本人是在JESON TK1開發板上實現yolo的視訊實時執行測試

darknet的安裝很簡單，從官網上克隆程式碼即可：

git clone https://github.com/pjreddie/darknet.git

修改makefile檔案，使用opencv和cuda

GPU=1
OPENCV=1

切換目錄
cd darknet
make通過就安裝成功，若出現如下錯誤：

obj/avgpool_layer_kernels.o -o libdarknet.so -lm -pthreadpkg-config –libs OpenCV-L/usr/local/cuda/lib64 -lcuda
 
 -lcudart -lcublas -lcurand -lstdc++ 
/usr/bin/ld: cannot find -lcudart 
/usr/bin/ld: cannot find -lcublas 
/usr/bin/ld: cannot find -lcurand 

下面進行視訊測試
權重檔案請自行在darknet官網下載，本部落格使用了tiny-yolo-voc.weights
tiny-yolo-coco.weights （考慮到TK1開發板效能速度問題，只使用了小模型）

VOC資料集測試，連線攝像頭，執行命令

cd darknet
#voc webcam test
.
 
/darknet detector demo cfg/voc.data cfg/tiny-yolo-voc.cfg tiny-yolo-voc.weights

測試速度不夠快，修改網路輸入圖片大小到208x208，修改tiny-yolo-voc.cfg第四行

width=208
height=208

速度達到16幀左右，基本滿足實時要求

同理：
coco資料集測試，連線攝像頭，執行命令

cd darknet
#coco webcam test
./darknet detector demo cfg/coco.data cfg/tiny-yolo.cfg tiny-yolo-coco.weights
 

速度在15幀左右

本測試主要程式碼梳理：

./darknet detector demo cfg/voc.data cfg/tiny-yolo-voc.cfg tiny-yolo-voc.weights

上述命令的意思是進入darknet.c檔案，這個檔案在examples資料夾中，然後進入darknet.c的main函式，main函式主要是判斷輸入的引數，判斷的時候以空格左鍵分隔符，根據輸入引數執行程式碼，main函式的主要程式碼：

int main(int argc, char **argv)
{
    //test_resize("data/bad.jpg");
    //test_box();
    //test_convolutional_layer();
    if(argc < 2){
        fprintf(stderr, "usage: %s <function>\n", argv[0]);
        return 0;
    }
    gpu_index = find_int_arg(argc, argv, "-i", 0);
    if(find_arg(argc, argv, "-nogpu")) {
        gpu_index = -1;
    }

#ifndef GPU
    gpu_index = -1;
#else
    if(gpu_index >= 0){
        cuda_set_device(gpu_index);
    }
#endif

    if (0 == strcmp(argv[1], "average")){
        average(argc, argv);
    } else if (0 == strcmp(argv[1], "yolo")){
        run_yolo(argc, argv);
    } else if (0 == strcmp(argv[1], "voxel")){
        run_voxel(argc, argv);
    } else if (0 == strcmp(argv[1], "super")){
        run_super(argc, argv);
    } else if (0 == strcmp(argv[1], "lsd")){
        run_lsd(argc, argv);
    } else if (0 == strcmp(argv[1], "detector")){
        run_detector(argc, argv);
    } else if (0 == strcmp(argv[1], "detect")){
        float thresh = find_float_arg(argc, argv, "-thresh", .24);
        char *filename = (argc > 4) ? argv[4]: 0;
        char *outfile = find_char_arg(argc, argv, "-out", 0);
        int fullscreen = find_arg(argc, argv, "-fullscreen");
        test_detector("cfg/coco.data", argv[2], argv[3], filename, thresh, .5, outfile, fullscreen);
    } else if (0 == strcmp(argv[1], "cifar")){
        run_cifar(argc, argv);
    } else if (0 == strcmp(argv[1], "go")){
        run_go(argc, argv);
    } else if (0 == strcmp(argv[1], "rnn")){
        run_char_rnn(argc, argv);
    } else if (0 == strcmp(argv[1], "vid")){
        run_vid_rnn(argc, argv);
    } else if (0 == strcmp(argv[1], "coco")){
        run_coco(argc, argv);
    } else if (0 == strcmp(argv[1], "classify")){
        predict_classifier("cfg/imagenet1k.data", argv[2], argv[3], argv[4], 5);
    } else if (0 == strcmp(argv[1], "classifier")){
        run_classifier(argc, argv);
    } else if (0 == strcmp(argv[1], "regressor")){
        run_regressor(argc, argv);
    } else if (0 == strcmp(argv[1], "segmenter")){
        run_segmenter(argc, argv);
    } else if (0 == strcmp(argv[1], "art")){
        run_art(argc, argv);
    } else if (0 == strcmp(argv[1], "tag")){
        run_tag(argc, argv);
    } else if (0 == strcmp(argv[1], "compare")){
        run_compare(argc, argv);
    } else if (0 == strcmp(argv[1], "dice")){
        run_dice(argc, argv);
    } else if (0 == strcmp(argv[1], "writing")){
        run_writing(argc, argv);
    } else if (0 == strcmp(argv[1], "3d")){
        composite_3d(argv[2], argv[3], argv[4], (argc > 5) ? atof(argv[5]) : 0);
    } else if (0 == strcmp(argv[1], "test")){
        test_resize(argv[2]);
    } else if (0 == strcmp(argv[1], "captcha")){
        run_captcha(argc, argv);
    } else if (0 == strcmp(argv[1], "nightmare")){
        run_nightmare(argc, argv);
    } else if (0 == strcmp(argv[1], "rgbgr")){
        rgbgr_net(argv[2], argv[3], argv[4]);
    } else if (0 == strcmp(argv[1], "reset")){
        reset_normalize_net(argv[2], argv[3], argv[4]);
    } else if (0 == strcmp(argv[1], "denormalize")){
        denormalize_net(argv[2], argv[3], argv[4]);
    } else if (0 == strcmp(argv[1], "statistics")){
        statistics_net(argv[2], argv[3]);
    } else if (0 == strcmp(argv[1], "normalize")){
        normalize_net(argv[2], argv[3], argv[4]);
    } else if (0 == strcmp(argv[1], "rescale")){
        rescale_net(argv[2], argv[3], argv[4]);
    } else if (0 == strcmp(argv[1], "ops")){
        operations(argv[2]);
    } else if (0 == strcmp(argv[1], "speed")){
        speed(argv[2], (argc > 3 && argv[3]) ? atoi(argv[3]) : 0);
    } else if (0 == strcmp(argv[1], "oneoff")){
        oneoff(argv[2], argv[3], argv[4]);
    } else if (0 == strcmp(argv[1], "oneoff2")){
        oneoff2(argv[2], argv[3], argv[4], atoi(argv[5]));
    } else if (0 == strcmp(argv[1], "partial")){
        partial(argv[2], argv[3], argv[4], atoi(argv[5]));
    } else if (0 == strcmp(argv[1], "average")){
        average(argc, argv);
    } else if (0 == strcmp(argv[1], "visualize")){
        visualize(argv[2], (argc > 3) ? argv[3] : 0);
    } else if (0 == strcmp(argv[1], "mkimg")){
        mkimg(argv[2], argv[3], atoi(argv[4]), atoi(argv[5]), atoi(argv[6]), argv[7]);
    } else if (0 == strcmp(argv[1], "imtest")){
        test_resize(argv[2]);
    } else {
        fprintf(stderr, "Not an option: %s\n", argv[1]);
    }
    return 0;
}

本部落格測試輸入引數為detector，因此你執行main的以下程式碼：

else if (0 == strcmp(argv[1], "detector")){
        run_detector(argc, argv);

run_detector函式位於examples資料夾中detector.c檔案，程式碼如下：

void run_detector(int argc, char **argv)
{
    char *prefix = find_char_arg(argc, argv, "-prefix", 0);
    float thresh = find_float_arg(argc, argv, "-thresh", .24);
    float hier_thresh = find_float_arg(argc, argv, "-hier", .5);
    int cam_index = find_int_arg(argc, argv, "-c", 0);
    int frame_skip = find_int_arg(argc, argv, "-s", 0);
    int avg = find_int_arg(argc, argv, "-avg", 3);
    if(argc < 4){
        fprintf(stderr, "usage: %s %s [train/test/valid] [cfg] [weights (optional)]\n", argv[0], argv[1]);
        return;
    }
    char *gpu_list = find_char_arg(argc, argv, "-gpus", 0);
    char *outfile = find_char_arg(argc, argv, "-out", 0);
    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");
    int fullscreen = find_arg(argc, argv, "-fullscreen");
    int width = find_int_arg(argc, argv, "-w", 0);
    int height = find_int_arg(argc, argv, "-h", 0);
    int fps = find_int_arg(argc, argv, "-fps", 0);

    char *datacfg = argv[3];
    char *cfg = argv[4];
    char *weights = (argc > 5) ? argv[5] : 0;
    char *filename = (argc > 6) ? argv[6]: 0;
    if(0==strcmp(argv[2], "test")) test_detector(datacfg, cfg, weights, filename, thresh, hier_thresh, outfile, fullscreen);
    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, outfile);
    else if(0==strcmp(argv[2], "valid2")) validate_detector_flip(datacfg, cfg, weights, outfile);
    else if(0==strcmp(argv[2], "recall")) validate_detector_recall(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, avg, hier_thresh, width, height, fps, fullscreen);
    }
}

命令列輸入第二個引數為demo，因此上述程式碼關鍵函式是demo()，demo函式位於src資料夾的demo.c檔案中，用於實現檢測和顯示檢測結果。程式碼如下：

void demo(char *cfgfile, char *weightfile, float thresh, int cam_index, const char *filename, char **names, int classes, int delay, char *prefix, int avg_frames, float hier, int w, int h, int frames, int fullscreen)
{
    demo_delay = delay;
    demo_frame = avg_frames;
    predictions = calloc(demo_frame, sizeof(float*));
    image **alphabet = load_alphabet();
    demo_names = names;
    demo_alphabet = alphabet;
    demo_classes = classes;
    demo_thresh = thresh;
    demo_hier = hier;
    printf("Demo\n");
    net = parse_network_cfg(cfgfile);
    if(weightfile){
        load_weights(&net, weightfile);
    }
    set_batch_network(&net, 1);
    pthread_t detect_thread;
    pthread_t fetch_thread;

    srand(2222222);

    if(filename){
        printf("video file: %s\n", filename);
        cap = cvCaptureFromFile(filename);
    }else{
        cap = cvCaptureFromCAM(cam_index);

        if(w){
            cvSetCaptureProperty(cap, CV_CAP_PROP_FRAME_WIDTH, w);
        }
        if(h){
            cvSetCaptureProperty(cap, CV_CAP_PROP_FRAME_HEIGHT, h);
        }
        if(frames){
            cvSetCaptureProperty(cap, CV_CAP_PROP_FPS, frames);
        }
    }

    if(!cap) error("Couldn't connect to webcam.\n");

    layer l = net.layers[net.n-1];
    demo_detections = l.n*l.w*l.h;
    int j;

    avg = (float *) calloc(l.outputs, sizeof(float));
    last_avg  = (float *) calloc(l.outputs, sizeof(float));
    last_avg2 = (float *) calloc(l.outputs, sizeof(float));
    for(j = 0; j < demo_frame; ++j) predictions[j] = (float *) calloc(l.outputs, sizeof(float));

    boxes = (box *)calloc(l.w*l.h*l.n, sizeof(box));
    probs = (float **)calloc(l.w*l.h*l.n, sizeof(float *));
    for(j = 0; j < l.w*l.h*l.n; ++j) probs[j] = (float *)calloc(l.classes+1, sizeof(float));

    buff[0] = get_image_from_stream(cap);
    buff[1] = copy_image(buff[0]);
    buff[2] = copy_image(buff[0]);
    buff_letter[0] = letterbox_image(buff[0], net.w, net.h);
    buff_letter[1] = letterbox_image(buff[0], net.w, net.h);
    buff_letter[2] = letterbox_image(buff[0], net.w, net.h);
    ipl = cvCreateImage(cvSize(buff[0].w,buff[0].h), IPL_DEPTH_8U, buff[0].c);

    int count = 0;
    if(!prefix){
        cvNamedWindow("Demo", CV_WINDOW_NORMAL); 
        if(fullscreen){
            cvSetWindowProperty("Demo", CV_WND_PROP_FULLSCREEN, CV_WINDOW_FULLSCREEN);
        } else {
            cvMoveWindow("Demo", 0, 0);
            cvResizeWindow("Demo", 1352, 1013);
        }
    }

    demo_time = get_wall_time();

    while(!demo_done){
        buff_index = (buff_index + 1) %3;
        if(pthread_create(&fetch_thread, 0, fetch_in_thread, 0)) error("Thread creation failed");
        if(pthread_create(&detect_thread, 0, detect_in_thread, 0)) error("Thread creation failed");
        if(!prefix){
            if(count % (demo_delay+1) == 0){
                fps = 1./(get_wall_time() - demo_time);
                demo_time = get_wall_time();
                float *swap = last_avg;
                last_avg  = last_avg2;
                last_avg2 = swap;
                memcpy(last_avg, avg, l.outputs*sizeof(float));
            }
            display_in_thread(0);
        }else{
            char name[256];
            sprintf(name, "%s_%08d", prefix, count);
            save_image(buff[(buff_index + 1)%3], name);
        }
        pthread_join(fetch_thread, 0);
        pthread_join(detect_thread, 0);
        ++count;
    }
}
#else
void demo(char *cfgfile, char *weightfile, float thresh, int cam_index, const char *filename, char **names, int classes, int delay, char *prefix, int avg, float hier, int w, int h, int frames, int fullscreen)
{
    fprintf(stderr, "Demo needs OpenCV for webcam images.\n");
}