xml格式标签转为txt格式标签用于yolo目标检测
xml -> txt
# _*_ coding:utf-8 _*_
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
"""
未知类别名,xml -> txt
时间: 2022.03.11
作者:余小晖
"""
imgs_path = './car-dataset/imgs/' #图片路径
anns_path = './car-dataset/anns/' #xml标签路径
ann_save_path = './car-dataset/anns_txt/' #txt标签保存路径
classes_save_file = './car-dataset/classes.txt' #classes.txt保存路径
if not os.path.exists(ann_save_path):
os.makedirs(ann_save_path)
anns = os.listdir(anns_path)
classes = [] #空列表用于保存类别名
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(ann, totle_name):
# in_file = open('VOCdevkit/VOC%s/Annotations/%s.xml' % (year, image_id), encoding='UTF-8')
# out_file = open('VOCdevkit/VOC%s/labels/%s.txt' % (year, image_id), 'w')
in_file = open(anns_path+ann,'r')
out_file = open(ann_save_path+totle_name+'.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'):
difficult = obj.find('difficult').text
cls = obj.find('name').text
# print(count)
# if cls not in classes or int(difficult) == 1:
# continue
if cls not in classes :
classes.append(cls)
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()
num = 0
for ann in anns:
ann = ann.split('.')
totle_name = ann[0]
ann =str.join('.' ,ann)
convert_annotation(ann, totle_name)
num+=1
print('num----------------------------',num)
print('=============classes==============================')
for i, cls in enumerate(classes):
with open(classes_save_file, 'a')as f:
f.write(cls+ '\n')
print(i, cls)