我的目标文件夹设置如下：

新建一个python文件hf.py,Annotations存放标注好的xml后缀的文件，images存放自己要训练的数据集，hf_txt
存放划分好的txt文件。

# -*- coding: utf-8 -*-
import os
import random
trainval_percent = 0.7
train_percent = 0.7
xmlfilepath = 'Annotations'
txtsavepath = 'images'
total_xml = os.listdir(xmlfilepath)
num = len(total_xml)
list = range(num)
tv = int(num * trainval_percent)
tr = int(tv * train_percent)
trainval = random.sample(list, tv)
train = random.sample(trainval, tr)
ftrainval = open('hf_txt/trainval.txt', 'w')
ftest = open('hf_txt/test.txt', 'w')
ftrain = open('hf_txt/train.txt', 'w')
fval = open('hf_txt/val.txt', 'w')
for i in list:
    name = total_xml[i][:-4] + '\n'
    if i in trainval:
        ftrainval.write(name)
        if i in train:
            ftrain.write(name)
        else:
            fval.write(name)
    else:
        ftest.write(name)
ftrainval.close()
ftrain.close()
fval.close()
ftest.close()

运行该脚本，将得到

里面存放的是不带后缀名的图片名，随机按比例划分的
划分好之后，再转化为YOLO格式的txt文件转化脚本如下：

# -*- coding: utf-8 -*-

import xml.etree.ElementTree as ET
import os
from os import getcwd

sets = ['train', 'val', 'test']
classes = ["yu"]#自己数据集的类别名，说多少写多少，不能有遗漏
abs_path = os.getcwd()

#归一化操作
def convert(size, box):
    dw = 1. / (size[0])
    dh = 1. / (size[1])
    x = (box[0] + box[1]) / 2.0 - 1
    y = (box[2] + box[3]) / 2.0 - 1
    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(image_id):
    in_file = open('Annotations/%s.xml' % (image_id),encoding='utf-8')
    out_file = open('labels/%s.txt' % (image_id), 'w',encoding='utf-8')
    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))
        b1, b2, b3, b4 = b
        # 标注越界修正
        if b2 > w:
            b2 = w
        if b4 > h:
            b4 = h
        b = (b1, b2, b3, b4)
        bb = convert((w, h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')


wd = getcwd()
for image_set in sets:
    if not os.path.exists('labels/'):
        os.makedirs('labels/')
    image_ids = open('hf_txt/%s.txt' % (image_set)).read().strip().split()
    list_file = open('%s.txt' % (image_set), 'w')
    for image_id in image_ids:
        list_file.write(abs_path + '/images/%s.png\n' % (image_id))#注意自己数据集的后缀名是png还是jpg
        convert_annotation(image_id)
    list_file.close()