XML和JSON格式转换成txt

XML如下这种：

• 转换代码

  import os
  import xml.etree.ElementTree as ET
  
  # xml文件存放目录(修改成自己的文件名)
  input_dir = r'C:\121\Annotations'
  
  # 输出txt文件目录（自己创建的文件夹）
  out_dir = r'C:\121\txt'
  
  class_list = []
  
  
  # 获取目录所有xml文件
  def file_name(input_dir):
      F = []
      for root, dirs, files in os.walk(input_dir):
  
          for file in files:
              # print file.decode('gbk')    #文件名中有中文字符时转码
              if os.path.splitext(file)[1] == '.xml':
                  t = os.path.splitext(file)[0]
                  F.append(t)  # 将所有的文件名添加到L列表中
      return F  # 返回L列表
  
  
  # 获取所有分类
  def get_class(filelist):
      for i in filelist:
          f_dir = input_dir + "\\" + i + ".xml"
          in_file = open(f_dir, encoding='UTF-8')
          filetree = ET.parse(in_file)
          in_file.close()
          root = filetree.getroot()
          for obj in root.iter('object'):
              cls = obj.find('name').text
              if cls not in class_list:
                  class_list.append(cls)
  
  
  def ConverCoordinate(imgshape, bbox):
      # 将xml像素坐标转换为txt归一化后的坐标
      xmin, xmax, ymin, ymax = bbox
      width = imgshape[0]
      height = imgshape[1]
      dw = 1. / width
      dh = 1. / height
      x = (xmin + xmax) / 2.0
      y = (ymin + ymax) / 2.0
      w = xmax - xmin
      h = ymax - ymin
  
      # 归一化
      x = x * dw
      y = y * dh
      w = w * dw
      h = h * dh
  
      return x, y, w, h
  
  
  def readxml(i):
      f_dir = input_dir + "\\" + i + ".xml"
  
      txtresult = ''
  
      outfile = open(f_dir, encoding='UTF-8')
      filetree = ET.parse(outfile)
      outfile.close()
      root = filetree.getroot()
  
      # 获取图片大小
      size = root.find('size')
      width = int(size.find('width').text)
      height = int(size.find('height').text)
      imgshape = (width, height)
  
      # 转化为yolov5的格式
      for obj in root.findall('object'):
          # 获取类别名
          obj_name = obj.find('name').text
  
          obj_id = class_list.index(obj_name)
          # 获取每个obj的bbox框的左上和右下坐标
          bbox = obj.find('bndbox')
          xmin = float(bbox.find('xmin').text)
          xmax = float(bbox.find('xmax').text)
          ymin = float(bbox.find('ymin').text)
          ymax = float(bbox.find('ymax').text)
          bbox_coor = (xmin, xmax, ymin, ymax)
  
          x, y, w, h = ConverCoordinate(imgshape, bbox_coor)
          txt = '{} {} {} {} {}\n'.format(obj_id, x, y, w, h)
          txtresult = txtresult + txt
  
      # print(txtresult)
      f = open(out_dir + "\\" + i + ".txt", 'a')
      f.write(txtresult)
      f.close()
  
  
  # 获取文件夹下的所有文件
  filelist = file_name(input_dir)
  
  # 获取所有分类
  get_class(filelist)
  
  # 打印class
  print(class_list)
  
  # xml转txt
  for i in filelist:
      readxml(i)
  
  # 在out_dir下生成一个class文件
  f = open(out_dir + "\\classes.txt", 'a')
  classresult = ''
  for i in class_list:
      classresult = classresult + i + "\n"
  f.write(classresult)
  f.close()
  

JSON格式一：

{“image”: “3591.jpg”, “annotations”: [{“label”: “boat”, “coordinates”: {“x”: 163.9615384615385, “y”: 76.0384615384616, “width”: 146.0, “height”: 23.0}}, {“label”: “boat”, “coordinates”: {“x”: 247.4615384615385, “y”: 38.538461538461604, “width”: 291.0, “height”: 52.0}}, {“label”: “boat”, “coordinates”: {“x”: 1756.9615384615386, “y”: 32.538461538461604, “width”: 136.0, “height”: 56.0}}]}]

• 对应的转换代码如下：

  import os
  import json
  
  # 指定包含 JSON 文件的文件夹路径
  folder_path = "C:/labels/json/"
  
  # 获取文件夹中所有 JSON 文件的文件名
  json_files = [f for f in os.listdir(folder_path) if f.endswith(".json")]
  
  for json_file in json_files:
      # 构建 JSON 文件的完整路径
      json_path = os.path.join(folder_path, json_file)
  
      # 读取 JSON 文件
      with open(json_path, "r") as file:
          data = json.load(file)
  
      # 提取注释信息
      annotations = data[0]['annotations']
  
      # 转换为文本格式
      annotations_str = ""
      for annotation in annotations:
          coordinates = annotation['coordinates']
          #设置输出的内容格式
          #annotation_str = f"label: {annotation['label']}, x: {coordinates['x']}, y: {coordinates['y']}, width: {coordinates['width']}, height: {coordinates['height']}\n"
          annotation_str = f"{'0'} {coordinates['x']} {coordinates['y']} {coordinates['width']} {coordinates['height']}\n"
          annotations_str += annotation_str
  
      # 构建文本文件的路径和文件名
      txt_file = os.path.splitext(json_file)[0] + ".txt"
      txt_path = os.path.join(folder_path, txt_file)
  
      # 保存注释信息为文本文件
      with open(txt_path, "w") as file:
          file.write(annotations_str)
  
  

  JSON格式二
  

• 转换代码

import json
import os

name2id = {'boat': 0}  # 标签名称


def convert(img_size, box):
    dw = 1. / (img_size[0])
    dh = 1. / (img_size[1])
    x = (box[0] + box[2]) / 2.0 - 1
    y = (box[1] + box[3]) / 2.0 - 1
    w = box[2] - box[0]
    h = box[3] - box[1]
    x = x * dw
    w = w * dw
    y = y * dh
    h = h * dh
    return (x, y, w, h)


def decode_json(json_floder_path, json_name):
    txt_name = 'C:/Users/labels/txt/' + json_name[0:-5] + '.txt'
    # txt文件夹的绝对路径
    txt_file = open(txt_name, 'w')

    json_path = os.path.join(json_floder_path, json_name)
    data = json.load(open(json_path, 'r', encoding='gb2312', errors='ignore'))

    img_w = data['imageWidth']
    img_h = data['imageHeight']

    for i in data['shapes']:

        label_name = i['label']
        if (i['shape_type'] == 'rectangle'):
            x1 = int(i['points'][0][0])
            y1 = int(i['points'][0][1])
            x2 = int(i['points'][1][0])
            y2 = int(i['points'][1][1])

            bb = (x1, y1, x2, y2)
            bbox = convert((img_w, img_h), bb)
            txt_file.write(str(name2id[label_name]) + " " + " ".join([str(a) for a in bbox]) + '\n')


if __name__ == "__main__":

    json_floder_path = 'C:/Users/labels/json/'
    # json文件夹的绝对路径
    json_names = os.listdir(json_floder_path)
    for json_name in json_names:
        decode_json(json_floder_path, json_name)