darknet源码分析之detect

首先下载源码，源码下载地址
由于本人是边看代码边记录，可能会有理解不对的地方，我会在看完整个源码之后，对博客内容进行修正。
Darknet代码详解（以darknet目录为相对目录）：
入口:examples/darknet.c

int main(int argc, char **argv)
{
    //test_resize("data/bad.jpg");
    //test_box();
    //test_convolutional_layer();
    if(argc < 2){
        fprintf(stderr, "usage: %s \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], "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")){
        //获取threshold值
        float thresh = find_float_arg(argc, argv, "-thresh", .24);
        //获取输入文件名
        char *filename = (argc > 4) ? argv[4]: 0;
        //获取输出文件名
        char *outfile = find_char_arg(argc, argv, "-out", 0);
        //是否全屏展示
        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], "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], "attention")){
        run_attention(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], "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;
}

从main（）函数可以看出，darknet支持很多参数，这篇主要讲述detect函数的用法
detect是使用模型进行预测的函数，比如用模型测试某张具体图片，命令如下：
./darknet detect cfg/yolo.cfg yolo.weights data/horses.jpg

下面就开始讲解test_detector（）函数（写的可能比较乱，大家有不理解的可以留言）

void test_detector(char *datacfg, char *cfgfile, char *weightfile, char *filename, float thresh, float hier_thresh, char *outfile, int fullscreen)
{
    //读取cfg文件（类似ini文件key=value），存储于双向链表
    list *options = read_data_cfg(datacfg);
    //从option中查找names对应的value，如没有，使用默认值“data/names.list”
    char *name_list = option_find_str(options, "names", "data/names.list");
    //获取所有类别名称，对应xml中定义的分类
    char **names = get_labels(name_list);
    //从data/labels/下加载ASCII码32-127的8种尺寸的图片，后边显示标签用。
    image **alphabet = load_alphabet();
    //加载之前训练的超参（权重等），这个函数之后详解
    network *net = load_network(cfgfile, weightfile, 0);
    //设置每层batch为1
    set_batch_network(net, 1);
    //srand函数是随机数发生器的初始化函数
    srand(2222222);
    double time;
    char buff[256];
    char *input = buff;
    int j;
    float nms=.3;
    while(1){
        if(filename){
            strncpy(input, filename, 256);
        } else {
            printf("Enter Image Path: ");
            fflush(stdout);
            input = fgets(input, 256, stdin);
            if(!input) return;
            strtok(input, "\n");
        }
        //加载图片，默认当做彩色处理
        image im = load_image_color(input,0,0);
        //调整图片尺寸
        image sized = letterbox_image(im, net->w, net->h);
        //image sized = resize_image(im, net->w, net->h);
        //image sized2 = resize_max(im, net->w);
        //image sized = crop_image(sized2, -((net->w - sized2.w)/2), -((net->h - sized2.h)/2), net->w, net->h);
        //resize_network(net, sized.w, sized.h);
        layer l = net->layers[net->n-1];

        box *boxes = calloc(l.w*l.h*l.n, sizeof(box));
        float **probs = calloc(l.w*l.h*l.n, sizeof(float *));
        for(j = 0; j < l.w*l.h*l.n; ++j) probs[j] = calloc(l.classes + 1, sizeof(float *));
        float **masks = 0;
        if (l.coords > 4){
            masks = calloc(l.w*l.h*l.n, sizeof(float*));
            for(j = 0; j < l.w*l.h*l.n; ++j) masks[j] = calloc(l.coords-4, sizeof(float *));
        }

        float *X = sized.data;
        time=what_time_is_it_now();
        //预测
        network_predict(net, X);
        printf("%s: Predicted in %f seconds.\n", input, what_time_is_it_now()-time);
        get_region_boxes(l, im.w, im.h, net->w, net->h, thresh, probs, boxes, masks, 0, 0, hier_thresh, 1);
        //if (nms) do_nms_obj(boxes, probs, l.w*l.h*l.n, l.classes, nms);
        if (nms) do_nms_sort(boxes, probs, l.w*l.h*l.n, l.classes, nms);
        //画预测结果
        draw_detections(im, l.w*l.h*l.n, thresh, boxes, probs, masks, names, alphabet, l.classes);
        //保存标记了预测标签的图片
        if(outfile){
            save_image(im, outfile);
        }
        else{
            save_image(im, "predictions");
#ifdef OPENCV
            cvNamedWindow("predictions", CV_WINDOW_NORMAL); 
            if(fullscreen){
                cvSetWindowProperty("predictions", CV_WND_PROP_FULLSCREEN, CV_WINDOW_FULLSCREEN);
            }
            show_image(im, "predictions");
            cvWaitKey(0);
            cvDestroyAllWindows();
#endif
        }

        free_image(im);
        free_image(sized);
        free(boxes);
        free_ptrs((void **)probs, l.w*l.h*l.n);
        if (filename) break;
    }
}

下面详细讲解load_network

network *load_network(char *cfg, char *weights, int clear)
{
    //解析yolo.cfg文件（主要是解析网络模型的结构，包括网络的层数，每层网络的参数类型，参数）
    network *net = parse_network_cfg(cfg);
    if(weights && weights[0] != 0){
        //加载预训练的权重。
        load_weights(net, weights);
    }
    if(clear) (*net->seen) = 0;
    return net;
}

下面详细讲解parse_network_cfg

network *parse_network_cfg(char *filename)
{
    //读取网络模型的结构，存于双向链表中
    list *sections = read_cfg(filename);
    node *n = sections->front;
    if(!n) error("Config file has no sections");
    //根据配置文件中参数创建网络模型
    network *net = make_network(sections->size - 1);
    net->gpu_index = gpu_index;
    size_params params;

    section *s = (section *)n->val;
    list *options = s->options;
    if(!is_network(s)) error("First section must be [net] or [network]");
    parse_net_options(options, net);

    params.h = net->h;
    params.w = net->w;
    params.c = net->c;
    params.inputs = net->inputs;
    params.batch = net->batch;
    params.time_steps = net->time_steps;
    params.net = net;

    size_t workspace_size = 0;
    n = n->next;
    int count = 0;
    free_section(s);
    fprintf(stderr, "layer     filters    size              input                output\n");
    while(n){
        params.index = count;
        fprintf(stderr, "%5d ", count);
        s = (section *)n->val;
        options = s->options;
        layer l = {0};
        LAYER_TYPE lt = string_to_layer_type(s->type);
        if(lt == CONVOLUTIONAL){
            l = parse_convolutional(options, params);
        }else if(lt == DECONVOLUTIONAL){
            l = parse_deconvolutional(options, params);
        }else if(lt == LOCAL){
            l = parse_local(options, params);
        }else if(lt == ACTIVE){
            l = parse_activation(options, params);
        }else if(lt == RNN){
            l = parse_rnn(options, params);
        }else if(lt == GRU){
            l = parse_gru(options, params);
        }else if (lt == LSTM) {
            l = parse_lstm(options, params);
        }else if(lt == CRNN){
            l = parse_crnn(options, params);
        }else if(lt == CONNECTED){
            l = parse_connected(options, params);
        }else if(lt == CROP){
            l = parse_crop(options, params);
        }else if(lt == COST){
            l = parse_cost(options, params);
        }else if(lt == REGION){
            l = parse_region(options, params);
        }else if(lt == DETECTION){
            l = parse_detection(options, params);
        }else if(lt == SOFTMAX){
            l = parse_softmax(options, params);
            net->hierarchy = l.softmax_tree;
        }else if(lt == NORMALIZATION){
            l = parse_normalization(options, params);
        }else if(lt == BATCHNORM){
            l = parse_batchnorm(options, params);
        }else if(lt == MAXPOOL){
            l = parse_maxpool(options, params);
        }else if(lt == REORG){
            l = parse_reorg(options, params);
        }else if(lt == AVGPOOL){
            l = parse_avgpool(options, params);
        }else if(lt == ROUTE){
            l = parse_route(options, params, net);
        }else if(lt == SHORTCUT){
            l = parse_shortcut(options, params, net);
        }else if(lt == DROPOUT){
            l = parse_dropout(options, params);
            l.output = net->layers[count-1].output;
            l.delta = net->layers[count-1].delta;
#ifdef GPU
            l.output_gpu = net->layers[count-1].output_gpu;
            l.delta_gpu = net->layers[count-1].delta_gpu;
#endif
        }else{
            fprintf(stderr, "Type not recognized: %s\n", s->type);
        }
        l.truth = option_find_int_quiet(options, "truth", 0);
        l.onlyforward = option_find_int_quiet(options, "onlyforward", 0);
        l.stopbackward = option_find_int_quiet(options, "stopbackward", 0);
        l.dontload = option_find_int_quiet(options, "dontload", 0);
        l.dontloadscales = option_find_int_quiet(options, "dontloadscales", 0);
        l.learning_rate_scale = option_find_float_quiet(options, "learning_rate", 1);
        l.smooth = option_find_float_quiet(options, "smooth", 0);
        option_unused(options);
        net->layers[count] = l;
        if (l.workspace_size > workspace_size) workspace_size = l.workspace_size;
        free_section(s);
        n = n->next;
        ++count;
        if(n){
            params.h = l.out_h;
            params.w = l.out_w;
            params.c = l.out_c;
            params.inputs = l.outputs;
        }
    }
    free_list(sections);
    layer out = get_network_output_layer(net);
    net->outputs = out.outputs;
    net->truths = out.outputs;
    if(net->layers[net->n-1].truths) net->truths = net->layers[net->n-1].truths;
    net->output = out.output;
    net->input = calloc(net->inputs*net->batch, sizeof(float));
    net->truth = calloc(net->truths*net->batch, sizeof(float));
#ifdef GPU
    net->output_gpu = out.output_gpu;
    net->input_gpu = cuda_make_array(net->input, net->inputs*net->batch);
    net->truth_gpu = cuda_make_array(net->truth, net->truths*net->batch);
#endif
    if(workspace_size){
        //printf("%ld\n", workspace_size);
#ifdef GPU
        if(gpu_index >= 0){
            net->workspace = cuda_make_array(0, (workspace_size-1)/sizeof(float)+1);
        }else {
            net->workspace = calloc(1, workspace_size);
        }
#else
        net->workspace = calloc(1, workspace_size);
#endif
    }
    return net;
}