labelimg标注格式转labelme标注格式，并读取imageData信息

在用CenterNet模型训练自己的数据集时，发现需要coco数据集格式，即需要labelme标注得到的json文件，但由于我是使用labelimg进行标注，所以只有xml文件。

于是开始寻找脚本进行转换，但发现网上的都没有办法读取imageData信息，得到json文件如下。

{
    "version": "3.16.2",
    "flags": {},
    "shapes": [
        {
            "label": "test class",
            "points": [
                [
                    631.0,
                    275.0
                ],
                [
                    714.0,
                    509.0
                ]
            ],
            "group_id": null,
            "shape_type": "rectangle",
            "flags": {}
        }
    ],
    "imagePath": "000000000000.jpg",
    "imageData": null,
    "imageHeight": 800,
    "imageWidth": 800
}

imageData的值为null，于是我开始找labelme读取图片信息时是怎么读取imageData的。最后找到了这篇。

https://blog.csdn.net/nodototao/article/details/123800645?spm=1001.2101.3001.6650.2&utm_medium=distribute.pc_relevant.none-task-blog-2%7Edefault%7ECTRLIST%7Edefault-2.pc_relevant_default&depth_1-utm_source=distribute.pc_relevant.none-task-blog-2%7Edefault%7ECTRLIST%7Edefault-2.pc_relevant_default&utm_relevant_index=5https://blog.csdn.net/nodototao/article/details/123800645?spm=1001.2101.3001.6650.2&utm_medium=distribute.pc_relevant.none-task-blog-2%7Edefault%7ECTRLIST%7Edefault-2.pc_relevant_default&depth_1-utm_source=distribute.pc_relevant.none-task-blog-2%7Edefault%7ECTRLIST%7Edefault-2.pc_relevant_default&utm_relevant_index=5然后我将代码改了改，变成下面的代码。

# --- utf-8 ---
# --- function: 将Labeling标注的格式转化为Labelme标注格式，并读取imageData ---

import os
import glob
import shutil
import xml.etree.ElementTree as ET
import json
from base64 import b64encode
from json import dumps



def get(root, name):
    return root.findall(name)


# 检查读取xml文件是否出错
def get_and_check(root, name, length):
    vars = root.findall(name)
    if len(vars) == 0:
        raise NotImplementedError('Can not fing %s in %s.' % (name, root.tag))
    if length > 0 and len(vars) != length:
        raise NotImplementedError('The size of %s is supposed to be %d, but is %d.' % (name, length, len(vars)))
    if length == 1:
        vars = vars[0]
    return vars



def convert(xml_file, json_file, save_dir, name, data):
    # 定义通过Labelme标注后生成的json文件
    json_dict = {"version": "3.16.2", "flags": {}, "shapes": [], "imagePath": "", "imageData": None,
                 "imageHeight": 0, "imageWidth": 0}

    # img_name = xml_file.split('.')[0]
    img_path = name + '.jpg'

    json_dict["imagePath"] = img_path

    tree = ET.parse(xml_file)  # 读取xml文件

    root = tree.getroot()

    size = get_and_check(root, 'size', 1)  # 读取xml中<>size<>字段中的内容

    # 读取二进制图片，获得原始字节码
    with open(data, 'rb') as jpg_file:
        byte_content = jpg_file.read()

    # 把原始字节码编码成base64字节码
    base64_bytes = b64encode(byte_content)

    # 把base64字节码解码成utf-8格式的字符串
    base64_string = base64_bytes.decode('utf-8')

    # 用字典的形式保存数据


    json_dict["imageData"] = base64_string

    # 获取图片的长宽信息
    width = int(get_and_check(size, 'width', 1).text)
    height = int(get_and_check(size, 'height', 1).text)

    json_dict["imageHeight"] = height
    json_dict["imageWidth"] = width

    # 当标注中有多个目标时全部读取出来
    for obj in get(root, 'object'):
        # 定义图片的标注信息
        img_mark_inf = {"label": "", "points": [], "group_id": None, "shape_type": "rectangle", "flags": {}}

        category = get_and_check(obj, 'name', 1).text  # 读取当前目标的类别

        img_mark_inf["label"] = category

        bndbox = get_and_check(obj, 'bndbox', 1)  # 获取标注宽信息

        xmin = float(get_and_check(bndbox, 'xmin', 1).text)
        ymin = float(get_and_check(bndbox, 'ymin', 1).text)
        xmax = float(get_and_check(bndbox, 'xmax', 1).text)
        ymax = float(get_and_check(bndbox, 'ymax', 1).text)

        img_mark_inf["points"].append([xmin, ymin])
        img_mark_inf["points"].append([xmax, ymax])
        # print(img_mark_inf["points"])

        json_dict["shapes"].append(img_mark_inf)

    # print("{}".format(json_dict))
    save = save_dir + json_file  # json文件的路径地址

    json_fp = open(save, 'w')  #
    json_str = json.dumps(json_dict, indent=4)  # 缩进，不需要的可以将indent=4去掉

    json_fp.write(json_str)  # 保存
    json_fp.close()


    # print("{}, {}".format(width, height))


def do_transformation(xml_dir, save_path):
    cnt = 0
    for fname in os.listdir(xml_dir):
        name = fname.split(".")[0]  # 获取图片名字

        path = os.path.join(xml_dir, fname)  # 文件路径

        save_json_name = name + '.json'

        data = img + name + '.jpg'  # xml文件对应的图片路径

        convert(path, save_json_name, save_path, name, data)

        cnt += 1


if __name__ == '__main__':
    img = "D:/test/VOCdevkit/VOC2007/JPEGImages/"    # xml对应图片文件夹
    xml_path = "D:/test/VOCdevkit/VOC2007/Annotations"    # xml文件夹

    save_json_path = "D:/test/12345/"    # 存放json文件夹

    if not os.path.exists(save_json_path):
        os.makedirs(save_json_path)

    do_transformation(xml_path, save_json_path)
    # xml = "2007_000039.xml"
    # xjson = "2007_000039.json"

    # convert(xml, xjson)

最后就能将数据集在labelimg标注得到的xml文件转为labelme标注的json文件，且还读取到了imageData，大功告成。

<annotation>
	<folder>测试图片</folder>
	<filename>000000000000.jpg</filename>
	<path>D:\test\000000000000.jpg</path>
	<source>
		<database>Unknown</database>
	</source>
	<size>
		<width>800</width>
		<height>800</height>
		<depth>3</depth>
	</size>
	<segmented>0</segmented>
	<object>
		<name>test class</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>631</xmin>
			<ymin>275</ymin>
			<xmax>714</xmax>
			<ymax>509</ymax>
		</bndbox>
	</object>
</annotation>

{
    "version": "3.16.2",
    "flags": {},
    "shapes": [
        {
            "label": "test class",
            "points": [
                [
                    631.0,
                    275.0
                ],
                [
                    714.0,
                    509.0
                ]
            ],
            "group_id": null,
            "shape_type": "rectangle",
            "flags": {}
        }
    ],
    "imagePath": "000000000000.jpg",
    "imageData": "/9j/4AAQSkZJRgABAQAAAQABAAD/......",
    "imageHeight": 800,
    "imageWidth": 800
}

以上就是转换结果，imageData太长了就不在这显示了。

代码参考

https://blog.csdn.net/Xiao_ZhiJ/article/details/122918983https://blog.csdn.net/Xiao_ZhiJ/article/details/122918983https://blog.csdn.net/nodototao/article/details/123800645?spm=1001.2101.3001.6650.2&utm_medium=distribute.pc_relevant.none-task-blog-2~default~CTRLIST~default-2.pc_relevant_default&depth_1-utm_source=distribute.pc_relevant.none-task-blog-2~default~CTRLIST~default-2.pc_relevant_default&utm_relevant_index=5https://blog.csdn.net/nodototao/article/details/123800645?spm=1001.2101.3001.6650.2&utm_medium=distribute.pc_relevant.none-task-blog-2~default~CTRLIST~default-2.pc_relevant_default&depth_1-utm_source=distribute.pc_relevant.none-task-blog-2~default~CTRLIST~default-2.pc_relevant_default&utm_relevant_index=5