数据格式转换（labelme、labelimg、yolo格式相互转换）

‍个人简介： 深度学习图像领域工作者
总结链接：
             链接中主要是个人工作的总结，每个链接都是一些常用demo，代码直接复制运行即可。包括：
                    1.工作中常用深度学习脚本
                    2.torch、numpy等常用函数详解
                    3.opencv 图片、视频等操作
                    4.个人工作中的项目总结（纯干活）
              链接： https://blog.csdn.net/qq_28949847/article/details/128552785
视频讲解： 以上记录，通过B站等平台进行了视频讲解使用，可搜索 ‘Python图像识别’ 进行观看
              B站：Python图像识别
              抖音：Python图像识别
              西瓜视频：Python图像识别

---

1. 目标检测矩形框转换

（1）labelme标注的数据json文件转为labelimg格式的xml文件

目前只能支持 json中 ‘rectangle’ 和 ‘polygon’ 两种模式的转换，其中 ‘polygon’ 的转换方式为，替换成最小外接矩形的左上角和右下角坐标。

输入：由labelme的rectangle或这polygon方式标注生成的json文件；

输出：类似于labelImg的rectangle方式标注生成的xml文件，是左上角和右下角的坐标。

个人只需修改相应的路径。

# -*- coding: utf-8 -*-
import numpy as np
import json
from lxml import etree
import os
from tqdm import tqdm


class ReadJson(object):
    '''
    读取json文件，获取相应的标签信息
    '''

    def __init__(self, json_path):
        self.json_data = json.load(open(json_path, encoding="utf-8"))
        self.filename = self.json_data['imagePath']
        self.width = self.json_data['imageWidth']
        self.height = self.json_data['imageHeight']

        self.coordis = []
        # 构建坐标
        self.process_shapes()

    def process_shapes(self):
        for single_shape in self.json_data['shapes']:
            if single_shape['shape_type'] == "rectangle":
                bbox_class = single_shape['label']
                xmin = single_shape['points'][0][0]
                ymin = single_shape['points'][0][1]
                xmax = single_shape['points'][1][0]
                ymax = single_shape['points'][1][1]
                self.coordis.append([xmin, ymin, xmax, ymax, bbox_class])
            elif single_shape['shape_type'] == 'polygon':
                bbox_class = single_shape['label']
                temp_points = single_shape['points']
                temp_points = np.array(temp_points)
                xmin, ymin = temp_points.min(axis=0)
                xmax, ymax = temp_points.max(axis=0)
                self.coordis.append([xmin, ymin, xmax, ymax, bbox_class])
            else:
                print("shape type error, shape_type not in ['rectangle', 'polygon']")

    def get_width_height(self):
        return self.width, self.height

    def get_filename(self):
        return self.filename

    def get_coordis(self):
        return self.coordis


class labelimg_Annotations_xml:
    def __init__(self, folder_name, filename, path, database="Unknown"):
        self.root = etree.Element("annotation")
        child1 = etree.SubElement(self.root, "folder")
        child1.text = folder_name
        child2 = etree.SubElement(self.root, "filename")
        child2.text = filename
        child3 = etree.SubElement(self.root, "path")
        child3.text = path
        child4 = etree.SubElement(self.root, "source")
        child5 = etree.SubElement(child4, "database")
        child5.text = database

    def set_size(self, width, height, channel):
        size = etree.SubElement(self.root, "size")
        widthn = etree.SubElement(size, "width")
        widthn.text = str(width)
        heightn = etree.SubElement(size, "height")
        heightn.text = str(height)
        channeln = etree.SubElement(size, "channel")
        channeln.text = str(channel)

    def set_segmented(self, seg_data=0):
        segmented = etree.SubElement(self.root, "segmented")
        segmented.text = str(seg_data)

    def set_object(self, label, x_min, y_min, x_max, y_max,
                   pose='Unspecified', truncated=0, difficult=0):
        object = etree.SubElement(self.root, "object")
        namen = etree.SubElement(object, "name")
        namen.text = label
        posen = etree.SubElement(object, "pose")
        posen.text = pose
        truncatedn = etree.SubElement(object, "truncated")
        truncatedn.text = str(truncated)
        difficultn = etree.SubElement(object, "difficult")
        difficultn.text = str(difficult)
        bndbox = etree.SubElement(object, "bndbox")
        xminn = etree.SubElement(bndbox, "xmin")
        xminn.text = str(x_min)
        yminn = etree.SubElement(bndbox, "ymin")
        yminn.text = str(y_min)
        xmaxn = etree.SubElement(bndbox, "xmax")
        xmaxn.text = str(x_max)
        ymaxn = etree.SubElement(bndbox, "ymax")
        ymaxn.text = str(y_max)

    def savefile(self, filename):
        tree = etree.ElementTree(self.root)
        tree.write(filename, pretty_print=True, xml_declaration=False, encoding='utf-8')


def json_transform_xml(json_path, xml_path):
    json_anno = ReadJson(json_path)
    width, height = json_anno.get_width_height()
    channel = 3
    filename = json_anno.get_filename()
    coordis = json_anno.get_coordis()

    anno = labelimg_Annotations_xml('JPEGImages', filename, 'JPEGImages')
    anno.set_size(width, height, channel)
    anno.set_segmented()
    for data in coordis:
        x_min, y_min, x_max, y_max, label = data
        anno.set_object(label, int(x_min), int(y_min), int(x_max), int(y_max))
    anno.savefile(xml_path)


if __name__ == "__main__":
    '''
        目前只能支持 json中 rectangle 和 polygon 两种模式的转换，其中 polygon 的转换方式为，替换成最小外接矩形的左上角和右下角坐标
    '''
    root_json_dir = r"C:\Users\JoelYang\Desktop\111111\bbox_20230417_gjx"
    # root_save_xml_dir = r"\\SHARE\public\Time_Plus\traindata\bbox\tiaoshui3m\20230418_zxl"
    root_save_xml_dir = root_json_dir
    for json_filename in tqdm(os.listdir(root_json_dir)):
        if not json_filename.endswith(".json"):
            continue
        json_path = os.path.join(root_json_dir, json_filename)
        save_xml_path = os.path.join(root_save_xml_dir, json_filename.replace(".json", ".xml"))
        json_transform_xml(json_path, save_xml_path)

效果如下图：

json文件：

xml文件：

（2）labelimg xml文件转 labelme json文件

import xml.etree.ElementTree as ET
import os
import json


def xml_transform_json(xml_path, file, save_path):
    print(os.path.join(xml_path, file))
    # 读取xml文件
    path_file_xml = os.path.join(xml_path, file)
    # 解析读取xml函数
    root = ET.parse(path_file_xml)
    folder = root.find('folder').text
    filename = root.find('filename').text
    path = root.find('path').text
    sz = root.find('size')
    width = int(sz[0].text)
    height = int(sz[1].text)

    # 构建json数据
    data = {}
    data['flags'] = {}
    data['version'] = "4.5.6"
    data["shapes"] = []
    for child in root.findall('object'):  # 找到图片中的所有框
        sub = child.find('bndbox')  # 找到框的标注值并进行读取
        xmin = float(sub[0].text)
        ymin = float(sub[1].text)
        xmax = float(sub[2].text)
        ymax = float(sub[3].text)
        points = [[xmin, ymin], [xmax, ymax]]
        itemData = {'points': []}
        itemData['points'].extend(points)
        name = child.find("name").text
        itemData["flag"] = {}
        itemData["group_id"] = None
        itemData["shape_type"] = "rectangle"
        itemData["label"] = name
        data["shapes"].append(itemData)
    data['imageWidth'] = width
    data['imageHeight'] = height
    data['imageData'] = None
    data['imagePath'] = filename

    filename, extension = os.path.splitext(file)
    jsonName = ".".join([filename, "json"])
    # 写入json
    json_path = os.path.join(save_path, jsonName)
    with open(json_path, "w") as f:
        json.dump(data, f)
    print(json_path, "加载入文件完成...")


if __name__ == '__main__':
    xml_path = r"C:\Users\JoelYang\Desktop\111111\bbox_20230417_gjx"
    # save_path = r"C:\Users\JoelYang\Desktop\111111\bbox_20230417_gjx"
    save_path = xml_path
    for root, dirs, files in os.walk(xml_path):
        for file in files:
            if not file.endswith(".xml"):
                continue
            xml_transform_json(root, file, save_path)

效果如下：

xml文件

转后的json文件

（3）VOC xml格式转yolo txt格式

import os
import xml.etree.ElementTree as ET

# VOC数据集路径
voc_ann_path = r"D:\lg\BaiduSyncdisk\project\person_code\project_self\chepai_OCR\data\traindata\xml"
voc_img_path = r"D:\lg\BaiduSyncdisk\project\person_code\project_self\chepai_OCR\data\traindata\VOC\images\train\images\train"
# YOLO数据集路径
yolo_out_path = r"D:\lg\BaiduSyncdisk\project\person_code\project_self\chepai_OCR\data\traindata\txt"
# VOC类别名称和对应的编号
classes = {"blue": 0, "green": 1}  # 根据实际情况修改
# 遍历VOC数据集文件夹
for filename in os.listdir(voc_ann_path):
    # 解析XML文件
    tree = ET.parse(os.path.join(voc_ann_path, filename))
    root = tree.getroot()
    # 获取图片尺寸
    size = root.find("size")
    width = int(size.find("width").text)
    height = int(size.find("height").text)
    # 创建YOLO标注文件
    yolo_filename = filename.replace(".xml", ".txt")
    yolo_file = open(os.path.join(yolo_out_path, yolo_filename), "w")
    # 遍历XML文件中的所有目标
    for obj in root.findall("object"):
        # 获取目标类别名称和边界框坐标
        name = obj.find("name").text
        xmin = int(obj.find("bndbox").find("xmin").text)
        ymin = int(obj.find("bndbox").find("ymin").text)
        xmax = int(obj.find("bndbox").find("xmax").text)
        ymax = int(obj.find("bndbox").find("ymax").text)
        # 计算边界框中心点坐标和宽高
        x = (xmin + xmax) / 2 / width
        y = (ymin + ymax) / 2 / height
        w = (xmax - xmin) / width
        h = (ymax - ymin) / height
        # 将目标写入YOLO标注文件
        class_id = classes[name]
        yolo_file.write(f"{class_id} {x} {y} {w} {h}\n")
    yolo_file.close()