1、detector.c
#include "network.h"
#include "region_layer.h"
#include "cost_layer.h"
#include "utils.h"
#include "parser.h"
#include "box.h"
#include "demo.h"
#include "option_list.h"
#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"
#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
IplImage* draw_train_chart(float max_img_loss, int max_batches, int number_of_lines, int img_size);
void draw_train_loss(IplImage* img, int img_size, float avg_loss, float max_img_loss, int current_batch, int max_batches);
#endif // OPENCV
#include "http_stream.h"
int check_mistakes;
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, int dont_show)
{
list *options = read_data_cfg(datacfg);
char *train_images = option_find_str(options, "train", "data/train.list");
char *backup_directory = option_find_str(options, "backup", "/backup/");
srand(time(0));
char *base = basecfg(cfgfile);
printf("%s\n", base);
float avg_loss = -1;
network *nets = calloc(ngpus, sizeof(network));
srand(time(0));
int seed = rand();
int i;
for(i = 0; i < ngpus; ++i){
srand(seed);
#ifdef GPU
cuda_set_device(gpus[i]);
#endif
nets[i] = parse_network_cfg(cfgfile);
if(weightfile){
load_weights(&nets[i], weightfile);
}
if(clear) *nets[i].seen = 0;
nets[i].learning_rate *= ngpus;
}
srand(time(0));
network net = nets[0];
const int actual_batch_size = net.batch * net.subdivisions;
if (actual_batch_size == 1) {
printf("\n Error: You set incorrect value batch=1 for Training! You should set batch=64 subdivision=64 \n");
getchar();
}
else if (actual_batch_size < 64) {
printf("\n Warning: You set batch=%d lower than 64! It is recommended to set batch=64 subdivision=64 \n", actual_batch_size);
}
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;
layer l = net.layers[net.n - 1];
int classes = l.classes;
float jitter = l.jitter;
list *plist = get_paths(train_images);
//int N = plist->size;
char **paths = (char **)list_to_array(plist);
int init_w = net.w;
int init_h = net.h;
int iter_save;
iter_save = get_current_batch(net);
load_args args = {0};
args.w = net.w;
args.h = net.h;
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 = 16; // 64
args.angle = net.angle;
args.exposure = net.exposure;
args.saturation = net.saturation;
args.hue = net.hue;
#ifdef OPENCV
args.threads = 3 * ngpus;
IplImage* img = NULL;
float max_img_loss = 5;
int number_of_lines = 100;
int img_size = 1000;
if (!dont_show)
img = draw_train_chart(max_img_loss, net.max_batches, number_of_lines, img_size);
#endif //OPENCV
pthread_t load_thread = load_data(args);
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
//int dim = (rand() % 4 + 16) * 32;
//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;
free_data(train);
load_thread = load_data(args);
for(i = 0; i < ngpus; ++i){
resize_network(nets + i, dim_w, dim_h);
}
net = nets[0];
}
time=what_time_is_it_now();
pthread_join(load_thread, 0);
train = buffer;
load_thread = load_data(args);
/*
int k;
for(k = 0; k < l.max_boxes; ++k){
box b = float_to_box(train.y.vals[10] + 1 + k*5);
if(!b.x) break;
printf("loaded: %f %f %f %f\n", b.x, b.y, b.w, b.h);
}
image im = float_to_image(448, 448, 3, train.X.vals[10]);
int k;
for(k = 0; k < l.max_boxes; ++k){
box b = float_to_box(train.y.vals[10] + 1 + k*5);
printf("%d %d %d %d\n", truth.x, truth.y, truth.w, truth.h);
draw_bbox(im, b, 8, 1,0,0);
}
save_image(im, "truth11");
*/
printf("Loaded: %lf seconds\n", (what_time_is_it_now()-time));
time=what_time_is_it_now();
float loss = 0;
#ifdef GPU
if(ngpus == 1){
loss = train_network(net, train);
} else {
loss = train_networks(nets, ngpus, train, 4);
}
#else
loss = train_network(net, train);
#endif
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 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)
draw_train_loss(img, img_size, avg_loss, max_img_loss, i, net.max_batches);
#endif // OPENCV
//if (i % 1000 == 0 || (i < 1000 && i % 100 == 0)) {
//if (i % 100 == 0) {
if(i >= (iter_save + 100)) {
iter_save = i;
#ifdef GPU
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);
}
free_data(train);
}
#ifdef GPU
if(ngpus != 1) sync_nets(nets, ngpus, 0);
#endif
char buff[256];
sprintf(buff, "%s/%s_final.weights", backup_directory, base);
save_weights(net, buff);
#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);
}
static int get_coco_image_id(char *filename)
{
char *p = strrchr(filename, '/');
char *c = strrchr(filename, '_');
if (c) p = c;
return atoi(p + 1);
}
static void print_cocos(FILE *fp, char *image_path, detection *dets, int num_boxes, int classes, int w, int h)
{
int i, j;
int image_id = get_coco_image_id(image_path);
for (i = 0; i < num_boxes; ++i) {
float xmin = dets[i].bbox.x - dets[i].bbox.w / 2.;
float xmax = dets[i].bbox.x + dets[i].bbox.w / 2.;
float ymin = dets[i].bbox.y - dets[i].bbox.h / 2.;
float ymax = dets[i].bbox.y + dets[i].bbox.h / 2.;
if (xmin < 0) xmin = 0;
if (ymin < 0) ymin = 0;
if (xmax > w) xmax = w;
if (ymax > h) ymax = h;
float bx = xmin;
float by = ymin;
float bw = xmax - xmin;
float bh = ymax - ymin;
for (j = 0; j < classes; ++j) {
if (dets[i].prob[j]) fprintf(fp, "{\"image_id\":%d, \"category_id\":%d, \"bbox\":[%f, %f, %f, %f], \"score\":%f},\n", image_id, coco_ids[j], bx, by, bw, bh, dets[i].prob[j]);
}
}
}
void print_detector_detections(FILE **fps, char *id, detection *dets, int total, int classes, int w, int h)
{
int i, j;
for (i = 0; i < total; ++i) {
float xmin = dets[i].bbox.x - dets[i].bbox.w / 2. + 1;
float xmax = dets[i].bbox.x + dets[i].bbox.w / 2. + 1;
float ymin = dets[i].bbox.y - dets[i].bbox.h / 2. + 1;
float ymax = dets[i].bbox.y + dets[i].bbox.h / 2. + 1;
if (xmin < 1) xmin = 1;
if (ymin < 1) ymin = 1;
if (xmax > w) xmax = w;
if (ymax > h) ymax = h;
for (j = 0; j < classes; ++j) {
if (dets[i].prob[j]) fprintf(fps[j], "%s %f %f %f %f %f\n", id, dets[i].prob[j],
xmin, ymin, xmax, ymax);
}
}
}
void print_imagenet_detections(FILE *fp, int id, detection *dets, int total, int classes, int w, int h)
{
int i, j;
for (i = 0; i < total; ++i) {
float xmin = dets[i].bbox.x - dets[i].bbox.w / 2.;
float xmax = dets[i].bbox.x + dets[i].bbox.w / 2.;
float ymin = dets[i].bbox.y - dets[i].bbox.h / 2.;
float ymax = dets[i].bbox.y + dets[i].bbox.h / 2.;
if (xmin < 0) xmin = 0;
if (ymin < 0) ymin = 0;
if (xmax > w) xmax = w;
if (ymax > h) ymax = h;
for (j = 0; j < classes; ++j) {
int class = j;
if (dets[i].prob[class]) fprintf(fp, "%d %d %f %f %f %f %f\n", id, j + 1, dets[i].prob[class],
xmin, ymin, xmax, ymax);
}
}
}
void validate_detector(char *datacfg, char *cfgfile, char *weightfile, char *outfile)
{
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");
char *prefix = option_find_str(options, "results", "results");
char **names = get_labels(name_list);
char *mapf = option_find_str(options, "map", 0);
int *map = 0;
if (mapf) map = read_map(mapf);
network net = parse_network_cfg_custom(cfgfile, 1); // set batch=1
if (weightfile) {
load_weights(&net, weightfile);
}
//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));
list *plist = get_paths(valid_images);
char **paths = (char **)list_to_array(plist);
layer l = net.layers[net.n - 1];
int classes = l.classes;
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")) {
if (!outfile) outfile = "coco_results";
snprintf(buff, 1024, "%s/%s.json", prefix, outfile);
fp = fopen(buff, "w");
fprintf(fp, "[\n");
coco = 1;
}
else if (0 == strcmp(type, "imagenet")) {
if (!outfile) outfile = "imagenet-detection";
snprintf(buff, 1024, "%s/%s.txt", prefix, outfile);
fp = fopen(buff, "w");
imagenet = 1;
classes = 200;
}
else {
if (!outfile) outfile = "comp4_det_test_";
fps = calloc(classes, sizeof(FILE *));
for (j = 0; j < classes; ++j) {
snprintf(buff, 1024, "%s/%s%s.txt", prefix, outfile, names[j]);
fps[j] = fopen(buff, "w");
}
}
int m = plist->size;
int i = 0;
int t;
float thresh = .005;
float nms = .45;
int nthreads = 4;
image *val = calloc(nthreads, sizeof(image));
image *val_resized = calloc(nthreads, sizeof(image));
image *buf = calloc(nthreads, sizeof(image));
image *buf_resized = calloc(nthreads, sizeof(image));
pthread_t *thr = calloc(nthreads, sizeof(pthread_t));
load_args args = { 0 };
args.w = net.w;
args.h = net.h;
args.c = net.c;
args.type = IMAGE_DATA;
//args.type = LETTERBOX_DATA;
for (t = 0; t < nthreads; ++t) {
args.path = paths[i + t];
args.im = &buf[t];
args.resized = &buf_resized[t];
thr[t] = load_data_in_thread(args);
}
time_t start = time(0);
for (i = nthreads; i < m + nthreads; i += nthreads) {
fprintf(stderr, "%d\n", i);
for (t = 0; t < nthreads && i + t - nthreads < m; ++t) {
pthread_join(thr[t], 0);
val[t] = buf[t];
val_resized[t] = buf_resized[t];
}
for (t = 0; t < nthreads && i + t < m; ++t) {
args.path = paths[i + t];
args.im = &buf[t];
args.resized = &buf_resized[t];
thr[t] = load_data_in_thread(args);
}
for (t = 0; t < nthreads && i + t - nthreads < m; ++t) {
char *path = paths[i + t - nthreads];
char *id = basecfg(path);
float *X = val_resized[t].data;
network_predict(net, X);
int w = val[t].w;
int h = val[t].h;
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(dets, nboxes, classes, nms);
if (coco) {
print_cocos(fp, path, dets, nboxes, classes, w, h);
}
else if (imagenet) {
print_imagenet_detections(fp, i + t - nthreads + 1, dets, nboxes, classes, w, h);
}
else {
print_detector_detections(fps, id, dets, nboxes, classes, w, h);
}
free_detections(dets, nboxes);
free(id);
free_image(val[t]);
free_image(val_resized[t]);
}
}
for (j = 0; j < classes; ++j) {
if (fps) fclose(fps[j]);
}
if (coco) {
fseek(fp, -2, SEEK_CUR);
fprintf(fp, "\n]\n");
fclose(fp);
}
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); // set batch=1
if (weightfile) {
load_weights(&net, weightfile);
}
//set_batch_network(&net, 1);
fuse_conv_batchnorm(net);
srand(time(0));
//list *plist = get_paths("data/coco_val_5k.list");
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];
int j, k;
int m = plist->size;
int i = 0;
float thresh = .001;
float iou_thresh = .5;
float nms = .4;
int total = 0;
int correct = 0;
int proposals = 0;
float avg_iou = 0;
for (i = 0; i < m; ++i) {
char *path = paths[i];
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(dets, nboxes, 1, nms);
char labelpath[4096];
replace_image_to_label(path, labelpath);
int num_labels = 0;
box_label *truth = read_boxes(labelpath, &num_labels);
for (k = 0; k < nboxes; ++k) {
if (dets[k].objectness > thresh) {
++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 < nboxes; ++k) {
float iou = box_iou(dets[k].bbox, t);
if (dets[k].objectness > thresh && iou > best_iou) {
best_iou = iou;
}
}
avg_iou += best_iou;
if (best_iou > iou_thresh) {
++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);
free_image(sized);
}
}
typedef struct {
box b;
float p;
int class_id;
int image_index;
int truth_flag;
int unique_truth_index;
} box_prob;
int detections_comparator(const void *pa, const void *pb)
{
box_prob a = *(box_prob *)pa;
box_prob b = *(box_prob *)pb;
float diff = a.p - b.p;
if (diff < 0) return 1;
else if (diff > 0) return -1;
return 0;
}
void validate_detector_map(char *datacfg, char *cfgfile, char *weightfile, float thresh_calc_avg_iou)
{
int j;
list *options = read_data_cfg(datacfg);
char *valid_images = option_find_str(options, "valid", "data/train.txt");
char *difficult_valid_images = option_find_str(options, "difficult", NULL);
char *name_list = option_find_str(options, "names", "data/names.list");
char **names = get_labels(name_list);
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) {
load_weights(&net, weightfile);
}
//set_batch_network(&net, 1);
fuse_conv_batchnorm(net);
calculate_binary_weights(net);
srand(time(0));
list *plist = get_paths(valid_images);
char **paths = (char **)list_to_array(plist);
char **paths_dif = NULL;
if (difficult_valid_images) {
list *plist_dif = get_paths(difficult_valid_images);
paths_dif = (char **)list_to_array(plist_dif);
}
layer l = net.layers[net.n - 1];
int classes = l.classes;
int m = plist->size;
int i = 0;
int t;
const float thresh = .005;
const float nms = .45;
const float iou_thresh = 0.5;
int nthreads = 4;
image *val = calloc(nthreads, sizeof(image));
image *val_resized = calloc(nthreads, sizeof(image));
image *buf = calloc(nthreads, sizeof(image));
image *buf_resized = calloc(nthreads, sizeof(image));
pthread_t *thr = calloc(nthreads, sizeof(pthread_t));
load_args args = { 0 };
args.w = net.w;
args.h = net.h;
args.c = net.c;
args.type = IMAGE_DATA;
//args.type = LETTERBOX_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_count = 0;
int *truth_classes_count = calloc(classes, sizeof(int));
for (t = 0; t < nthreads; ++t) {
args.path = paths[i + t];
args.im = &buf[t];
args.resized = &buf_resized[t];
thr[t] = load_data_in_thread(args);
}
time_t start = time(0);
for (i = nthreads; i < m + nthreads; i += nthreads) {
fprintf(stderr, "%d\n", i);
for (t = 0; t < nthreads && i + t - nthreads < m; ++t) {
pthread_join(thr[t], 0);
val[t] = buf[t];
val_resized[t] = buf_resized[t];
}
for (t = 0; t < nthreads && i + t < m; ++t) {
args.path = paths[i + t];
args.im = &buf[t];
args.resized = &buf_resized[t];
thr[t] = load_data_in_thread(args);
}
for (t = 0; t < nthreads && i + t - nthreads < m; ++t) {
const int image_index = i + t - nthreads;
char *path = paths[image_index];
char *id = basecfg(path);
float *X = val_resized[t].data;
network_predict(net, X);
int nboxes = 0;
float hier_thresh = 0;
detection *dets;
if (args.type == LETTERBOX_DATA) {
int letterbox = 1;
dets = get_network_boxes(&net, val[t].w, val[t].h, thresh, hier_thresh, 0, 1, &nboxes, letterbox);
}
else {
int letterbox = 0;
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];
replace_image_to_label(path, labelpath);
int num_labels = 0;
box_label *truth = read_boxes(labelpath, &num_labels);
int i, j;
for (j = 0; j < num_labels; ++j) {
truth_classes_count[truth[j].id]++;
}
// difficult
box_label *truth_dif = NULL;
int num_labels_dif = 0;
if (paths_dif)
{
char *path_dif = paths_dif[image_index];
char labelpath_dif[4096];
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;
for (class_id = 0; class_id < classes; ++class_id) {
float prob = dets[i].prob[class_id];
if (prob > 0) {
detections_count++;
detections = realloc(detections, detections_count * sizeof(box_prob));
detections[detections_count - 1].b = dets[i].bbox;
detections[detections_count - 1].p = prob;
detections[detections_count - 1].image_index = image_index;
detections[detections_count - 1].class_id = class_id;
detections[detections_count - 1].truth_flag = 0;
detections[detections_count - 1].unique_truth_index = -1;
int truth_index = -1;
float max_iou = 0;
for (j = 0; j < num_labels; ++j)
{
box t = { truth[j].x, truth[j].y, truth[j].w, truth[j].h };
//printf(" IoU = %f, prob = %f, class_id = %d, truth[j].id = %d \n",
// box_iou(dets[i].bbox, t), prob, class_id, truth[j].id);
float current_iou = box_iou(dets[i].bbox, t);
if (current_iou > iou_thresh && class_id == truth[j].id) {
if (current_iou > max_iou) {
max_iou = current_iou;
truth_index = unique_truth_count + j;
}
}
}
// best IoU
if (truth_index > -1) {
detections[detections_count - 1].truth_flag = 1;
detections[detections_count - 1].unique_truth_index = truth_index;
}
else {
// if object is difficult then remove detection
for (j = 0; j < num_labels_dif; ++j) {
box t = { truth_dif[j].x, truth_dif[j].y, truth_dif[j].w, truth_dif[j].h };
float current_iou = box_iou(dets[i].bbox, t);
if (current_iou > iou_thresh && class_id == truth_dif[j].id) {
--detections_count;
break;
}
}
}
// calc avg Io