xml2yolo脚本

xml2yolo脚本

• yolo所对应的格式是.txt,其中包含框的类别索引，中心点坐标，boundingboxs的宽，高。

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./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)#中心点，宽，高

def convert_annotation(image_name):
    in_file = open('./ANNOTATIONS/'+image_name[:-3]+'xml')#读入每张图片对应的.xml
    out_file = open('./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')#把名字和bbx写入到.txt文件

wd = getcwd()

if __name__ == '__main__':
    for image_path in glob.glob("./IMAGES/*.jpg"):#读入图像数据名
        image_name = image_path.split('\\')[-1]#只取名字后缀
        #print(image_path)
        convert_annotation(image_name)#转换标签