1. 批量移除xml标注中的某一个类别标签
# 批量移除xml标注中的某一个类别标签
import xml.etree.cElementTree as ET
import os# xml文件路径
xml_path = r'./Annotations'
xml_files = os.listdir(xml_path)
# 需要删除的类别名称
CLASSES = ["person"]for axml in xml_files:path_xml = os.path.join(xml_path, axml)tree = ET.parse(path_xml)root = tree.getroot()for child in root.findall('object'):name = child.find('name').textif name in CLASSES:root.remove(child)tree.write(os.path.join(xml_path, axml))# import xml.etree.cElementTree as ET
# import os
# import shutil
# import logging# # 配置日志
# logging.basicConfig(filename='xml_process.log', level=logging.INFO,
# format='%(asctime)s - %(levelname)s - %(message)s')# def process_xml(xml_path, classes_to_remove):
# backup_path = os.path.join(xml_path, '_backup')
# os.makedirs(backup_path, exist_ok=True)# for filename in os.listdir(xml_path):
# if not filename.endswith('.xml'):
# continue# src_path = os.path.join(xml_path, filename)
# dest_path = os.path.join(backup_path, filename)# try:
# # 备份原始文件
# shutil.copy2(src_path, dest_path)
# logging.info(f"已备份文件: {filename}")# # 解析XML
# tree = ET.parse(src_path, parser=ET.XMLParser(encoding='utf-8'))
# root = tree.getroot()# # 查找并删除目标节点
# removed_count = 0
# for obj in root.findall('.//{*}object'): # 处理命名空间
# name_elem = obj.find('.//{*}name')
# if name_elem is not None and name_elem.text.lower() in [c.lower() for c in classes_to_remove]:
# root.remove(obj)
# removed_count += 1# # 保存修改
# tree.write(src_path, encoding='utf-8', xml_declaration=True)
# logging.info(f"已处理文件: {filename}, 删除 {removed_count} 个标注")# except ET.ParseError as e:
# logging.error(f"XML解析错误 {filename}: {str(e)}")
# except Exception as e:
# logging.error(f"处理文件 {filename} 时发生错误: {str(e)}")# if __name__ == "__main__":
# xml_folder = r'./Annotations'
# target_classes = ["person"]
# process_xml(xml_folder, target_classes)
# print("批量处理完成，请检查日志文件 xml_process.log")2. 修改标签的label名字
"""
使用python xml解析树解析xml文件，批量修改xml文件里object节点下name节点的text
"""import glob
import xml.etree.ElementTree as ET
path = r'./Annotations' # xml文件夹路径
i = 0
for xml_file in glob.glob(path + '/*.xml'):# print(xml_file)tree = ET.parse(xml_file) obj_list = tree.getroot().findall('object') for per_obj in obj_list:if per_obj[0].text == 'dangerous-behavior': # 找到错误的标签“ dangerous-behavior ”per_obj[0].text = 'climbing' # 修改成“自己想要的标签名”i = i+1tree.write(xml_file) # 将改好的文件重新写入，会覆盖原文件
print('共完成了{}处替换'.format(i))
3. 划分YOLOv11数据集
# 该代码用于划分yolov11数据集
import os
import shutil
import random# random.seed(0) #随机种子，可自选开启
def split_data(file_path, label_path, new_file_path, train_rate, val_rate, test_rate):images = os.listdir(file_path)labels = os.listdir(label_path)images_no_ext = {os.path.splitext(image)[0]: image for image in images}labels_no_ext = {os.path.splitext(label)[0]: label for label in labels}matched_data = [(img, images_no_ext[img], labels_no_ext[img]) for img in images_no_ext if img in labels_no_ext]unmatched_images = [img for img in images_no_ext if img not in labels_no_ext]unmatched_labels = [label for label in labels_no_ext if label not in images_no_ext]if unmatched_images:print("未匹配的图片文件:")for img in unmatched_images:print(images_no_ext[img])if unmatched_labels:print("未匹配的标签文件:")for label in unmatched_labels:print(labels_no_ext[label])random.shuffle(matched_data)total = len(matched_data)train_data = matched_data[:int(train_rate * total)]val_data = matched_data[int(train_rate * total):int((train_rate + val_rate) * total)]test_data = matched_data[int((train_rate + val_rate) * total):]# 处理训练集for img_name, img_file, label_file in train_data:old_img_path = os.path.join(file_path, img_file)old_label_path = os.path.join(label_path, label_file)new_img_dir = os.path.join(new_file_path, 'train', 'images')new_label_dir = os.path.join(new_file_path, 'train', 'labels')os.makedirs(new_img_dir, exist_ok=True)os.makedirs(new_label_dir, exist_ok=True)shutil.copy(old_img_path, os.path.join(new_img_dir, img_file))shutil.copy(old_label_path, os.path.join(new_label_dir, label_file))# 处理验证集for img_name, img_file, label_file in val_data:old_img_path = os.path.join(file_path, img_file)old_label_path = os.path.join(label_path, label_file)new_img_dir = os.path.join(new_file_path, 'val', 'images')new_label_dir = os.path.join(new_file_path, 'val', 'labels')os.makedirs(new_img_dir, exist_ok=True)os.makedirs(new_label_dir, exist_ok=True)shutil.copy(old_img_path, os.path.join(new_img_dir, img_file))shutil.copy(old_label_path, os.path.join(new_label_dir, label_file))# 处理测试集for img_name, img_file, label_file in test_data:old_img_path = os.path.join(file_path, img_file)old_label_path = os.path.join(label_path, label_file)new_img_dir = os.path.join(new_file_path, 'test', 'images')new_label_dir = os.path.join(new_file_path, 'test', 'labels')os.makedirs(new_img_dir, exist_ok=True)os.makedirs(new_label_dir, exist_ok=True)shutil.copy(old_img_path, os.path.join(new_img_dir, img_file))shutil.copy(old_label_path, os.path.join(new_label_dir, label_file))print("数据集已划分完成")if __name__ == '__main__':file_path = r"./data/JPEGImages" # 图片文件夹label_path = r'./data/labels' # 标签文件夹new_file_path = r"./VOCdevkit" # 新数据存放位置split_data(file_path, label_path, new_file_path, train_rate=0.8, val_rate=0.1, test_rate=0.1)本文代码皆来自于CSDN博主，本文是为了方便自己使用做了汇总，参考：
笑脸惹桃花-CSDN博客
voc xml标签批量修改，更改、删除指定类别-CSDN博客
python批量修改labelme标注的json文件中的标签名_labelme批量修改标签-CSDN博客
