-
Notifications
You must be signed in to change notification settings - Fork 0
/
XmlTransfromTxt.py
72 lines (61 loc) · 2.39 KB
/
XmlTransfromTxt.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
import xml.etree.ElementTree as ET
import os
from os import getcwd
import glob
# 1.
# 自己创建文件夹,例如:label_mal label_txt 也可以修改别的
image_set = 'datasets/tea/labels/val_xml_enhance_2' # 需要转换的文件夹名称(文件夹内放xml标签文件)
imageset2 = 'datasets/tea/labels/val_txt_enhance_2' # 保存txt的文件夹
# 2.
# 换成你的类别 当前的顺序,就txt 0,1,2,3 四个类别
classes = ['tea'] # 标注时的标签 注意顺序一定不要错。
# 3.
# # 转换文件夹的绝对路径
# data_dir = 'D:/detectAuto_/data'
# 或者 读取当前路径
data_dir = getcwd() # 当前路径
'''
xml中框的左上角坐标和右下角坐标(x1,y1,x2,y2)
》》txt中的中心点坐标和宽和高(x,y,w,h),并且归一化
'''
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(data_dir, imageset1, imageset2, image_id):
in_file = open(data_dir + '/%s/%s.xml' % (imageset1, image_id), encoding='UTF-8') # 读取xml
out_file = open(data_dir + '/%s/%s.txt' % (imageset2, image_id), 'w', encoding='UTF-8') # 保存txt
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
if cls not in classes or int(difficult) == 1:
continue
cls_id = classes.index(cls) # 获取类别索引
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('%.6f' % a) for a in bb]) + '\n')
image_ids = []
for x in glob.glob(data_dir + '/%s' % image_set + '/*.xml'):
image_ids.append(os.path.basename(x)[:-4])
print('\n%s数量:' % image_set, len(image_ids)) # 确认数量
i = 0
for image_id in image_ids:
i = i + 1
convert_annotation(data_dir, image_set, imageset2, image_id)
print("%s 数据:%s/%s文件完成!" % (image_set, i, len(image_ids)))
print("Done!!!")