电脑上的程序太多了,要逐步转移上传上来,以防丢失。
一、程序
import xml.etree.ElementTree as ET
import os
sets = []
classes = ["plaque"] ##修改为自己的类别
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(path, outpath):
in_file = open(path, encoding='utf-8')
out_file = open(outpath, 'w', encoding='utf-8') # 最后写入的文件,必须要执行这句,不然会报错
tree = ET.parse(in_file)
root = tree.getroot()
if root.find('size'):
size = root.find('size')
w = int(size.find('width').text) # 偶尔xml标记出错,width或height设置为0了
h = int(size.find('height').text) # 需要标记出来,便于单独处理
# 遍历目标obj
for obj in root.iter('object'):
# iter()方法可以递归遍历元素/树的所有子元素
difficult = obj.find('difficult').text
cls = obj.find('name').text
# 如果训练标签中的品种不在程序预定品种,或者difficult = 1,跳过此object
if cls not in classes or int(difficult) == 1:
continue
# 通过类别名称找到id
cls_id = classes.index(cls)
xmlbox = obj.find('bndbox')
# 获取对应的bndbox的数组 = ['xmin', 'xmax', 'ymin', 'ymax']
b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text),
float(xmlbox.find('ymax').text))
# 进行归一化操作
bb = convert((w, h), b)
# bb对应的是归一化后的(x,y,w,h)
out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
rootdir = 'C:/Users/CNXIGAO13/Desktop/CPR_labels' # xml文件目录
txtdir = 'C:/Users/CNXIGAO13/Desktop/txt' # 输出的txt文件目录
list = os.listdir(rootdir) # 列出文件夹下所有的目录与文件
for i in range(0, len(list)):
path = os.path.join(rootdir, list[i])
stem = list[i].split(".")[0]
# print(stem)
out_path = os.path.join(txtdir, stem + '.txt')
# print(out_path)
convert_annotation(path, out_path)