1、XML的格式

<annotation>
	<folder>cr</folder>
	<filename>crazing_2.jpg</filename>
	<source>
		<database>NEU-DET</database>
	</source>
	<size>
		<width>200</width>
		<height>200</height>
		<depth>1</depth>
	</size>
	<segmented>0</segmented>
	<object>
		<name>crazing</name>
		<pose>Unspecified</pose>
		<truncated>1</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>99</xmin>
			<ymin>120</ymin>
			<xmax>200</xmax>
			<ymax>174</ymax>
		</bndbox>
	</object>
	<object>
		<name>crazing</name>
		<pose>Unspecified</pose>
		<truncated>1</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>8</xmin>
			<ymin>16</ymin>
			<xmax>200</xmax>
			<ymax>111</ymax>
		</bndbox>
	</object>
</annotation>

我们来读一下这个xml文件核心内容

xmin ymin xmax ymax 这四个值代表了这个图像中的矩形框的位置并且给这个位置取名为crazing

举个例子一张有图片

我们用框框把狗框起来并且命名这个框为狗

计算机就知道这个地方有个狗

2、转化代码

import xml.etree.ElementTree as ET

import pickle
import os
from os import listdir, getcwd
from os.path import join
import glob

classes = ["crazing", "inclusion", "patches", "pitted_surface", "rolled-in_scale", "scratches"]


def convert(size, box):
    dw = 1.0 / size[0]
    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)


def convert_annotation(image_name):
    in_file = open('./Basic_data/indata/' + image_name[:-3] + 'xml')  # xml文件路径
    out_file = open('./Basic_data/labels/train/' + image_name[:-3] + 'txt', 'w')  # 转换后的txt文件存放路径
    f = open('./Basic_data/indata/' + image_name[:-3] + 'xml')
    xml_text = f.read()
    root = ET.fromstring(xml_text)
    f.close()
    size = root.find('size')
    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("datasets/Basic_data/IMAGES/*.jpg"):  # 每一张图片都对应一个xml文件这里写xml对应的图片的路径
        image_name = image_path.split('\\')[-1]
        convert_annotation(image_name)

代码中有注释，大家自己理解一下哈

再给大家看一下我的文件结构