参考）YOLOv2训练自己的数据集（voc格式）进行实验，基本上是正确的，但其初始给出的代码并非是在linux下可以运行的，因此参考部分博客写了下面的程序，可以实现对文件夹内图片的批量读取以及更改名称符合VOC数据集习惯。另原文有部分小错误，本文已经修改，但后文属于转载，版权属原作者所有，本文仅为记录和交流用。如下文所示。

1 准备数据

#include <dirent.h>
#include <sys/stat.h>
#include <unistd.h>
#include <stdio.h>
#include <string.h>
#include <opencv2/opencv.hpp>

#define img_num 2000
char img_file[img_num][1000];

int list_dir_name(char* dirname,int tabs)
{
    DIR* dp;
    struct dirent* dirp;
    struct stat st;
    char tab[tabs + 1];
		char img_count=0;

    /* open dirent directory */
    if((dp = opendir(dirname)) == NULL)
    {
        perror("opendir");
        return -1;
    }



    /* fill tab array with tabs */
    memset(tab,'\t',tabs);
    tab[tabs] = 0;

    /**
     * read all files in this dir
     **/
    while((dirp = readdir(dp)) != NULL)

    {
        char fullname[255];
        memset(fullname,sizeof(fullname));

        /* ignore hidden files */
        if(dirp->d_name[0] == '.')
            continue;

        /* display file name */
        //printf("img_name:%s\n",dirp->d_name);

        strncpy(fullname,dirname,sizeof(fullname));
        strncat(fullname,dirp->d_name,sizeof(fullname));
	    strcat(img_file[img_count++],fullname);				
	    printf("Image %3d path:%s\n",img_count-1,img_file[img_count-1]);//fullname=dir+file name,the absolute path of the image file        

				/* get dirent status */
        if(stat(fullname,&st) == -1)
        {
            perror("stat");
            fputs(fullname,stderr);
            return -1;
        }
        /* if dirent is a directory,call itself */
        if(S_ISDIR(st.st_mode) && list_dir_name(fullname,tabs + 1) == -1)
            return -1;
    }
    return img_count;

}

int main(int argc,char* argv[])
{
	char* dir="/home/robot/Downloads/mark_recognition/car_img/simple_3class/";
        printf("%s\n",dir);

        char sum=list_dir_name(dir,1);
	printf("Img total num:%d\n",sum);

	int i;
	char order[1000];

	char txt_path[1000];
	char* txt_name="train.txt";
	memset(txt_path,sizeof(txt_path));
	strcat(txt_path,dir);
	strcat(txt_path,txt_name);
	FILE *fp = fopen(txt_path,"w");

	for (i = 0; i<sum; ++i)
	{
		char img_path[1000];
		memset(img_path,sizeof(img_path));

		printf("Source %s\n",img_file[i]);
		IplImage *pSrc = cvLoadImage(img_file[i]);
		sprintf(order,"%05d.jpg",i);
		strcat(img_path,dir);
		strcat(img_path,order);
		cvSaveImage(img_path,pSrc);
		fprintf(fp,"%05d\n",i);
		
		printf("Save as%s\n",img_path);
		cvReleaseImage(&pSrc);
	}
	fclose(fp);

	

	return 0;
}

2 用YOLOv2训练

1.生成相关文件

import xml.etree.ElementTree as ET  
import pickle  
import os  
from os import listdir,getcwd  
from os.path import join  
  
#sets=[('2012','train'),('2012','val'),('2007','test')]  
  
#classes = ["aeroplane","bicycle","bird","boat","bottle","bus","car","cat","chair","cow","diningtable","dog","horse","motorbike","person","pottedplant","sheep","sofa","train","tvmonitor"]  
  
sets=[('2007','train')]  
classes = [ "person"]  
  
  
def convert(size,Box):  
    dw = 1./size[0]  
    dh = 1./size[1]  
    x = (Box[0] + Box[1])/2.0  
    y = (Box[2] + Box[3])/2.0  
    w = Box[1] - Box[0]  
    h = Box[3] - Box[2]  
    x = x*dw  
    w = w*dw  
    y = y*dh  
    h = h*dh  
    return (x,y,w,h)  
  
def convert_annotation(year,image_id):  
    in_file = open('VOCdevkit/VOC%s/Annotations/%s.xml'%(year,image_id))  #（如果使用的不是VOC而是自设置数据集名字，则这里需要修改）  
    out_file = open('VOCdevkit/VOC%s/labels/%s.txt'%(year,image_id),'w')  #（同上）  
    tree=ET.parse(in_file)  
    root = tree.getroot()  
    size = root.find('size')  
    w = int(size.find('width').text)  
    h = int(size.find('height').text)  
  
    for obj in root.iter('object'):  
        difficult = obj.find('difficult').text  
        cls = obj.find('name').text  
        if cls not in classes or int(difficult) == 1:  
            continue  
        cls_id = classes.index(cls)  
        xmlBox = obj.find('bndBox')  
        b = (float(xmlBox.find('xmin').text),float(xmlBox.find('xmax').text),float(xmlBox.find('ymin').text),float(xmlBox.find('ymax').text))  
        bb = convert((w,h),b)  
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')  
  
wd = getcwd()  
  
for year,image_set in sets:  
    if not os.path.exists('VOCdevkit/VOC%s/labels/'%(year)):  
        os.makedirs('VOCdevkit/VOC%s/labels/'%(year))  
    image_ids = open('VOCdevkit/VOC%s/ImageSets/Main/%s.txt'%(year,image_set)).read().strip().split()  
    list_file = open('%s_%s.txt'%(year,image_set),'w')  
    for image_id in image_ids:  
        list_file.write('%s/VOCdevkit/VOC%s/JPEGImages/%s.jpg\n'%(wd,year,image_id))  
        convert_annotation(year,image_id)  
    list_file.close()

.
1. .
2. .
3. [convolutional]
4. size=1
5. stride=1
6. pad=1
7. filters=30//修改最后一层卷积层核参数个数，计算公式是依旧自己数据的类别数filter=num×（classes+coords+1）=5×（1+4+1）=30
8. activation=linear
10. [region]
11. anchors=1.08,1.19,3.42,4.41,6.63,11.38,9.42,5.11,16.62,10.52
12. bias_match=1
13. classes=1//类别数，本例为1类
14. coords=4
15. num=5
16. softmax=1
17. jitter=.2
18. rescore=1
19. object_scale=5
20. noobject_scale=1
21. class_scale=1
22. coord_scale=1
24. absolute=1
25. thresh=.6
26. random=1