From 54f83e153549dd1a63bcc8fa5e55fb171621a989 Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Wed, 17 Jan 2018 18:05:07 +0000
Subject: [PATCH] Some fixes
---
src/detector.c | 158 ++++++++++++++++++++++++++++++++--------------------
1 files changed, 97 insertions(+), 61 deletions(-)
diff --git a/src/detector.c b/src/detector.c
index a513816..f401d20 100644
--- a/src/detector.c
+++ b/src/detector.c
@@ -9,7 +9,22 @@
#ifdef OPENCV
#include "opencv2/highgui/highgui_c.h"
+#include "opencv2/core/core_c.h"
+#include "opencv2/core/version.hpp"
+
+#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)
+#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)
+#pragma comment(lib, "opencv_core" OPENCV_VERSION ".lib")
+#pragma comment(lib, "opencv_imgproc" OPENCV_VERSION ".lib")
+#pragma comment(lib, "opencv_highgui" OPENCV_VERSION ".lib")
#endif
+
+#endif
+
static int coco_ids[] = {1,2,3,4,5,6,7,8,9,10,11,13,14,15,16,17,18,19,20,21,22,23,24,25,27,28,31,32,33,34,35,36,37,38,39,40,41,42,43,44,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,67,70,72,73,74,75,76,77,78,79,80,81,82,84,85,86,87,88,89,90};
void train_detector(char *datacfg, char *cfgfile, char *weightfile, int *gpus, int ngpus, int clear)
@@ -55,6 +70,9 @@
//int N = plist->size;
char **paths = (char **)list_to_array(plist);
+ int init_w = net.w;
+ int init_h = net.h;
+
load_args args = {0};
args.w = net.w;
args.h = net.h;
@@ -66,7 +84,7 @@
args.num_boxes = l.max_boxes;
args.d = &buffer;
args.type = DETECTION_DATA;
- args.threads = 4;
+ args.threads = 8;
args.angle = net.angle;
args.exposure = net.exposure;
@@ -78,9 +96,11 @@
int count = 0;
//while(i*imgs < N*120){
while(get_current_batch(net) < net.max_batches){
- if(l.random && count++%10 == 0){
+ if(l.random && count++%10 == 0){
printf("Resizing\n");
- int dim = (rand() % 10 + 10) * 32;
+ int dim = (rand() % 12 + (init_w/32 - 5)) * 32; // +-160
+ //int dim = (rand() % 10 + 10) * 32;
+ //if (get_current_batch(net)+100 > net.max_batches) dim = 544;
//int dim = (rand() % 4 + 16) * 32;
printf("%d\n", dim);
args.w = dim;
@@ -136,14 +156,15 @@
i = get_current_batch(net);
printf("%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);
- if(i%1000==0 || (i < 1000 && i%100 == 0)){
+ //if (i % 1000 == 0 || (i < 1000 && i % 100 == 0)) {
+ if (i % 100 == 0) {
#ifdef GPU
- if(ngpus != 1) sync_nets(nets, ngpus, 0);
+ if (ngpus != 1) sync_nets(nets, ngpus, 0);
#endif
- char buff[256];
- sprintf(buff, "%s/%s_%d.weights", backup_directory, base, i);
- save_weights(net, buff);
- }
+ char buff[256];
+ sprintf(buff, "%s/%s_%d.weights", backup_directory, base, i);
+ save_weights(net, buff);
+ }
free_data(train);
}
#ifdef GPU
@@ -208,7 +229,7 @@
}
}
-void print_imagenet_detections(FILE *fp, int id, box *boxes, float **probs, int total, int classes, int w, int h, int *map)
+void print_imagenet_detections(FILE *fp, int id, box *boxes, float **probs, int total, int classes, int w, int h)
{
int i, j;
for(i = 0; i < total; ++i){
@@ -224,7 +245,6 @@
for(j = 0; j < classes; ++j){
int class = j;
- if (map) class = map[j];
if (probs[i][class]) fprintf(fp, "%d %d %f %f %f %f %f\n", id, j+1, probs[i][class],
xmin, ymin, xmax, ymax);
}
@@ -233,6 +253,7 @@
void validate_detector(char *datacfg, char *cfgfile, char *weightfile)
{
+ int j;
list *options = read_data_cfg(datacfg);
char *valid_images = option_find_str(options, "valid", "data/train.list");
char *name_list = option_find_str(options, "names", "data/names.list");
@@ -242,24 +263,7 @@
int *map = 0;
if (mapf) map = read_map(mapf);
-
- char buff[1024];
- char *type = option_find_str(options, "eval", "voc");
- FILE *fp = 0;
- int coco = 0;
- int imagenet = 0;
- if(0==strcmp(type, "coco")){
- snprintf(buff, 1024, "%s/coco_results.json", prefix);
- fp = fopen(buff, "w");
- fprintf(fp, "[\n");
- coco = 1;
- } else if(0==strcmp(type, "imagenet")){
- snprintf(buff, 1024, "%s/imagenet-detection.txt", prefix);
- fp = fopen(buff, "w");
- imagenet = 1;
- }
-
- network net = parse_network_cfg(cfgfile);
+ network net = parse_network_cfg_custom(cfgfile, 1);
if(weightfile){
load_weights(&net, weightfile);
}
@@ -274,12 +278,31 @@
layer l = net.layers[net.n-1];
int classes = l.classes;
- int j;
- FILE **fps = calloc(classes, sizeof(FILE *));
- for(j = 0; j < classes; ++j){
- snprintf(buff, 1024, "%s/%s%s.txt", prefix, base, names[j]);
- fps[j] = fopen(buff, "w");
+ char buff[1024];
+ char *type = option_find_str(options, "eval", "voc");
+ FILE *fp = 0;
+ FILE **fps = 0;
+ int coco = 0;
+ int imagenet = 0;
+ if(0==strcmp(type, "coco")){
+ snprintf(buff, 1024, "%s/coco_results.json", prefix);
+ fp = fopen(buff, "w");
+ fprintf(fp, "[\n");
+ coco = 1;
+ } else if(0==strcmp(type, "imagenet")){
+ snprintf(buff, 1024, "%s/imagenet-detection.txt", prefix);
+ fp = fopen(buff, "w");
+ imagenet = 1;
+ classes = 200;
+ } else {
+ fps = calloc(classes, sizeof(FILE *));
+ for(j = 0; j < classes; ++j){
+ snprintf(buff, 1024, "%s/%s%s.txt", prefix, base, names[j]);
+ fps[j] = fopen(buff, "w");
+ }
}
+
+
box *boxes = calloc(l.w*l.h*l.n, sizeof(box));
float **probs = calloc(l.w*l.h*l.n, sizeof(float *));
for(j = 0; j < l.w*l.h*l.n; ++j) probs[j] = calloc(classes, sizeof(float *));
@@ -330,12 +353,12 @@
network_predict(net, X);
int w = val[t].w;
int h = val[t].h;
- get_region_boxes(l, w, h, thresh, probs, boxes, 0);
+ get_region_boxes(l, w, h, thresh, probs, boxes, 0, map);
if (nms) do_nms_sort(boxes, probs, l.w*l.h*l.n, classes, nms);
if (coco){
print_cocos(fp, path, boxes, probs, l.w*l.h*l.n, classes, w, h);
} else if (imagenet){
- print_imagenet_detections(fp, i+t-nthreads+1 + 9741, boxes, probs, l.w*l.h*l.n, 200, w, h, map);
+ print_imagenet_detections(fp, i+t-nthreads+1, boxes, probs, l.w*l.h*l.n, classes, w, h);
} else {
print_detector_detections(fps, id, boxes, probs, l.w*l.h*l.n, classes, w, h);
}
@@ -345,7 +368,7 @@
}
}
for(j = 0; j < classes; ++j){
- fclose(fps[j]);
+ if(fps) fclose(fps[j]);
}
if(coco){
fseek(fp, -2, SEEK_CUR);
@@ -355,9 +378,9 @@
fprintf(stderr, "Total Detection Time: %f Seconds\n", (double)(time(0) - start));
}
-void validate_detector_recall(char *cfgfile, char *weightfile)
+void validate_detector_recall(char *datacfg, char *cfgfile, char *weightfile)
{
- network net = parse_network_cfg(cfgfile);
+ network net = parse_network_cfg_custom(cfgfile, 1);
if(weightfile){
load_weights(&net, weightfile);
}
@@ -365,7 +388,9 @@
fprintf(stderr, "Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
srand(time(0));
- list *plist = get_paths("data/voc.2007.test");
+ list *options = read_data_cfg(datacfg);
+ char *valid_images = option_find_str(options, "valid", "data/train.txt");
+ list *plist = get_paths(valid_images);
char **paths = (char **)list_to_array(plist);
layer l = net.layers[net.n-1];
@@ -379,7 +404,7 @@
int m = plist->size;
int i=0;
- float thresh = .001;
+ float thresh = .001;// .001; // .2;
float iou_thresh = .5;
float nms = .4;
@@ -394,7 +419,7 @@
image sized = resize_image(orig, net.w, net.h);
char *id = basecfg(path);
network_predict(net, sized.data);
- get_region_boxes(l, 1, 1, thresh, probs, boxes, 1);
+ get_region_boxes(l, 1, 1, thresh, probs, boxes, 1, 0);
if (nms) do_nms(boxes, probs, l.w*l.h*l.n, 1, nms);
char labelpath[4096];
@@ -402,6 +427,7 @@
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);
@@ -410,16 +436,16 @@
++proposals;
}
}
- for (j = 0; j < num_labels; ++j) {
- ++total;
- box t = {truth[j].x, truth[j].y, truth[j].w, truth[j].h};
- float best_iou = 0;
- for(k = 0; k < l.w*l.h*l.n; ++k){
- float iou = box_iou(boxes[k], t);
- if(probs[k][0] > thresh && iou > best_iou){
- best_iou = iou;
- }
- }
+ for (j = 0; j < num_labels; ++j) {
+ ++total;
+ box t = { truth[j].x, truth[j].y, truth[j].w, truth[j].h };
+ float best_iou = 0;
+ for (k = 0; k < l.w*l.h*l.n; ++k) {
+ float iou = box_iou(boxes[k], t);
+ if (probs[k][0] > thresh && iou > best_iou) {
+ best_iou = iou;
+ }
+ }
avg_iou += best_iou;
if(best_iou > iou_thresh){
++correct;
@@ -440,11 +466,10 @@
char **names = get_labels(name_list);
image **alphabet = load_alphabet();
- network net = parse_network_cfg(cfgfile);
+ network net = parse_network_cfg_custom(cfgfile, 1);
if(weightfile){
load_weights(&net, weightfile);
}
- layer l = net.layers[net.n-1];
set_batch_network(&net, 1);
srand(2222222);
clock_t time;
@@ -452,12 +477,10 @@
char *input = buff;
int j;
float nms=.4;
- box *boxes = calloc(l.w*l.h*l.n, sizeof(box));
- float **probs = calloc(l.w*l.h*l.n, sizeof(float *));
- for(j = 0; j < l.w*l.h*l.n; ++j) probs[j] = calloc(l.classes, sizeof(float *));
while(1){
if(filename){
strncpy(input, filename, 256);
+ if (input[strlen(input) - 1] == 0x0d) input[strlen(input) - 1] = 0;
} else {
printf("Enter Image Path: ");
fflush(stdout);
@@ -467,11 +490,17 @@
}
image im = load_image_color(input,0,0);
image sized = resize_image(im, net.w, net.h);
+ layer l = net.layers[net.n-1];
+
+ box *boxes = calloc(l.w*l.h*l.n, sizeof(box));
+ float **probs = calloc(l.w*l.h*l.n, sizeof(float *));
+ for(j = 0; j < l.w*l.h*l.n; ++j) probs[j] = calloc(l.classes, sizeof(float *));
+
float *X = sized.data;
time=clock();
network_predict(net, X);
printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
- get_region_boxes(l, 1, 1, thresh, probs, boxes, 0);
+ 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);
draw_detections(im, l.w*l.h*l.n, thresh, boxes, probs, names, alphabet, l.classes);
save_image(im, "predictions");
@@ -479,6 +508,8 @@
free_image(im);
free_image(sized);
+ free(boxes);
+ free_ptrs((void **)probs, l.w*l.h*l.n);
#ifdef OPENCV
cvWaitKey(0);
cvDestroyAllWindows();
@@ -489,8 +520,9 @@
void run_detector(int argc, char **argv)
{
+ 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", .2);
+ 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);
if(argc < 4){
@@ -525,16 +557,20 @@
char *datacfg = argv[3];
char *cfg = argv[4];
char *weights = (argc > 5) ? argv[5] : 0;
+ 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);
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(cfg, weights);
+ else if(0==strcmp(argv[2], "recall")) validate_detector_recall(datacfg, cfg, weights);
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);
- demo(cfg, weights, thresh, cam_index, filename, names, classes, frame_skip, prefix);
+ 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);
}
}
--
Gitblit v1.10.0