xml格式转yolo的txt格式

增加了对xml文件内容异常判断

假如xml文件，<size> <width>0</width> <height>0</height> <depth>3</depth> </size> ，代表图片的宽高都没有写入，可以读取图片的宽高进行填补，防止转换时报错
。

增加转换后txt文件的小数点后位数

像labelImg，labelme等标注工具标注的yolotxt文件，拉的框框小数点位数只有6位，所以添加该功能。

类似SCUT-HEAD-Dataset数据集的转换

SCUT-HEAD-Dataset数据集转换为yolo能识别的txt类型数据集。

以下是转换源码，需要opencv库，需要自行创建label文件夹

import xml.etree.ElementTree as ET
from os import listdir, getcwd
import glob
import cv2
 
# 类别名称，打开一个xml文件看
#
#  <object>
#    <name>person</name>
#    <pose>Unspecified</pose>
#    <truncated>0</truncated>
#    <difficult>0</difficult>
#    <bndbox>
#      <xmin>476</xmin>
#      <ymin>137</ymin>
#      <xmax>498</xmax>
#      <ymax>156</ymax>
#    </bndbox>
#  </object>

classes = ["person"] #<name>person</name>,中是啥填啥，多个用逗号隔开
 
def convert(size, box):
#新增对框框范围的判断，防止0作为被除数
    if size[0]==0:
        dw=size[0]
    else:
        dw = 1.0 / size[0]

    if size[1] == 0:
        dw = size[1]
    else:
        dh = 1.0 / 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)
    return ('%.6f'%x,'%.6f'%y,'%.6f'%w,'%.6f'%h)
 
def convert_annotation(image_name,image_path):
    print(f"Processing {image_name}")
    f = open('./Annotations/' + image_name[:-3] + 'xml', encoding="utf8") # xml文件存放文件夹路径
    out_file = open('./label/' + image_name[:-3] + 'txt', 'w')  # 存放转换后的txt文件路径，记得先创建label文件夹
    xml_text = f.read()
    root = ET.fromstring(xml_text)
    f.close()
    size = root.find('size')
    #填补图片高宽缺失
    img = cv2.imread(image_path)
    sz = img.shape

    w=int(sz[1])
    h=int(sz[0])
    # w = int(size.find('width').text)
    # h = int(size.find('height').text)
 
    for obj in root.iter('object'):
        cls = obj.find('name').text
        if cls not in classes:
            print(cls)
            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()
 
if __name__ == '__main__':
 
    for image_path in glob.glob("./JPEGImages/*.jpg"):  # 放图片的文件夹，自己图片什么类型，自行替换
        image_name = image_path.split('\\')[-1]
        convert_annotation(image_name,image_path)