将训练数据的图片和xml文件重新命名

   之前在做模型训练时，对图片数据进行处理：对训练的图片和xml文件重新命名为6位数前缀的名称（原始的可能有中文或者不符合使用习惯等），修改后的图片和xml格式如下：

                                                      
                                                   

   代码如下，需要将原始的图片和对应的xml文件分别放到images和labels文件夹中：
                                                           

from xml.etree.ElementTree import ElementTree
from os import walk, path
import cv2
import os


def read_xml(in_path):
    tree = ElementTree()
    tree.parse(in_path)
    return tree


def write_xml(tree, out_path):
    tree.write(out_path, encoding="utf-8", xml_declaration=True)

def get_path_prex(rootdir):
    data_path = []
    prefixs = []
    for root, dirs, files in walk(rootdir, topdown=True):
        for name in files:
            pre, ending = path.splitext(name)
            if ending != ".xml":
                continue
            else:
                data_path.append(path.join(root, name))
                prefixs.append(pre)

    return data_path, prefixs


if __name__ == "__main__":

    # build files which will be used in VOC2007
    if not os.path.exists("Annotations"):
        os.mkdir("Annotations")
    if not os.path.exists("JPEGImages"):
        os.mkdir("JPEGImages")

    xml_paths, prefixs = get_path_prex("labels")

    for i in range(len(xml_paths)):
        # rename and save the corresponding xml
        tree = read_xml(xml_paths[i])
        # save output xml, 000001.xml
        write_xml(tree, "Annotations/{}.xml".format("%06d" % (i + 1)))

        # rename and save the corresponding image
        img_pre = prefixs[i] + ".jpg"
        root = os.getcwd() + '/images/'
        img_path = path.join(root, img_pre)
        img = cv2.imread(img_path)
        # save output jpg, 000001.jpg
        cv2.imwrite('JPEGImages/{}.jpg'.format("%06d" % (i + 1)), img)

   运行后，会生成JPEGImages和Annotations文件夹， 对应VOC2007下的文件两个文件，分别为新命名的图片和xml文件，将得到的文件夹拷贝到VOC2007下覆盖即可。