xml2txt 自用

最新推荐文章于 2023-08-08 08:52:15 发布

诩安

最新推荐文章于 2023-08-08 08:52:15 发布

阅读量162

点赞数 2

文章标签： python 开发语言

本文链接：https://blog.csdn.net/yihyun/article/details/126713412

版权

自用专栏收录该内容

6 篇文章 0 订阅

订阅专栏

本文介绍如何使用Python脚本将VOC格式的XML标签文件转换为YOLO所需的.txt文件，涉及XML解析、坐标转换及类别处理。主要步骤包括读取XML、获取尺寸信息、遍历对象并进行坐标变换和写入txt文件。

摘要由CSDN通过智能技术生成

xml2txt

格式转换

import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join


def convert(size, box):
    # size=(width, height)  b=(xmin, xmax, ymin, ymax)
    # x_center = (xmax+xmin)/2        y_center = (ymax+ymin)/2
    # x = x_center / width            y = y_center / height
    # w = (xmax-xmin) / width         h = (ymax-ymin) / height

    x_center = (box[0] + box[1]) / 2.0
    y_center = (box[2] + box[3]) / 2.0
    x = x_center / size[0]
    y = y_center / size[1]

    w = (box[1] - box[0]) / size[0]
    h = (box[3] - box[2]) / size[1]

    # print(x, y, w, h)
    return (x, y, w, h)


def convert_annotation(xml_files_path, save_txt_files_path, classes):
    xml_files = os.listdir(xml_files_path)
    # print(xml_files)
    for xml_name in xml_files:
        # print(xml_name)
        xml_file = os.path.join(xml_files_path, xml_name)
        out_txt_path = os.path.join(save_txt_files_path, xml_name.split('.')[0] + '.txt')
        out_txt_f = open(out_txt_path, 'w')
        tree = ET.parse(xml_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))
            # b=(xmin, xmax, ymin, ymax)
            # print(w, h, b)
            bb = convert((w, h), b)
            out_txt_f.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')


if __name__ == "__main__":
    # 把forklift_pallet的voc的xml标签文件转化为yolo的txt标签文件
    # 1、需要转化的类别
    classes = ['1','2','3','4','5','6']
    # 2、voc格式的xml标签文件路径
    xml_files1 = r'F:\your xml path'
 
    # 3、转化为yolo格式的txt标签文件存储路径
    save_txt_files1 = r'F:\save txt path'

    convert_annotation(xml_files1, save_txt_files1, classes)