COCO数据集格式---XML转txt格式脚本

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',"pitter_surface","rolled-in_scale","scratches"]

def convert(size,box):
    dw=1./size[0]
    dh=1./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(r'C:\Users\xy\Desktop\netdet\NEU-DET\ANNOTATIONS\\'+image_name[:-3]+'xml')#读取xml文件
    out_file=open(r'C:\Users\xy\Desktop\netdet\NEU-DET\LABELS\\'+image_name[:-3]+'txt','w')
    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'):
        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((r"C:\Users\xy\Desktop\netdet\NEU-DET\IMAGES\*.jpg")):
        print('done')
        image_name=image_path.split('\\')[-1]
        convert_annotation(image_name)
        print('done')