YOLO源码分析之detector.c

最新推荐文章于 2024-07-02 09:44:40 发布
最新推荐文章于 2024-07-02 09:44:40 发布
阅读量7.1k 收藏 7
点赞数
分类专栏： darknet
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/a130098300/article/details/53558004
版权

guthub地址:https://github.com/pjreddie/darknet/blob/master/

这里参考的网络定义文件如下

// cfg/yolo-voc.cfg
[net] # yolo的网络架构要求第一个section必须为[net]或[netowrk]，参见src/parse.c:586
# sections->size为cfg中配置的[*]数量，该cfg的size为32
batch=64
subdivisions=8
height=416
width=416
channels=3
momentum=0.9
decay=0.0005
angle=0
saturation = 1.5
exposure = 1.5
hue=.1

learning_rate=0.0001
max_batches = 45000
policy=steps
steps=100,25000,35000
scales=10,.1,.1

[convolutional]
batch_normalize=1
filters=32
size=3
stride=1
pad=1
activation=leaky

[maxpool]
size=2
stride=2

[convolutional]
batch_normalize=1
filters=64
size=3
stride=1
pad=1
activation=leaky

[maxpool]
size=2
stride=2

[convolutional]
batch_normalize=1
filters=128
size=3
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=64
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=128
size=3
stride=1
pad=1
activation=leaky

[maxpool]
size=2
stride=2

[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky

[maxpool]
size=2
stride=2

[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky

[maxpool]
size=2
stride=2

[convolutional]
batch_normalize=1
filters=1024
size=3
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=1024
size=3
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=1024
size=3
stride=1
pad=1
activation=leaky


#######

[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=1024
activation=leaky

[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=1024
activation=leaky

[route]
layers=-9

[reorg]
stride=2

[route]
layers=-1,-3

[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=1024
activation=leaky

[convolutional]
size=1
stride=1
pad=1
filters=125
activation=linear

[region]
anchors = 1.08,1.19,  3.42,4.41,  6.63,11.38,  9.42,5.11,  16.62,10.52
bias_match=1
classes=20
coords=4
num=5
softmax=1
jitter=.2
rescore=1

object_scale=5
noobject_scale=1
class_scale=1
coord_scale=1

absolute=1
thresh = .6
random=0

下面是detector.c的源代码 

#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"
#endif
static int coco_ids[] = {1,2,3,4,5,6,7,8,9,10,11,13,14,15,16,17,18,19,20,21,22,23,24,25,27,28,31,32,33,34,35,36,37,38,39,40,41,42,43,44,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,67,70,72,73,74,75,76,77,78,79,80,81,82,84,85,86,87,88,89,90};

void train_detector(char *datacfg, char *cfgfile, char *weightfile, int *gpus, int ngpus, int clear)
{
    list *options = read_data_cfg(datacfg);
    char *train_images = option_find_str(options, "train", "data/train.list");	// 训练自己的数据集时，这里要进行相应的修改
    char *backup_directory = option_find_str(options, "backup", "/backup/");	// 训练自己的数据集时，这里要进行相应的修改

    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];

    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]; //最后一层的索引号是net.n-1，这里net.n是31.所以最后一层region层的索引号是30

    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);

    load_args args = {0};
    args.w = net.w;	// [net]层的w
    args.h = net.h;
    args.paths = paths;
    args.n = imgs;
    args.m = plist->size; // train_images中的image数目，即训练样本数
    args.classes = classes;
    args.jitter = jitter;
    args.num_boxes = l.max_boxes; // cfg里没有配置该项，这里使用默认值30
    args.d = &buffer;
    args.type = DETECTION_DATA;
    args.threads = 8;

    args.angle = net.angle;
    args.exposure = net.exposure;
    args.saturation = net.saturation;
    args.hue = net.hue;

    pthread_t load_thread = load_data(args);
    clock_t 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() % 10 + 10) * 32;
            if (get_current_batch(net)+100 > net.max_batches) dim = 544;
            //int dim = (rand() % 4 + 16) * 32;
            printf("%d\n", dim);
            args.w = dim;
            args.h = dim;

            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, dim);
            }
            net = nets[0];
        }
        time=clock();
        pthread_join(load_thread, 0);
        train = buffer; //这里采用多线程的方式，这里获取的train里重要的成员变量有X{rows=batch, cols=[net].w*[net].h*[net].c}
        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", sec(clock()-time));

        time=clock();
        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 = loss;
        avg_loss = avg_loss*.9 + loss*.1;

        i = get_current_batch(net);
        printf("%d: %f, %f avg, %f rate, %lf seconds, %d images\n", get_current_batch(net), loss, avg_loss, get_current_rate(net), sec(clock()-time), i*imgs);
        if(i%1000==0 || (i < 1000 && i%100 == 0)){
#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);
}


static int get_coco_image_id(char *filename)
{
    char *p = strrchr(filename, '_');
    return atoi(p+1);
}

static void print_cocos(FILE *fp, char *image_path, box *boxes, float **probs, 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 = boxes[i].x - boxes[i].w/2.;
        float xmax = boxes[i].x + boxes[i].w/2.;
        float ymin = boxes[i].y - boxes[i].h/2.;
        float ymax = boxes[i].y + boxes[i].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 (probs[i][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, probs[i][j]);
        }
    }
}

void print_detector_detections(FILE **fps, char *id, box *boxes, float **probs, int total, int classes, int w, int h)
{
    int i, j;
    for(i = 0; i < total; ++i){
        float xmin = boxes[i].x - boxes[i].w/2.;
        float xmax = boxes[i].x + boxes[i].w/2.;
        float ymin = boxes[i].y - boxes[i].h/2.;
        float ymax = boxes[i].y + boxes[i].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){
            if (probs[i][j]) fprintf(fps[j], "%s %f %f %f %f %f\n", id, probs[i][j],
                    xmin, ymin, xmax, ymax);
        }
    }
}

void print_imagenet_detections(FILE *fp, int id, box *boxes, float **probs, int total, int classes, int w, int h)
{
    int i, j;
    for(i = 0; i < total; ++i){
        float xmin = boxes[i].x - boxes[i].w/2.;
        float xmax = boxes[i].x + boxes[i].w/2.;
        float ymin = boxes[i].y - boxes[i].h/2.;
        float ymax = boxes[i].y + boxes[i].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 (probs[i][class]) fprintf(fp, "%d %d %f %f %f %f %f\n", id, j+1, probs[i][class],
                    xmin, ymin, xmax, ymax);
        }
    }
}

void validate_detector(char *datacfg, char *cfgfile, char *weightfile)
{
    int j;
    list *options = read_data_cfg(datacfg);
    char *valid_images = option_find_str(options, "valid", "data/train.list");
    char *name_list = option_find_str(options, "names", "data/names.list");
    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(cfgfile);
    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));

    char *base = "comp4_det_test_";
    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")){
        snprintf(buff, 1024, "%s/coco_results.json", prefix);
        fp = fopen(buff, "w");
        fprintf(fp, "[\n");
        coco = 1;
    } else if(0==strcmp(type, "imagenet")){
        snprintf(buff, 1024, "%s/imagenet-detection.txt", prefix);
        fp = fopen(buff, "w");
        imagenet = 1;
        classes = 200;
    } else {
        fps = calloc(classes, sizeof(FILE *));
        for(j = 0; j < classes; ++j){
            snprintf(buff, 1024, "%s/%s%s.txt", prefix, base, names[j]);
            fps[j] = fopen(buff, "w");
        }
    }


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

    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.type = IMAGE_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;
            get_region_boxes(l, w, h, thresh, probs, boxes, 0, map);
            if (nms) do_nms_sort(boxes, probs, l.w*l.h*l.n, classes, nms);
            if (coco){
                print_cocos(fp, path, boxes, probs, l.w*l.h*l.n, classes, w, h);
            } else if (imagenet){
                print_imagenet_detections(fp, i+t-nthreads+1, boxes, probs, l.w*l.h*l.n, classes, w, h);
            } else {
                print_detector_detections(fps, id, boxes, probs, l.w*l.h*l.n, classes, w, h);
            }
            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 *cfgfile, char *weightfile)
{
    network net = parse_network_cfg(cfgfile);
    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("data/voc.2007.test");
    char **paths = (char **)list_to_array(plist);

    layer l = net.layers[net.n-1];
    int classes = l.classes;

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

    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_color(path, 0, 0);
        image sized = resize_image(orig, net.w, net.h);
        char *id = basecfg(path);
        network_predict(net, sized.data);
        get_region_boxes(l, 1, 1, thresh, probs, boxes, 1, 0);
        if (nms) do_nms(boxes, probs, l.w*l.h*l.n, 1, nms);

        char labelpath[4096];
        find_replace(path, "images", "labels", labelpath);
        find_replace(labelpath, "JPEGImages", "labels", labelpath);
        find_replace(labelpath, ".jpg", ".txt", labelpath);
        find_replace(labelpath, ".JPEG", ".txt", labelpath);

        int num_labels = 0;
        box_label *truth = read_boxes(labelpath, &num_labels);
        for(k = 0; k < l.w*l.h*l.n; ++k){
            if(probs[k][0] > 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 < l.w*l.h*l.n; ++k){
                float iou = box_iou(boxes[k], t);
                if(probs[k][0] > thresh && iou > best_iou){
                    best_iou = iou;
                }
            }
            avg_iou += best_iou;
            if(best_iou > iou_thresh){
                ++correct;
            }
        }

        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);
    }
}

void test_detector(char *datacfg, char *cfgfile, char *weightfile, char *filename, float thresh)
{
    list *options = read_data_cfg(datacfg);
    char *name_list = option_find_str(options, "names", "data/names.list");
    char **names = get_labels(name_list);

    image **alphabet = load_alphabet();
    network net = parse_network_cfg(cfgfile);
    if(weightfile){
        load_weights(&net, weightfile);
    }
    set_batch_network(&net, 1);
    srand(2222222);
    clock_t time;
    char buff[256];
    char *input = buff;
    int j;
    float nms=.4;
    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");
        }
        image im = load_image_color(input,0,0);
        image sized = resize_image(im, net.w, net.h);
        layer l = net.layers[net.n-1];

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

        float *X = sized.data;
        time=clock();
        network_predict(net, X);
        printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
        get_region_boxes(l, 1, 1, thresh, probs, boxes, 0, 0);
        if (nms) do_nms_sort(boxes, probs, l.w*l.h*l.n, l.classes, nms);
        draw_detections(im, l.w*l.h*l.n, thresh, boxes, probs, names, alphabet, l.classes);
        save_image(im, "predictions");
        show_image(im, "predictions");

        free_image(im);
        free_image(sized);
        free(boxes);
        free_ptrs((void **)probs, l.w*l.h*l.n);
#ifdef OPENCV
        cvWaitKey(0);
        cvDestroyAllWindows();
#endif
        if (filename) break;
    }
}

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);
    int cam_index = find_int_arg(argc, argv, "-c", 0);
    int frame_skip = find_int_arg(argc, argv, "-s", 0);
    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);
    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;
    char *filename = (argc > 6) ? argv[6]: 0;
    if(0==strcmp(argv[2], "test")) test_detector(datacfg, cfg, weights, filename, thresh);
    else if(0==strcmp(argv[2], "train")) train_detector(datacfg, cfg, weights, gpus, ngpus, clear);
    else if(0==strcmp(argv[2], "valid")) validate_detector(datacfg, cfg, weights);
    else if(0==strcmp(argv[2], "recall")) validate_detector_recall(cfg, weights);
    else if(0==strcmp(argv[2], "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);
    }
}


小班得瑞
关注
专栏目录
Tensorflow在手机端的部署——官网Android工程源码分析之TensorFlowYoloDetector.java (1)
c20081052的专栏
11-24 1430
文章分析下tensorflow提供的官方Android工程的源码分析，后续涉及更改代码，因此有必要对其做深入理解。 首先工程文件路径为：tensorflow-master\tensorflow\examples\android 由于这个android工程中实现了目标检测，风格迁移，语音，图像分类四个功能，其中目标检测中有用到yolo检测，有用到ssd-mobilenet v1检测，还有就是用到...
yolo3源码分析
热门推荐
runner668的博客
06-05 1万+
要想更好地调参或者修改相应的功能就必须对源码有所了解，为此先看一下安装目录再往下讲解是很必要的。顺便粘贴一下makefileGPU=0 CUDNN=0 OPENCV=0 OPENMP=0 DEBUG=0 ARCH= -gencode arch=compute_30,code=sm_30 \ -gencode arch=compute_35,code=sm_35 \ -ge...
yolo3批量测试 修改detector.c文件
qq_38214193的博客
09-07 4732
在网上找了一些批量的代码，发现跑不起来，之后看了一下，下载的darknet包的结构不同，于是自己结合网上的代码修改了一下自己的test_detector函数。 我使用的是这个网址上下载的darknet：https://github.com/AlexeyAB/darknet 修改的是darknet/src/detector.c文件中的test_detector函数。 1、复制如下代码替换原来的...
yolov4源码中的detector.c，为了方便对比修改部分，以及防止不同版本的yolov4源码
03-28
yolov4源码中的detector.c，为了方便对比修改部分，以及防止不同版本的yolov4源码
【yolo】非极大值抑制NMS在yolov5的使用与实现详解,含简单示例与代码解析
最新发布
qq_51677409的博客
07-02 1684
🚀交并比（IoU， Intersection over Union）是一种计算不同图像相互重叠比例的算法，经常被用于深度学习领域的目标检测或语义分割任务中。在我们得到模型输出的预测框位置后，也可以计算输出框与真实框（Ground Truth Bound）之间的 IoU，此时，这个框的取值范围为 0～1，0 表示两个框不相交，1 表示两个框正好重合。
Yolov3算法实现社交距离安全检测项目讲解和实战（Social Distance Detector）
哆啦A梦爱学习的博客
09-01 4763
点击上方“码农的后花园”，选择“星标”公众号精选文章，第一时间送达在我们进行交流谈话时，人与人之间总要保持一定的距离，尤其是在疫情的情况下，人与人之间更要保持一定的安全距离，今天给大家...
YOLODetector：对象检测器menggunakan metode YOLO（320，微小）
02-14
YOLOD检测器 物体检测器menggunakan metode YOLO（320，微小） 仓库github ini membutuhkan yolov3.weights / yolov3-tiny.weights文件.weights-nya menyesuaikan dengan yolo configurationnya .weights dapat didownload pada： ：//pjreddie.com/darknet/yolo/
yolov3源码解析——test_detector(01）
BTboay
12-15 865
上文说到darknet.c中主函数detect条件分支，即调用test_detector函数 下面对test_detector函数进行逐句分析，该函数在include/darknet.h中声明，在examples/detector.c中实现，源码如下： void test_detector(char *datacfg, char *cfgfile, char *weightfile, cha...
yolo源码解析c语言,YOLO 实践篇（darknet）：You Only Look Once
weixin_26757939的博客
05-21 1763
前言最近在学习 object detection 领域的相关知识，从传统的目标检测如 DPM 模型，到基于候选区的R-CNN系列模型，再到 single network && end to end 的 yolo 模型，还有针对 yolo 模型的缺陷进一步完善的 SSD 模型等等。一系列的理论和实践需要学习，希望能够记录学习过程中的点点滴滴，不断修改、完善和总结，系统的学习一遍。当然...
深度学习之---yolo源代码部分分析
zxyhhjs2017的博客
12-19 712
yolo代码是用c写的，我们先从主函数开始： main: int main(int argc, char **argv) { //test_resize("data/bad.jpg"); //test_box(); //test_convolutional_layer(); if(argc &lt; 2){ fprintf(stderr, "u...
darknet-master_difficults2l_yolo.zip
10-10
《深入解析darknet框架：基于darknet-master_difficults2l_yolo的源码分析》 Darknet是一款开源的深度学习框架，以其轻量级、高效和灵活性著称，尤其在目标检测领域有着广泛的应用。这里我们将深入探讨的darknet-...
yolov3测试代码test_detector
m0_37799466的博客
05-29 1664
void test_detector(char *datacfg, char *cfgfile, char *weightfile, char *filename, float thresh, float hier_thresh, char *outfile, int fullscreen) { //从datacfg文件中读取类别名称 list *options = read_data_cfg(datacfg); char *name_list = option_find_str(opti
yolov3 详解和C源码分析
damonlearning的博客
11-06 3406
检测部分 函数为 test_detector 这里主要研究cpu操作，下一篇会记录gpu的实现和cuda编程 1、读取文件 list *options = read_data_cfg(datacfg);//读取coco.data文件内容，放入双向链表里面, //逐行读取等号两边字符串放入kvp中，kvp存放在node中，list和node形成双向链表。 char *name_list = o...
yolov3源码解析——图像数据读取test_detector(02)
BTboay
12-17 1048
test_detector函数中image **alphabet = load_alphabet();实现对data/labels下的图像数据进行读取，本文主要解读这一部分设计的内容。 load_alphabet()函数在include/darknet.h中声明，在src/image.c中实现，代码如下： image **load_alphabet() { int i, j; ...
训练YOLO的一点心得（detector的一些指令用法）
看风起云落的博客
03-13 791
https://www.cnblogs.com/qinguoyi/p/8507803.html
yolo源码解析(1):代码逻辑
JarvisLau的博客
04-14 1295
一. 整体代码逻辑 yolo中源码分为三个部分,\example,\include,以及\src文件夹下都有源代码存在. 结构如下所示 ├── examples │ ├── darknet.c(主程序) │ │── xxx1.c │ └── xxx2.c │ ├── include │ ├── darknet.h │ │ ├── Makefile │ │ └── src
yolov3的yolo层源码详解
weixin_41912543的博客
09-24 2245
概述 yolo系列由于使用了纯c语言写，又是开源代码，所以自然成为了边缘计算的公司首选的架构。 它的重要性和影响力就不再赘述，本文主要从源码的角度，来带你深入理解yolo解析的思路，同时，在阅读源码的过程中也由衷感慨yolo作者代码的优美，整个代码没有依赖过多第三方库，只需要opencv用作效果显示，整个源码的大小只有不到1M（901K），却集成了CPU和GPU版本，可以说是非常强悍了。 准备知识 要看懂yolov3源码中yolo层的正向传播过程，首先应该弄懂作者是如何保存特征图的。 我放了一张图，可以参
java使用yolov2_yolo v2 源码分析（一）
weixin_32001071的博客
03-02 238
detector .c文件，这里仅分析train_detectorvoid train_detector(char *datacfg, char *cfgfile, char *weightfile, int *gpus, int ngpus, int clear){list *options = read_data_cfg(datacfg);char *train_images = option...
使用C++调用Yolo模型的方法与步骤
m0_61789994的博客
05-23 5153
Yolo算法是一种基于深度学习的目标检测算法，其主要思想是将目标检测任务转化为一个回归问题。相比于传统的两阶段目标检测方法，Yolo算法采用单阶段的检测流程，使得其在速度上有较大优势。Yolo算法将输入图像划分为一个固定大小的网格，并在每个网格上预测目标的边界框和类别。每个边界框由5个值来表示：边界框中心的坐标(x, y)、边界框的宽度和高度(w, h)，以及边界框中包含目标的置信度。通过在多个尺度上进行预测，结合非极大值抑制等后处理步骤，可以得到最终的目标检测结果。
yolo_face_detect.kmodel下载
10-13
yolo_face_detect.kmodel是一种用于人脸检测的深度学习模型，可以实现对图像或视频中人脸的快速定位和识别。下载yolo_face_detect.kmodel可以在项目中使用这个模型来进行人脸检测任务。 要下载yolo_face_detect.k...
评论 3
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值