xml2txt

-*- coding: utf-8 -*-

import xml.etree.ElementTree as ET

import os

from os import getcwd

sets = 'train', 'val', 'test'

classes = "person" # 改成自己的类别

abs_path = os.getcwd()

print(abs_path)

def convert(size, box):

dw = 1. / (size0)

dh = 1. / (size1)

x = (box0 + box1) / 2.0 - 1

y = (box2 + box3) / 2.0 - 1

w = box1 - box0

h = box3 - box2

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('data_prov2/xml/train/%s.xml' % (image_id), encoding='UTF-8')

out_file = open('data_prov2/labels/train/%s.txt' % (image_id), '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

difficult = obj.find('difficult').text

cls = obj.find('name').text

if cls not in classes or int(difficult) == 1:

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))

b1, b2, b3, b4 = b

标注越界修正

if b2 > w:

b2 = w

if b4 > h:

b4 = h

b = (b1, b2, b3, b4)

bb = convert((w, h), b)

out_file.write(str(cls_id) + " " + " ".join(str(a) for a in bb) + '\n')

for image_set in sets:

if not os.path.exists('data_prov2/labels/train/'):

os.makedirs('data_prov2/labels/train/')

image_ids = open('data_prov2/dataSet/%s.txt' % (image_set)).read().strip().split()

list_file = open('data_prov2/%s.txt' % (image_set), 'w')

for image_id in image_ids:

list_file.write(abs_path + 'data_prov2/images/train/%s.jpg\n' % (image_id))

convert_annotation(image_id)

list_file.close()