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 IoU, true-positives, false-positives for required Threshold
                        if (prob > thresh_calc_avg_iou) {
                            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;
                            }
                            else
                                fp_for_thresh++;
                        }
                    }
                }
            }

            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]);
            free_image(val_resized[t]);
        }
    }

    if((tp_for_thresh + fp_for_thresh) > 0)
        avg_iou = avg_iou / (tp_for_thresh + fp_for_thresh);


    // SORT(detections)
    qsort(detections, detections_count, sizeof(box_prob), detections_comparator);

    typedef struct {
        double precision;
        double recall;
        int tp, fp, fn;
    } pr_t;

    // for PR-curve
    pr_t **pr = calloc(classes, sizeof(pr_t*));
    for (i = 0; i < classes; ++i) {
        pr[i] = calloc(detections_count, sizeof(pr_t));
    }
    printf("detections_count = %d, unique_truth_count = %d  \n", detections_count, unique_truth_count);


    int *truth_flags = calloc(unique_truth_count, sizeof(int));

    int rank;
    for (rank = 0; rank < detections_count; ++rank) {
        if(rank % 100 == 0)
            printf(" rank = %d of ranks = %d \r", rank, detections_count);

        if (rank > 0) {
            int class_id;
            for (class_id = 0; class_id < classes; ++class_id) {
                pr[class_id][rank].tp = pr[class_id][rank - 1].tp;
                pr[class_id][rank].fp = pr[class_id][rank - 1].fp;
            }
        }

        box_prob d = detections[rank];
        // if (detected && isn't detected before)
        if (d.truth_flag == 1) {
            if (truth_flags[d.unique_truth_index] == 0)
            {
                truth_flags[d.unique_truth_index] = 1;
                pr[d.class_id][rank].tp++;    // true-positive
            }
        }
        else {
            pr[d.class_id][rank].fp++;    // false-positive
        }

        for (i = 0; i < classes; ++i)
        {
            const int tp = pr[i][rank].tp;
            const int fp = pr[i][rank].fp;
            const int fn = truth_classes_count[i] - tp;    // false-negative = objects - true-positive
            pr[i][rank].fn = fn;

            if ((tp + fp) > 0) pr[i][rank].precision = (double)tp / (double)(tp + fp);
            else pr[i][rank].precision = 0;

            if ((tp + fn) > 0) pr[i][rank].recall = (double)tp / (double)(tp + fn);
            else pr[i][rank].recall = 0;
        }
    }

    free(truth_flags);


    double mean_average_precision = 0;

    for (i = 0; i < classes; ++i) {
        double avg_precision = 0;
        int point;
        for (point = 0; point < 11; ++point) {
            double cur_recall = point * 0.1;
            double cur_precision = 0;
            for (rank = 0; rank < detections_count; ++rank)
            {
                if (pr[i][rank].recall >= cur_recall) {    // > or >=
                    if (pr[i][rank].precision > cur_precision) {
                        cur_precision = pr[i][rank].precision;
                    }
                }
            }
            //printf("class_id = %d, point = %d, cur_recall = %.4f, cur_precision = %.4f \n", i, point, cur_recall, cur_precision);

            avg_precision += cur_precision;
        }
        avg_precision = avg_precision / 11;
        printf("class_id = %d, name = %s, \t ap = %2.2f %% \n", i, names[i], avg_precision*100);
        mean_average_precision += avg_precision;
    }

    const float cur_precision = (float)tp_for_thresh / ((float)tp_for_thresh + (float)fp_for_thresh);
    const float cur_recall = (float)tp_for_thresh / ((float)tp_for_thresh + (float)(unique_truth_count - tp_for_thresh));
    const float f1_score = 2.F * cur_precision * cur_recall / (cur_precision + cur_recall);
    printf(" for thresh = %1.2f, precision = %1.2f, recall = %1.2f, F1-score = %1.2f \n",
        thresh_calc_avg_iou, cur_precision, cur_recall, f1_score);

    printf(" for thresh = %0.2f, TP = %d, FP = %d, FN = %d, average IoU = %2.2f %% \n",
        thresh_calc_avg_iou, tp_for_thresh, fp_for_thresh, unique_truth_count - tp_for_thresh, avg_iou * 100);

    mean_average_precision = mean_average_precision / classes;
    printf("\n mean average precision (mAP) = %f, or %2.2f %% \n", mean_average_precision, mean_average_precision*100);


    for (i = 0; i < classes; ++i) {
        free(pr[i]);
    }
    free(pr);
    free(detections);
    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
typedef struct {
    float w, h;
} anchors_t;

int anchors_comparator(const void *pa, const void *pb)
{
    anchors_t a = *(anchors_t *)pa;
    anchors_t b = *(anchors_t *)pb;
    float diff = b.w*b.h - a.w*a.h;
    if (diff < 0) return 1;
    else if (diff > 0) return -1;
    return 0;
}

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));

    list *options = read_data_cfg(datacfg);
    char *train_images = option_find_str(options, "train", "data/train.list");
    list *plist = get_paths(train_images);
    int number_of_images = plist->size;
    char **paths = (char **)list_to_array(plist);

    int number_of_boxes = 0;
    printf(" read labels from %d images \n", number_of_images);

    int i, j;
    for (i = 0; i < number_of_images; ++i) {
        char *path = paths[i];
        char labelpath[4096];
        replace_image_to_label(path, labelpath);

        int num_labels = 0;
        box_label *truth = read_boxes(labelpath, &num_labels);
        //printf(" new path: %s \n", labelpath);
        char buff[1024];
        for (j = 0; j < num_labels; ++j)
        {
            if (truth[j].x > 1 || truth[j].x <= 0 || truth[j].y > 1 || truth[j].y <= 0 ||
                truth[j].w > 1 || truth[j].w <= 0 || truth[j].h > 1 || truth[j].h <= 0)
            {
                printf("\n\nWrong label: %s - j = %d, x = %f, y = %f, width = %f, height = %f \n",
                    labelpath, j, truth[j].x, truth[j].y, truth[j].w, truth[j].h);
                sprintf(buff, "echo \"Wrong label: %s - j = %d, x = %f, y = %f, width = %f, height = %f\" >> bad_label.list",
                    labelpath, j, truth[j].x, truth[j].y, truth[j].w, truth[j].h);
                system(buff);
                if (check_mistakes) getchar();
            }
            number_of_boxes++;
            rel_width_height_array = realloc(rel_width_height_array, 2 * number_of_boxes * sizeof(float));
            rel_width_height_array[number_of_boxes * 2 - 2] = truth[j].w * width;
            rel_width_height_array[number_of_boxes * 2 - 1] = truth[j].h * height;
            printf("\r loaded \t image: %d \t box: %d", i+1, number_of_boxes);
        }
    }
    printf("\n all loaded. \n");

    CvMat* points = cvCreateMat(number_of_boxes, 2, CV_32FC1);
    CvMat* centers = cvCreateMat(num_of_clusters, 2, CV_32FC1);
    CvMat* labels = cvCreateMat(number_of_boxes, 1, CV_32SC1);

    for (i = 0; i < number_of_boxes; ++i) {
        points->data.fl[i * 2] = rel_width_height_array[i * 2];
        points->data.fl[i * 2 + 1] = rel_width_height_array[i * 2 + 1];
        //cvSet1D(points, i * 2, cvScalar(rel_width_height_array[i * 2], 0, 0, 0));
        //cvSet1D(points, i * 2 + 1, cvScalar(rel_width_height_array[i * 2 + 1], 0, 0, 0));
    }


    const int attemps = 10;
    double compactness;

    enum {
        KMEANS_RANDOM_CENTERS = 0,
        KMEANS_USE_INITIAL_LABELS = 1,
        KMEANS_PP_CENTERS = 2
    };

    printf("\n calculating k-means++ ...");
    // Should be used: distance(box, centroid) = 1 - IoU(box, centroid)
    cvKMeans2(points, num_of_clusters, labels,
        cvTermCriteria(CV_TERMCRIT_EPS+CV_TERMCRIT_ITER, 10000, 0), attemps,
        0, KMEANS_PP_CENTERS,
        centers, &compactness);

    // sort anchors
    qsort(centers->data.fl, num_of_clusters, 2*sizeof(float), anchors_comparator);

    //orig 2.0 anchors = 1.08,1.19,  3.42,4.41,  6.63,11.38,  9.42,5.11,  16.62,10.52
    //float orig_anch[] = { 1.08,1.19,  3.42,4.41,  6.63,11.38,  9.42,5.11,  16.62,10.52 };
    // worse than ours (even for 19x19 final size - for input size 608x608)

    //orig anchors = 1.3221,1.73145, 3.19275,4.00944, 5.05587,8.09892, 9.47112,4.84053, 11.2364,10.0071
    //float orig_anch[] = { 1.3221,1.73145, 3.19275,4.00944, 5.05587,8.09892, 9.47112,4.84053, 11.2364,10.0071 };
    // orig (IoU=59.90%) better than ours (59.75%)

    //gen_anchors.py = 1.19, 1.99, 2.79, 4.60, 4.53, 8.92, 8.06, 5.29, 10.32, 10.66
    //float orig_anch[] = { 1.19, 1.99, 2.79, 4.60, 4.53, 8.92, 8.06, 5.29, 10.32, 10.66 };

    // ours: anchors = 9.3813,6.0095, 3.3999,5.3505, 10.9476,11.1992, 5.0161,9.8314, 1.5003,2.1595
    //float orig_anch[] = { 9.3813,6.0095, 3.3999,5.3505, 10.9476,11.1992, 5.0161,9.8314, 1.5003,2.1595 };
    //for (i = 0; i < num_of_clusters * 2; ++i) centers->data.fl[i] = orig_anch[i];

    //for (i = 0; i < number_of_boxes; ++i)
    //    printf("%2.2f,%2.2f, ", points->data.fl[i * 2], points->data.fl[i * 2 + 1]);

    printf("\n");
    float avg_iou = 0;
    for (i = 0; i < number_of_boxes; ++i) {
        float box_w = points->data.fl[i * 2];
        float box_h = points->data.fl[i * 2 + 1];
        //int cluster_idx = labels->data.i[i];
        int cluster_idx = 0;
        float min_dist = FLT_MAX;
        for (j = 0; j < num_of_clusters; ++j) {
            float anchor_w = centers->data.fl[j * 2];
            float anchor_h = centers->data.fl[j * 2 + 1];
            float w_diff = anchor_w - box_w;
            float h_diff = anchor_h - box_h;
            float distance = sqrt(w_diff*w_diff + h_diff*h_diff);
            if (distance < min_dist) min_dist = distance, cluster_idx = j;
        }

        float anchor_w = centers->data.fl[cluster_idx * 2];
        float anchor_h = centers->data.fl[cluster_idx * 2 + 1];
        float min_w = (box_w < anchor_w) ? box_w : anchor_w;
        float min_h = (box_h < anchor_h) ? box_h : anchor_h;
        float box_intersect = min_w*min_h;
        float box_union = box_w*box_h + anchor_w*anchor_h - box_intersect;
        float iou = box_intersect / box_union;
        if (iou > 1 || iou < 0) { // || box_w > width || box_h > height) {
            printf(" Wrong label: i = %d, box_w = %d, box_h = %d, anchor_w = %d, anchor_h = %d, iou = %f \n",
                i, box_w, box_h, anchor_w, anchor_h, iou);
        }
        else avg_iou += iou;
    }
    avg_iou = 100 * avg_iou / number_of_boxes;
    printf("\n avg IoU = %2.2f %% \n", avg_iou);

    char buff[1024];
    FILE* fw = fopen("anchors.txt", "wb");
    if (fw) {
        printf("\nSaving anchors to the file: anchors.txt \n");
        printf("anchors = ");
        for (i = 0; i < num_of_clusters; ++i) {
            sprintf(buff, "%2.4f,%2.4f", centers->data.fl[i * 2], centers->data.fl[i * 2 + 1]);
            printf("%s", buff);
            fwrite(buff, sizeof(char), strlen(buff), fw);
            if (i + 1 < num_of_clusters) {
                fwrite(", ", sizeof(char), 2, fw);
                printf(", ");
            }
        }
        printf("\n");
        fclose(fw);
    }
    else {
        printf(" Error: file anchors.txt can't be open \n");
    }

    if (show) {
        size_t img_size = 700;
        IplImage* img = cvCreateImage(cvSize(img_size, img_size), 8, 3);
        cvZero(img);
        for (j = 0; j < num_of_clusters; ++j) {
            CvPoint pt1, pt2;
            pt1.x = pt1.y = 0;
            pt2.x = centers->data.fl[j * 2] * img_size / width;
            pt2.y = centers->data.fl[j * 2 + 1] * img_size / height;
            cvRectangle(img, pt1, pt2, CV_RGB(255, 255, 255), 1, 8, 0);
        }

        for (i = 0; i < number_of_boxes; ++i) {
            CvPoint pt;
            pt.x = points->data.fl[i * 2] * img_size / width;
            pt.y = points->data.fl[i * 2 + 1] * img_size / height;
            int cluster_idx = labels->data.i[i];
            int red_id = (cluster_idx * (uint64_t)123 + 55) % 255;
            int green_id = (cluster_idx * (uint64_t)321 + 33) % 255;
            int blue_id = (cluster_idx * (uint64_t)11 + 99) % 255;
            cvCircle(img, pt, 1, CV_RGB(red_id, green_id, blue_id), CV_FILLED, 8, 0);
            //if(pt.x > img_size || pt.y > img_size) printf("\n pt.x = %d, pt.y = %d \n", pt.x, pt.y);
        }
        cvShowImage("clusters", img);
        cvWaitKey(0);
        cvReleaseImage(&img);
        cvDestroyAllWindows();
    }

    free(rel_width_height_array);
    cvReleaseMat(&points);
    cvReleaseMat(&centers);
    cvReleaseMat(&labels);
}
#else
void calc_anchors(char *datacfg, int num_of_clusters, int width, int height, int show) {
    printf(" k-means++ can't be used without OpenCV, because there is used cvKMeans2 implementation \n");
}
#endif // OPENCV

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");
    int names_size = 0;
    char **names = get_labels_custom(name_list, &names_size); //get_labels(name_list);

    image **alphabet = load_alphabet();
    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);
    if (net.layers[net.n - 1].classes != names_size) {
        printf(" Error: in the file %s number of names %d that isn't equal to classes=%d in the file %s \n",
            name_list, names_size, net.layers[net.n - 1].classes, cfgfile);
        if(net.layers[net.n - 1].classes > names_size) getchar();
    }
    srand(2222222);
    double time;
    char buff[256];
    char *input = buff;
    int j;
    float nms=.45;    // 0.4F
    while(1){
        if(filename){
            strncpy(input, filename, 256);
            if(strlen(input) > 0)
                if (input[strlen(input) - 1] == 0x0d) input[strlen(input) - 1] = 0;
        } else {
            printf("****detector.c 1133****** Enter Image Path: ");					//dspeia
            fflush(stdout);
            input = fgets(input, 256, stdin);
            if(!input) return;
            strtok(input, "\n");
        }
        image im = load_image(input,0,0,net.c);
		printf("****detector.c 1140****** input: %c",input);					//dspeia

        int letterbox = 0;
        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));
        //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= what_time_is_it_now();
        double time = get_time_point();
        network_predict(net, X);
        //network_predict_image(&net, im); letterbox = 1;
		//圖片載入完成
        printf("%s: Predicted in %lf milli-seconds. **detecotr.c 1162 \n", input, ((double)get_time_point() - time) / 1000);  
        //printf("%s: Predicted in %f seconds.\n", input, (what_time_is_it_now()-time));

        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);
		printf("****  l.classes == %c ** \n", l.classes);  //test classes
		draw_detections_v3(im, dets, nboxes, thresh, names, alphabet, l.classes, ext_output);		//draw_detections_v3,不是image.c的draw_detections
         
		save_image(im, "pre-img//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);
        //free_ptrs((void **)probs, l.w*l.h*l.n);
#ifdef OPENCV
        if (!dont_show) {
            cvWaitKey(0);
            cvDestroyAllWindows();
        }
#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)
{	//輸入中有第四位引數的函式，要求cmd中跟上引數如："-out_filename result/out.mp4" 其他的不跟引數
    int dont_show = find_arg(argc, argv, "-dont_show");	//不展示視窗，find_arg()有匹配為1，無匹配則0
    int show = find_arg(argc, argv, "-show");
    check_mistakes = find_arg(argc, argv, "-check_mistakes");
    int http_stream_port = find_int_arg(argc, argv, "-http_port", -1);		//瀏覽器展示結果的埠號
    char *out_filename = find_char_arg(argc, argv, "-out_filename", 0);		//如：-out_filename out.mp4，有視訊檔案輸入才能有輸出，無法用攝像頭儲存輸出
    char *outfile = find_char_arg(argc, argv, "-out", 0);
    char *prefix = find_char_arg(argc, argv, "-prefix", 0);
    float thresh = find_float_arg(argc, argv, "-thresh", .25);    // 0.24	//單一閾值
    float hier_thresh = find_float_arg(argc, argv, "-hier", .5);	//多類別顯示閾值
    int cam_index = find_int_arg(argc, argv, "-c", 0);		//攝像頭選擇
    int frame_skip = find_int_arg(argc, argv, "-s", 0);		//在框中跳幀顯示
    int num_of_clusters = find_int_arg(argc, argv, "-num_of_clusters", 5);	//簇個數？
    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");		//輸出目標座標
    int save_labels = find_arg(argc, argv, "-save_labels");
    if(argc < 4){
        fprintf(stderr, "usage: %s %s [train/test/valid/demo/map] [data] [cfg] [weights (optional)]\n", argv[0], argv[1]);
        return;
    }
    char *gpu_list = find_char_arg(argc, argv, "-gpus", 0);		//選擇gpu
    int *gpus = 0;
    int gpu = 0;
    int ngpus = 0;
    if(gpu_list){
        printf("%s\n", gpu_list);
        int len = strlen(gpu_list);
        ngpus = 1;
        int i;
        for(i = 0; i < len; ++i){
            if (gpu_list[i] == ',') ++ngpus;
        }
        gpus = calloc(ngpus, sizeof(int));
        for(i = 0; i < ngpus; ++i){
            gpus[i] = atoi(gpu_list);
            gpu_list = strchr(gpu_list, ',')+1;
        }
    } else {
        gpu = gpu_index;
        gpus = &gpu;
        ngpus = 1;
    }

    int clear = find_arg(argc, argv, "-clear");

    char *datacfg = argv[3];
    char *cfg = argv[4];
    char *weights = (argc > 5) ? argv[5] : 0;
    if(weights)
        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, 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, height, show);
    else if(0==strcmp(argv[2], "demo")) {
        list *options = read_data_cfg(datacfg);
        int classes = option_find_int(options, "classes", 20);	//class可能是一幀最大類別數？？
        char *name_list = option_find_str(options, "names", "data/names.list");
        char **names = get_labels(name_list);
        if(filename)
            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, ext_output);

        free_list_contents_kvp(options);
        free_list(options);
    }
    else printf(" There isn't such command: %s", argv[2]);
}
 

image.c

#include "image.h"
#include "utils.h"
#include "blas.h"
#include "cuda.h"
#include <stdio.h>
#include <math.h>

#define STB_IMAGE_IMPLEMENTATION
#include "stb_image.h"
#define STB_IMAGE_WRITE_IMPLEMENTATION
#include "stb_image_write.h"


#ifdef OPENCV
#include "opencv2/highgui/highgui_c.h"
#include "opencv2/imgproc/imgproc_c.h"
#include "opencv2/core/types_c.h"
#include "opencv2/core/version.hpp"
#ifndef CV_VERSION_EPOCH
#include "opencv2/videoio/videoio_c.h"
#include "opencv2/imgcodecs/imgcodecs_c.h"
#include "http_stream.h"


#endif
#include "http_stream.h"
#endif

extern int check_mistakes;
int windows = 0;

float colors[6][3] = { {1,0,1}, {0,0,1},{0,1,1},{0,1,0},{1,1,0},{1,0,0} };

float get_color(int c, int x, int max)
{
    float ratio = ((float)x/max)*5;
    int i = floor(ratio);
    int j = ceil(ratio);
    ratio -= i;
    float r = (1-ratio) * colors[i][c] + ratio*colors[j][c];
    //printf("%f\n", r);
    return r;
}

static float get_pixel(image m, int x, int y, int c)
{
    assert(x < m.w && y < m.h && c < m.c);
    return m.data[c*m.h*m.w + y*m.w + x];
}
static float get_pixel_extend(image m, int x, int y, int c)
{
    if (x < 0 || x >= m.w || y < 0 || y >= m.h) return 0;
    /*
    if(x < 0) x = 0;
    if(x >= m.w) x = m.w-1;
    if(y < 0) y = 0;
    if(y >= m.h) y = m.h-1;
    */
    if (c < 0 || c >= m.c) return 0;
    return get_pixel(m, x, y, c);
}
static void set_pixel(image m, int x, int y, int c, float val)
{
    if (x < 0 || y < 0 || c < 0 || x >= m.w || y >= m.h || c >= m.c) return;
    assert(x < m.w && y < m.h && c < m.c);
    m.data[c*m.h*m.w + y*m.w + x] = val;
}
static void add_pixel(image m, int x, int y, int c, float val)
{
    assert(x < m.w && y < m.h && c < m.c);
    m.data[c*m.h*m.w + y*m.w + x] += val;
}

void composite_image(image source, image dest, int dx, int dy)
{
    int x,y,k;
    for(k = 0; k < source.c; ++k){
        for(y = 0; y < source.h; ++y){
            for(x = 0; x < source.w; ++x){
                float val = get_pixel(source, x, y, k);
                float val2 = get_pixel_extend(dest, dx+x, dy+y, k);
                set_pixel(dest, dx+x, dy+y, k, val * val2);
            }
        }
    }
}

image border_image(image a, int border)
{
    image b = make_image(a.w + 2*border, a.h + 2*border, a.c);
    int x,y,k;
    for(k = 0; k < b.c; ++k){
        for(y = 0; y < b.h; ++y){
            for(x = 0; x < b.w; ++x){
                float val = get_pixel_extend(a, x - border, y - border, k);
                if(x - border < 0 || x - border >= a.w || y - border < 0 || y - border >= a.h) val = 1;
                set_pixel(b, x, y, k, val);
            }
        }
    }
    return b;
}

image tile_images(image a, image b, int dx)
{
    if(a.w == 0) return copy_image(b);
    image c = make_image(a.w + b.w + dx, (a.h > b.h) ? a.h : b.h, (a.c > b.c) ? a.c : b.c);
    fill_cpu(c.w*c.h*c.c, 1, c.data, 1);
    embed_image(a, c, 0, 0);
    composite_image(b, c, a.w + dx, 0);
    return c;
}

image get_label(image **characters, char *string, int size)
{
    if(size > 7) size = 7;
    image label = make_empty_image(0,0,0);
    while(*string){
        image l = characters[size][(int)*string];
        image n = tile_images(label, l, -size - 1 + (size+1)/2);
        free_image(label);
        label = n;
        ++string;
    }
    image b = border_image(label, label.h*.25);
    free_image(label);
    return b;
}

image get_label_v3(image **characters, char *string, int size)
{
    size = size / 10;
    if (size > 7) size = 7;
    image label = make_empty_image(0, 0, 0);
    while (*string) {
        image l = characters[size][(int)*string];
        image n = tile_images(label, l, -size - 1 + (size + 1) / 2);
        free_image(label);
        label = n;
        ++string;
    }
    image b = border_image(label, label.h*.25);
    free_image(label);
    return b;
}

void draw_label(image a, int r, int c, image label, const float *rgb)
{
    int w = label.w;
    int h = label.h;
    if (r - h >= 0) r = r - h;

    int i, j, k;
    for(j = 0; j < h && j + r < a.h; ++j){
        for(i = 0; i < w && i + c < a.w; ++i){
            for(k = 0; k < label.c; ++k){
                float val = get_pixel(label, i, j, k);
                set_pixel(a, i+c, j+r, k, rgb[k] * val);
            }
        }
    }
}

void draw_box(image a, int x1, int y1, int x2, int y2, float r, float g, float b)
{
    //normalize_image(a);
    int i;
    if(x1 < 0) x1 = 0;
    if(x1 >= a.w) x1 = a.w-1;
    if(x2 < 0) x2 = 0;
    if(x2 >= a.w) x2 = a.w-1;

    if(y1 < 0) y1 = 0;
    if(y1 >= a.h) y1 = a.h-1;
    if(y2 < 0) y2 = 0;
    if(y2 >= a.h) y2 = a.h-1;

    for(i = x1; i <= x2; ++i){
        a.data[i + y1*a.w + 0*a.w*a.h] = r;
        a.data[i + y2*a.w + 0*a.w*a.h] = r;

        a.data[i + y1*a.w + 1*a.w*a.h] = g;
        a.data[i + y2*a.w + 1*a.w*a.h] = g;

        a.data[i + y1*a.w + 2*a.w*a.h] = b;
        a.data[i + y2*a.w + 2*a.w*a.h] = b;
    }
    for(i = y1; i <= y2; ++i){
        a.data[x1 + i*a.w + 0*a.w*a.h] = r;
        a.data[x2 + i*a.w + 0*a.w*a.h] = r;

        a.data[x1 + i*a.w + 1*a.w*a.h] = g;
        a.data[x2 + i*a.w + 1*a.w*a.h] = g;

        a.data[x1 + i*a.w + 2*a.w*a.h] = b;
        a.data[x2 + i*a.w + 2*a.w*a.h] = b;
    }
}

void draw_box_width(image a, int x1, int y1, int x2, int y2, int w, float r, float g, float b)
{
    int i;
    for(i = 0; i < w; ++i){
        draw_box(a, x1+i, y1+i, x2-i, y2-i, r, g, b);
    }
}

void draw_bbox(image a, box bbox, int w, float r, float g, float b)
{
    int left  = (bbox.x-bbox.w/2)*a.w;
    int right = (bbox.x+bbox.w/2)*a.w;
    int top   = (bbox.y-bbox.h/2)*a.h;
    int bot   = (bbox.y+bbox.h/2)*a.h;

    int i;
    for(i = 0; i < w; ++i){
        draw_box(a, left+i, top+i, right-i, bot-i, r, g, b);
    }
}

image **load_alphabet()
{
    int i, j;
    const int nsize = 8;
    image **alphabets = calloc(nsize, sizeof(image));
    for(j = 0; j < nsize; ++j){
        alphabets[j] = calloc(128, sizeof(image));
        for(i = 32; i < 127; ++i){
            char buff[256];
            sprintf(buff, "data/labels/%d_%d.png", i, j);
            alphabets[j][i] = load_image_color(buff, 0, 0);
        }
    }
    return alphabets;
}



// Creates array of detections with prob > thresh and fills best_class for them
detection_with_class* get_actual_detections(detection *dets, int dets_num, float thresh, int* selected_detections_num)
{
    int selected_num = 0;
    detection_with_class* result_arr = calloc(dets_num, sizeof(detection_with_class));
    int i;
    for (i = 0; i < dets_num; ++i) {		//提取到的特徵目標迴圈判斷
        int best_class = -1;
        float best_class_prob = thresh;
        int j;
        for (j = 0; j < dets[i].classes; ++j) {		//對檢測到的目標的類別概率判斷，賦予最大的概率類別
            if (dets[i].prob[j] > best_class_prob ) {
                best_class = j;
                best_class_prob = dets[i].prob[j];
            }
        }
        if (best_class >= 0) {			//如果最大的類別概率大於0，該detction結構體賦給result_arr返回
            result_arr[selected_num].det = dets[i];
            result_arr[selected_num].best_class = best_class;
            ++selected_num;
        }
    }
    if (selected_detections_num)
        *selected_detections_num = selected_num;
    return result_arr;
}

// compare to sort detection** by bbox.x
int compare_by_lefts(const void *a_ptr, const void *b_ptr) {
    const detection_with_class* a = (detection_with_class*)a_ptr;
    const detection_with_class* b = (detection_with_class*)b_ptr;
    const float delta = (a->det.bbox.x - a->det.bbox.w/2) - (b->det.bbox.x - b->det.bbox.w/2);
    return delta < 0 ? -1 : delta > 0 ? 1 : 0;
}

// compare to sort detection** by best_class probability
int compare_by_probs(const void *a_ptr, const void *b_ptr) {
    const detection_with_class* a = (detection_with_class*)a_ptr;
    const detection_with_class* b = (detection_with_class*)b_ptr;
    float delta = a->det.prob[a->best_class] - b->det.prob[b->best_class];
    return delta < 0 ? -1 : delta > 0 ? 1 : 0;
}

void draw_detections_v3(image im, detection *dets, int num, float thresh, char **names, image **alphabet, int classes, int ext_output)
{
    int selected_detections_num;
	//例項化一個結構體並得到卷積後的各個特徵的類名和最大概率
    detection_with_class* selected_detections = get_actual_detections(dets, num, thresh, &selected_detections_num); 
    // text output
    qsort(selected_detections, selected_detections_num, sizeof(*selected_detections), compare_by_lefts);
    int i;
    for (i = 0; i < selected_detections_num; ++i) {  //對於檢測到的目標的迴圈
         int best_class = selected_detections[i].best_class;		//上面返回的結構體中的best_class   原為const int
		/*************dspeia 20181026 修改label上的顯示***************/
		if (best_class != 1 && best_class != 2 && best_class !=  3 && best_class != 0){ 
			printf("%s: %.0f%%   ******* image.c 292 *******", names[79], selected_detections[i].det.prob[best_class] * 100);  //增加這一句，cmd上顯示other，呼叫的coco.name檔案，如何圖片上顯示other？？
		}
		else {
			printf("%s: %.0f%%   ******* image.c 292 *******", names[best_class], selected_detections[i].det.prob[best_class] * 100);
		}
        if (ext_output)				//如果cmd的命令該位置為真，可打印出各個目標的box位置
            printf("\t(left_x: %4.0f   top_y: %4.0f   width: %4.0f   height: %4.0f)\n",
                (selected_detections[i].det.bbox.x - selected_detections[i].det.bbox.w / 2)*im.w,
                (selected_detections[i].det.bbox.y - selected_detections[i].det.bbox.h / 2)*im.h,
                selected_detections[i].det.bbox.w*im.w, selected_detections[i].det.bbox.h*im.h);
        else
            printf("\n");
        //int j;
        //for (j = 0; j < classes; ++j) {			//一個object有多個預測類別時進入，輸出大於給定閾值的同一個目標的不同類別資訊。控制是否進入for的是classes
        //    if (selected_detections[i].det.prob[j] > thresh && j != best_class) {
        //        printf("%s: %.0f%%    ******image.c 303 ***** \n", names[j], selected_detections[i].det.prob[j] * 100);
        //    }
        //}
    }
	/*******************dspeia 20181017***********************/
	

    // image output
    qsort(selected_detections, selected_detections_num, sizeof(*selected_detections), compare_by_probs);
    for (i = 0; i < selected_detections_num; ++i) {
            int width = im.h * .006;
            if (width < 1)
                width = 1;

            /*
            if(0){
            width = pow(prob, 1./2.)*10+1;
            alphabet = 0;
            }
            */

            //printf("%d %s: %.0f%%\n", i, names[selected_detections[i].best_class], prob*100);
            int offset = selected_detections[i].best_class * 123457 % classes;
            float red = get_color(2, offset, classes);
            float green = get_color(1, offset, classes);
            float blue = get_color(0, offset, classes);
            float rgb[3];

            //width = prob*20+2;
			//rgb值為了定義label框的顏色
            rgb[0] = red;
            rgb[1] = green;
            rgb[2] = blue;
            box b = selected_detections[i].det.bbox;
            //printf("%f %f %f %f\n", b.x, b.y, b.w, b.h);

            int left = (b.x - b.w / 2.)*im.w;
            int right = (b.x + b.w / 2.)*im.w;
            int top = (b.y - b.h / 2.)*im.h;
            int bot = (b.y + b.h / 2.)*im.h;

            if (left < 0) left = 0;
            if (right > im.w - 1) right = im.w - 1;
            if (top < 0) top = 0;
            if (bot > im.h - 1) bot = im.h - 1;



			/*******************************/
			int the_class = selected_detections[i].best_class;

			//char cut_class[20] = { 0 };		//為了傳類名到cut函式的方法一
			//strcpy(cut_class, names[the_class]);
			//char cut_class = names[the_class];
			float cut_pro = selected_detections[i].det.prob[the_class] * 100;
			printf("******355 **cut_class  :%s  ...........cut_class:%.0f \n", names[the_class], cut_pro);
			//printf(cut_class);
			//printf("%f", cut_pro);	//

			/******dspeia    ****/
			int pre_x = left;
			int pre_y = top;
			int pre_h = bot - top;
			int pre_w = right - left;
			save_cut_image(pre_x, pre_y, pre_h, pre_w, i, im, names, cut_pro, the_class);
			printf("/************  cut and save over *****************/ \n");
			/********************************/

            //int b_x_center = (left + right) / 2;
            //int b_y_center = (top + bot) / 2;
            //int b_width = right - left;
            //int b_height = bot - top;
            //sprintf(labelstr, "%d x %d - w: %d, h: %d", b_x_center, b_y_center, b_width, b_height);

            draw_box_width(im, left, top, right, bot, width, red, green, blue);
            if (alphabet) {
                char labelstr[4096] = { 0 };
				if (selected_detections[i].best_class != 0 && selected_detections[i].best_class != 1 && selected_detections[i].best_class != 2 && selected_detections[i].best_class != 3){
					strcat(labelstr, names[79]);  //加入這一句if，在label上寫other
				}
				else
				{
					strcat(labelstr, names[selected_detections[i].best_class]);

				}
                //int j;
                //for (j = 0; j < classes; ++j) {  //同一個object多個預測時，畫多個框,註釋了圖片上仍然畫第二框，只是cmd上不列印第二預測
                //    if (selected_detections[i].det.prob[j] > thresh && j != selected_detections[i].best_class) {
                //        strcat(labelstr, ", ");
                //        strcat(labelstr, names[j]);
                //    }
                //}
                image label = get_label_v3(alphabet, labelstr, (im.h*.03));  //畫出框，複製到im上
                draw_label(im, top + width, left, label, rgb);
				//image* pic -> label;
				//const CvArr* label_copy = (CvArr*)&label;          //**********************
				//cvShowImage("*ima 394 label", label_copy);        //***********dspeia plus test
                free_image(label);				
            }
            if (selected_detections[i].det.mask) {
                image mask = float_to_image(14, 14, 1, selected_detections[i].det.mask);
                image resized_mask = resize_image(mask, b.w*im.w, b.h*im.h);
                image tmask = threshold_image(resized_mask, .5);
                embed_image(tmask, im, left, top);
                free_image(mask);
                free_image(resized_mask);
                free_image(tmask);
            }
    }
    free(selected_detections);
}

/********************dspeia  20181017********************/
/***********     darknet.exe detector test cfg/coco.data cfg/yolov3.cfg yolov3.weights    */

void save_cut_image(int px, int py, int ph, int pw, int no, image m_img, char **names, float cut_pro, int the_class)
{
	//cvShowImage("the enter", *m_img);
	image copy = copy_image(m_img);
	if (m_img.c == 3) rgbgr_image(copy);
	int x, y, k;
	char buff[256];
	/*****************************/
	//printf("%s: %.0f%%   ******* image.c 292 *******", cut_clas, selected_detections[i].det.prob[best_class] * 100);
	/**********************************/
	sprintf(buff, "results//%s%.0f%%%d.jpg", names[the_class], cut_pro, no);
	printf("****411** cut_class  :%s  ...........cut_class:%.0f ", names[the_class], cut_pro);//
	printf(names[the_class]);
	printf("%f",cut_pro);	//
	IplImage *disp = cvCreateImage(cvSize(m_img.w, m_img.h), IPL_DEPTH_8U, m_img.c);
	//cvShowImage("**the enter", disp);   //disp 為黑框亂碼
	int step = disp->widthStep;
	for (y = 0; y < m_img.h; ++y) {
		for (x = 0; x < m_img.w; ++