以前标注了一批数据集是xml格式的,但是想用其他模型训练以下,然后模型需要的是txt类型的标签,那就搞段代码自己转换以下吧!!!
1.我的文件夹目录
images:存放原始图片
labels:存放xml格式的标签
labelstxt:存放转换成txt格式的标签
2.xml数据格式
3.转换后的txt数据格式
4.上代码
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)