Windows下使用Yolov3批量测试、结果保存、得到AP / MAP / recall

Windows下使用Yolov3批量测试、结果保存、得到AP / MAP / recall

 

1、用VS打开darknet的工程文件darknet.sln

 

2、找到detector.c进行修改

1）头文件添加

#include <sys/stat.h>
#include<stdio.h>
#include<time.h>
#include<sys/types.h>

2）GetFilename函数添加

char *GetFilename(char *p)
{
    static char name[20] = { "" };
    char *q = strrchr(p, '/') + 1;
    strncpy(name, q, 6);//注意后面的6，如果你的测试集的图片的名字字符（不包括后缀）是其他长度，请改为你需要的长度（官方的默认的长度是6）
    return name;
}

3）找到test_detector函数进行如下修改（约第1200+行）

在..\darknet-master\build\darknet\x64目录下新建test_pics文件夹存放测试后的图片结果

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, char *outfile)
{
    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, 1); // set batch=1
    if (weightfile) {
        load_weights(&net, weightfile);
    }
    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, i;
    float nms = .45;    // 0.4F
    if (filename) {
        strncpy(input, filename, 256);
        list *plist = get_paths(input);
        char **paths = (char **)list_to_array(plist);
        printf("Start Testing!\n");
        int m = plist->size;

        for (i = 0; i < m; ++i) {
            char *path = paths[i];
            image im = load_image(path, 0, 0, net.c);
            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];
            float *X = sized.data;
            double time = get_time_point();
            network_predict(net, X);
            printf("%s: Predicted in %lf milli-seconds.\n", input, ((double)get_time_point() - time) / 1000);
            printf("Try Very Hard:");
            printf("%s: Predicted in %lf milli-seconds.\n", path, ((double)get_time_point() - time) / 1000);
            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);
            draw_detections_v3(im, dets, nboxes, thresh, names, alphabet, l.classes, ext_output);

            char b[2048];
            sprintf(b, "test_pics/%s", GetFilename(path)); //图片保存的位置,或可用绝对路径“E:\\xxxxxx\\build\\darknet\\x64\\test_pics”
            save_image(im, b);
            printf("save %s successfully!\n", b);

            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);
        }
    }

    printf("All Done!\n");
    system("pause");
    exit(0);

    free_ptrs(names, net.layers[net.n - 1].classes);
    free_list_contents_kvp(options);
    free_list(options);

    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);
    printf("All Done!\n");
    system("pause");

}

4）右键darknet重新生成

 

3、批量测试并保存结果

在cmd中输入以下命令：

darknet.exe detector test data\voc.data yolov3-voc.cfg weights_result\yolov3-voc_10000.weights E:\xxxxxx\build\darknet\VOCdevkit\2007_test.txt

 其中“E:\xxxxxx\build\darknet\VOCdevkit\2007_test.txt”是测试文件路径，2007_test.txt打开为测试图片的绝对路径，如下：

运行结果如下：

 

4、得到AP / MAP / recall

1）得到AP / MAP，在cmd中输入以下命令：

darknet.exe detector map data\voc.data yolov3-voc.cfg weights_result\yolov3-voc_final.weights

运行结果如下：

2）得到recall，在cmd中输入以下命令：

darknet.exe detector recall data\voc.data yolov3-voc.cfg weights_result\yolov3-voc_final.weights

 运行结果如下：

 

5、参考：

Windows环境下yolov3+darknet批量处理图片

YOLOv3的批量图片检测以及批量输出（windows下）

YOLOv3批量测试图片并保存在自定义文件夹下