import xml.etree.cElementTree as ET
import os
path_root = ['E:\data-VOC0712\VOC2007\Annotations',
'E:\data-VOC0712\VOC2012\Annotations']
CLASSES = [
"bottle",
"cat", "chair", "diningtable",
"dog", "motorbike", "person",
"pottedplant","sofa",
"tvmonitor"]
for anno_path in path_root:
xml_list = os.listdir(anno_path)
for axml in xml_list:
path_xml = os.path.join(anno_path, axml)
tree = ET.parse(path_xml)
root = tree.getroot()
for child in root.findall('object'):
name = child.find('name').text
if not name in CLASSES:
root.remove(child)
tree.write(os.path.join('E:\data-myVOC0712\Annotations', axml))