目标检测：xml格式转为txt格式（已验证）

1.确认你的目录格式

这里仅展示训练集目录，根据个人需求可设置val，test目录（问就是我懒~）

2.确认你的xml格式

<annotation>
<folder>images</folder>
<filename>vid_000021_frame0000007.jpg</filename>
<size>
<width>480</width>
<height>270</height>
<depth>3</depth>
</size>
<object>
<name>1</name>
<bndbox>
<xmin>373</xmin>
<ymin>241</ymin>
<xmax>408</xmax>
<ymax>270</ymax>
</bndbox>
</object>
<object>
<name>1</name>
<bndbox>
<xmin>444</xmin>
<ymin>222</ymin>
<xmax>480</xmax>
<ymax>269</ymax>
</bndbox>
</object>
</annotation>

3.运行xml2txt.py

需要修改的位置：main()方法
（1）修改root_path路径为你的文件目录
我这里是D:\StudyAPP\PyCharm2023\Projects\PreData\data2---->改成你的文件目录咯
（2）修改name_list数组为你的classes信息
[‘1’, ‘2’, ‘3’, ‘4’, ‘5’, ‘6’]—>该成你的标签哈，[‘car’, ‘person’] 等等
（3）如果还需要转val和test的同学
改成 flags = [‘train’，‘val’ ] 就行~
运行完会在目录下生成新的labels目录，里面就是yolo格式的txt！！！
如下所示：

import os
from tqdm import tqdm
from lxml import etree


def parse_xml_to_dict(xml):
    """
    将xml文件解析成字典形式，参考tensorflow的recursive_parse_xml_to_dict
    Args：
        xml: xml tree obtained by parsing XML file contents using lxml.etree

    Returns:
        Python dictionary holding XML contents.
    """

    if len(xml) == 0:  # 遍历到底层，直接返回tag对应的信息
        return {xml.tag: xml.text}

    result = {}
    for child in xml:
        child_result = parse_xml_to_dict(child)  # 递归遍历标签信息
        if child.tag != 'object':
            result[child.tag] = child_result[child.tag]
        else:
            if child.tag not in result:  # 因为object可能有多个，所以需要放入列表里
                result[child.tag] = []
            result[child.tag].append(child_result[child.tag])
    return {xml.tag: result}


def translate_info(file_names: list, save_root: str, class_dict: dict, flag: str):
    """
    将对应xml文件信息转为yolo中使用的txt文件信息
    :param flag:
    :param file_names:
    :param save_root:
    :param class_dict:
    :return:
    """
    save_txt_path = os.path.join(save_root, "labels")
    if os.path.exists(save_txt_path) is False:
        os.makedirs(save_txt_path)
    voc_images_path = os.path.join(save_root, "images")
    voc_xml_path = os.path.join(save_root, "xmls")
    for file in tqdm(file_names, desc="translate {} file...".format(flag)):
        # 检查下图像文件是否存在
        img_path = os.path.join(voc_images_path, file + ".jpg")
        assert os.path.exists(img_path), "file:{} not exist...".format(img_path)

        # 检查xml文件是否存在
        xml_path = os.path.join(voc_xml_path, file + ".xml")
        assert os.path.exists(xml_path), "file:{} not exist...".format(xml_path)

        # read xml
        with open(xml_path) as fid:
            xml_str = fid.read()
        xml = etree.fromstring(xml_str)
        data = parse_xml_to_dict(xml)["annotation"]
        img_height = int(data["size"]["height"])
        img_width = int(data["size"]["width"])

        # write object info into txt
        assert "object" in data.keys(), "file: '{}' lack of object key.".format(xml_path)
        if len(data["object"]) == 0:
            # 如果xml文件中没有目标就直接忽略该样本
            print("Warning: in '{}' xml, there are no objects.".format(xml_path))
            continue

        with open(os.path.join(save_txt_path, file + ".txt"), "w") as f:
            for index, obj in enumerate(data["object"]):
                # 获取每个object的box信息
                xmin = float(obj["bndbox"]["xmin"])
                xmax = float(obj["bndbox"]["xmax"])
                ymin = float(obj["bndbox"]["ymin"])
                ymax = float(obj["bndbox"]["ymax"])
                class_name = obj["name"]
                class_index = class_dict[class_name]  # 目标id从0开始

                # 进一步检查数据，有的标注信息中可能有w或h为0的情况，这样的数据会导致计算回归loss为nan
                if xmax <= xmin or ymax <= ymin:
                    print("Warning: in '{}' xml, there are some bbox w/h <=0".format(xml_path))
                    continue

                # 将box信息转换到yolo格式
                xcenter = xmin + (xmax - xmin) / 2
                ycenter = ymin + (ymax - ymin) / 2
                w = xmax - xmin
                h = ymax - ymin

                # 绝对坐标转相对坐标，保存6位小数
                xcenter = round(xcenter / img_width, 6)
                ycenter = round(ycenter / img_height, 6)
                w = round(w / img_width, 6)
                h = round(h / img_height, 6)

                info = [str(i) for i in [class_index, xcenter, ycenter, w, h]]

                if index == 0:
                    f.write(" ".join(info))
                else:
                    f.write("\n" + " ".join(info))


def main():
    """
    修改root_path和name_list即可
    """
    root_path = r"D:\StudyAPP\PyCharm2023\Projects\PreData\data2"
    flags = ['train']
    name_list = ['1', '2', '3', '4', '5', '6', '7',
                 '8', '9', '10', '11', '12', '13', '14',
                 '15', '16']

    for flag in flags:
        voc_root = os.path.join(root_path, flag)
        class_dict = dict(zip(name_list, range(0, len(name_list))))
        xml_path = os.path.join(voc_root, "xmls")
        file_names = [line.split('.')[0] for line in os.listdir(xml_path)]

        translate_info(file_names, voc_root, class_dict, flag)


if __name__ == "__main__":
    main()