I have marked a batch of data sets in xml format before, but I want to use other models to train the following, and then the model needs txt type tags, so I will convert the following code by myself! ! !
1. My folder directory
images: store original images
labels: store labels in xml format
labelstxt: Store labels converted into txt format
2.xml data format
3. Converted txt data format
4. Code
import os
import xml.etree.ElementTree as ET
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)
classes = ["0","1"] #标签名
def convert_annotation(fileName):
#in_file写入xml标签文件夹路径
in_file = open(r'C:\Users\Desktop\class\labels\\'+fileName,encoding='utf-8')
#out_file写入输出txt标签类型的存放文件夹位置
out_file = open(r'C:\Users\Desktop\class\labelstxt\\'+fileName[:-4]+'.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:
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')
if __name__ == '__main__':
#xml标签文件夹路径
files = os.listdir(r'C:\Users\Desktop\class\labels')
for item in files:
print(item)
convert_annotation(item)