（日常搬砖）voc(xml)格式的标注转换为coco（json）格式

目前手里的数据集都是xml的标注格式，无法直接在detectron2中作对比试验。
detectron2官方文档给出了自定义数据集的注册方案，需先将其转换为coco的.json格式。
爬了很多坑，找了很多代码，终于找到了能用的。
开整！！
代码如下：

import os
import argparse
import json
import xml.etree.ElementTree as ET
from typing import Dict, List
from tqdm import tqdm
import re


def get_label2id(labels_path: str) -> Dict[str, int]:
    """id is 1 start"""
    with open(labels_path, 'r') as f:
        labels_str = f.read().split()
    labels_ids = list(range(1, len(labels_str)+1))
    return dict(zip(labels_str, labels_ids))


def get_annpaths(ann_dir_path: str = None,
                 ann_ids_path: str = None,
                 ext: str = '',
                 annpaths_list_path: str = None) -> List[str]:
    # If use annotation paths list
    if annpaths_list_path is not None:
        with open(annpaths_list_path, 'r') as f:
            ann_paths = f.read().split()
        return ann_paths

    # If use annotaion ids list
    ext_with_dot = '.' + ext if ext != '' else ''
    with open(ann_ids_path, 'r') as f:
        ann_ids = f.read().split()
    ann_paths = [os.path.join(ann_dir_path, aid+ext_with_dot) for aid in ann_ids]
    return ann_p