61 lines
1.9 KiB
Python
61 lines
1.9 KiB
Python
|
import xml.etree.ElementTree as ET
|
||
|
|
|
||
|
|
import pickle
|
||
|
|
import os
|
||
|
|
from os import listdir, getcwd
|
||
|
|
from os.path import join
|
||
|
|
import glob
|
||
|
|
|
||
|
|
classes = ['crazing', 'inclusion', 'patches', 'pitted_surface', 'rolled-in_scale', 'scratches'] # xml文件中标记的种类
|
||
|
|
|
||
|
|
|
||
|
|
def convert(size, box):
|
||
|
|
dw = 1.0 / size[0]
|
||
|
|
dh = 1.0 / 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(image_name):
|
||
|
|
try:
|
||
|
|
in_file = open('../dataset/annotations/val/' + image_name[:-3] + 'xml', encoding='utf-8') # 原来的xml文件路径
|
||
|
|
except FileNotFoundError:
|
||
|
|
print(f"Warning: XML file for {image_name} not found, skipping.")
|
||
|
|
return
|
||
|
|
|
||
|
|
out_file = open('../dataset/labels/val/' + image_name[:-3] + 'txt', 'w', encoding='utf-8') # 转换后的txt文件存放路径
|
||
|
|
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)
|
||
|
|
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')
|
||
|
|
in_file.close()
|
||
|
|
out_file.close()
|
||
|
|
|
||
|
|
|
||
|
|
wd = getcwd()
|
||
|
|
|
||
|
|
if __name__ == '__main__':
|
||
|
|
|
||
|
|
for image_path in glob.glob("../dataset/images/val/*.jpg"): # xml对应的图片的路径
|
||
|
|
image_name = image_path.split('\\')[-1]
|
||
|
|
convert_annotation(image_name)
|