VOC格式(.xml)标签转yolo格式(.txt)标签(含去除某一类别和xml中无size类的处理)

VOC格式(.xml)标签转yolo格式(.txt)标签(含去除某一类别和xml中无size类的处理)

.xml文件转.txt文件的时候,会遇到需要去除某一类别,或者.xml文件中没有size类的情况。以下代码可以解决上述问题。
自己根据情况改写 classes, drop_class, is_size, images, xml, txt这些输入即可

import xml.etree.ElementTree as ET
import pickle
import os
from tqdm import tqdm
from os import listdir, getcwd
from os.path import join
import cv2

classes = ["holothurian", "echinus", "scallop", "starfish","waterweeds"] ## .xml文件中的全部类别
drop_class=['waterweeds']## .xml文件转.txt文件,不需要转的类别
is_size=False ## .xml文件中是否有size选项
images = r" " ## 图片的路径,如果is_size=True的话,这个就可以忽略
xml=r' ' ## .xml文件的路径
txt=r' ' ## 需要保存.txt文件的路径
if not os.path.exists(txt):
    os.makedirs(txt)

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_id):

    in_file = open(os.path.join(xml,'%s.xml') % (image_id), encoding='utf-8')

    out_file = open(os.path.join(txt, '%s.txt') % (image_id),'w', encoding='utf-8')

    tree = ET.parse(in_file)

    root = tree.getroot()
    if is_size:

        size = root.find('size')

        w = int(size.find('width').text)

        h = int(size.find('height').text)
    else:
        img = cv2.imread(images + "/" + image_id + '.jpg')
        w = int(img.shape[1])
        h = int(img.shape[0])


    for obj in root.iter('object'):
        cls = obj.find('name').text
        if cls in drop_class:
            pass
        else:
            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')

if __name__ == '__main__':
    ids123=os.listdir(xml)
    image_ids=[i[:-4] for i in ids123]
    for image_id in tqdm(image_ids):
        convert_annotation(image_id)


你可能感兴趣的:(目标检测,xml,计算机视觉)