -1093,13 +1117,39 @@
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(dets, nboxes, l.classes, nms);
- draw_detections_v3(im, dets, nboxes, thresh, names, alphabet, l.classes);
- free_detections(dets, nboxes);
+ 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);
@@ -1115,6 +1165,7 @@
// free memory
free_ptrs(names, net.layers[net.n - 1].classes);
+ free_list_contents_kvp(options);
free_list(options);
int i;
@@ -1145,6 +1196,10 @@
int num_of_clusters = find_int_arg(argc, argv, "-num_of_clusters", 5);
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;
@@ -1181,7 +1236,7 @@
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);
@@ -1196,7 +1251,10 @@
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