标注文件格式转换：xml和json相互转化、xml和txt相互转化、txt和json相互转化

一、xml和json相互转化

1、xml转json

#coding:utf-8
import os
import glob
import json
import shutil
import numpy as np
import xml.etree.ElementTree as ET
# 项目根目录下放置data/coco文件夹，里面分别有annotations、train2017、val2017三个文件夹。
# 格式转化前要将xml和图片全部放入annotation文件夹中，train2017、val2017里面为空。
# 转换后生成的json文件会放在根目录下，要把annotations里面的图片和xml文件删除，并把两个json文件放进去，
# 并且转换后train2017、val2017里面分别为训练集和验证集对应图片。

path2 = "."
 
START_BOUNDING_BOX_ID = 1 
def get(root, name):
    return root.findall(name)

def get_and_check(root, name, length):
    vars = root.findall(name)
    if len(vars) == 0:
        raise NotImplementedError('Can not find %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_list, json_file):
    json_dict = {"images": [], "type": "instances", "annotations": [], "categories": []}
    categories = pre_define_categories.copy()
    bnd_id = START_BOUNDING_BOX_ID
    all_categories = {}
    for index, line in enumerate(xml_list):
        # print("Processing %s"%(line))
        xml_f = line
        tree = ET.parse(xml_f)
        root = tree.getroot()
        
        filename = os.path.basename(xml_f)[:-4] + ".jpg"
        image_id = 20190000001 + index
        size = get_and_check(root, 'size', 1)
        width = int(get_and_check(size, 'width', 1).text)
        height = int(get_and_check(size, 'height', 1).text)
        image = {'file_name': filename, 'height': height, 'width': width, 'id':image_id}
        json_dict['images'].append(image)
        ## Cruuently we do not support segmentation
        #  segmented = get_and_check(root, 'segmented', 1).text
        #  assert segmented == '0'
        for obj in get(root, 'object'):
            category = get_and_check(obj, 'name', 1).text
            if category in all_categories:
                all_categories[category] += 1
            else:
                all_categories[category] = 1
            if category not in categories:
                if only_care_pre_define_categories:
                    continue
                new_id = len(categories) + 1
                print("[warning] category '{}' not in 'pre_define_categories'({}), create new id: {} automatically".format(category, pre_define_categories, new_id))
                categories[category] = new_id
            category_id = categories[category]
            bndbox = get_and_check(obj, 'bndbox', 1)
            xmin = int(float(get_and_check(bndbox, 'xmin', 1).text))
            ymin = int(float(get_and_check(bndbox, 'ymin', 1).text))
            xmax = int(float(get_and_check(bndbox, 'xmax', 1).text))
            ymax = int(float(get_and_check(bndbox, 'ymax', 1).text))
            assert(xmax > xmin), "xmax <= xmin, {}".format(line)
            assert(ymax > ymin), "ymax <= ymin, {}".format(line)
            o_width = abs(xmax - xmin)
            o_height = abs(ymax - ymin)
            ann = {'area': o_width*o_height, 'iscrowd': 0, 'image_id':
                   image_id, 'bbox':[xmin, ymin, o_width, o_height],
                   'category_id': category_id, 'id': bnd_id, 'ignore': 0,
                   'segmentation': []}
            json_dict['annotations'].append(ann)
            bnd_id = bnd_id + 1
 
    for cate, cid in categories.items():
        cat = {'supercategory': 'none', 'id': cid, 'name': cate}
        json_dict['categories'].append(cat)
    json_fp = open(json_file, 'w')
    json_str = json.dumps(json_dict)
    json_fp.write(json_str)
    json_fp.close()
    print("------------create {} done--------------".format(json_file))
    print("find {} categories: {} -->>> your pre_define_categories {}: {}".format(len(all_categories), all_categories.keys(), len(pre_define_categories), pre_define_categories.keys()))
    print("category: id --> {}".format(categories))
    print(categories.keys())
    print(categories.values())
 
 
if __name__ == '__main__':
    classes = ['person']  #改为你需要检测的类别
    pre_define_categories = {}
    for i, cls in enumerate(classes):
        pre_define_categories[cls] = i + 1
    # pre_define_categories = {'a1': 1, 'a3': 2, 'a6': 3, 'a9': 4, "a10": 5}
    only_care_pre_define_categories = True
    # only_care_pre_define_categories = False
 
    train_ratio = 0.9
    save_json_train = 'instances_train2017.json'
    save_json_val = 'instances_val2017.json'
    xml_dir = "data/coco/annotations"
 
    xml_list = glob.glob(xml_dir + "/*.xml")
    xml_list = np.sort(xml_list)
    np.random.seed(100)
    np.random.shuffle(xml_list)
 
    train_num = int(len(xml_list)*train_ratio)
    xml_list_train = xml_list[:train_num]
    xml_list_val = xml_list[train_num:]
 
    convert(xml_list_train, save_json_train)
    convert(xml_list_val, save_json_val)
 
    if os.path.exists(path2 + "/annotations"):
        shutil.rmtree(path2 + "/annotations")
    os.makedirs(path2 + "/annotations")
    if os.path.exists(path2 + "/images/train2017"):
        shutil.rmtree(path2 + "/images/train2017")
    os.makedirs(path2 + "/images/train2017")
    if os.path.exists(path2 + "/images/val2017"):
        shutil.rmtree(path2 +"/images/val2017")
    os.makedirs(path2 + "/images/val2017")
 
    f1 = open("train.txt", "w")
    for xml in xml_list_train:
        img = xml[:-4] + ".jpg"
        f1.write(os.path.basename(xml)[:-4] + "\n")
        shutil.copyfile(img, path2 + "/data/coco/train2017/" + os.path.basename(img))
 
    f2 = open("val.txt", "w")
    for xml in xml_list_val:
        img = xml[:-4] + ".jpg"
        f2.write(os.path.basename(xml)[:-4] + "\n")
        shutil.copyfile(img, path2 + "/data/coco/val2017/" + os.path.basename(img))
    f1.close()
    f2.close()
    print("-------------------------------")
    print("train number:", len(xml_list_train))
    print("val number:", len(xml_list_val))

2、json转xml

# coco2voc.py

# pip install pycocotools
import os
import time
import json
import pandas as pd
from tqdm import tqdm
from pycocotools.coco import COCO
 
#json文件路径和用于存放xml文件的路径
anno = 'C:/Users/user/Desktop/val/instances_val2017.json'
xml_dir = 'C:/Users/user/Desktop/val/xml/'

coco = COCO(anno)  # 读文件
cats = coco.loadCats(coco.getCatIds())  # 这里loadCats就是coco提供的接口，获取类别
    
# Create anno dir
dttm = time.strftime("%Y%m%d%H%M%S", time.localtime())

def trans_id(category_id):
    names = []
    namesid = []
    for i in range(0, len(cats)):
        names.append(cats[i]['name'])
        namesid.append(cats[i]['id'])
    index = namesid.index(category_id)
    return index
    

def convert(anno,xml_dir): 

    with open(anno, 'r') as load_f:
        f = json.load(load_f)
    
    imgs = f['images']  #json文件的img_id和图片对应关系 imgs列表表示多少张图
    
    cat = f['categories']
    df_cate = pd.DataFrame(f['categories'])                     # json中的类别
    df_cate_sort = df_cate.sort_values(["id"], ascending=True)  # 按照类别id排序
    categories = list(df_cate_sort['name'])                     # 获取所有类别名称
    print('categories = ', categories)
    df_anno = pd.DataFrame(f['annotations'])                    # json中的annotation
    
    for i in tqdm(range(len(imgs))):  # 大循环是images所有图片,Tqdm是可扩展的Python进度条，可以在长循环中添加一个进度提示信息
        xml_content = []
        file_name = imgs[i]['file_name']    # 通过img_id找到图片的信息
        height = imgs[i]['height']
        img_id = imgs[i]['id']
        width = imgs[i]['width']
        
        version =['"1.0"','"utf-8"'] 
    
        # xml文件添加属性
        xml_content.append("<?xml version=" + version[0] +" "+ "encoding="+ version[1] + "?>")
        xml_content.append("<annotation>")
        xml_content.append("    <filename>" + file_name + "</filename>")
        xml_content.append("    <size>")
        xml_content.append("        <width>" + str(width) + "</width>")
        xml_content.append("        <height>" + str(height) + "</height>")
        xml_content.append("        <depth>"+ "3" + "</depth>")
        xml_content.append("    </size>")
    
        # 通过img_id找到annotations
        annos = df_anno[df_anno["image_id"].isin([img_id])]  # (2,8)表示一张图有两个框
    
        for index, row in annos.iterrows():  # 一张图的所有annotation信息
            bbox = row["bbox"]
            category_id = row["category_id"]
            cate_name = categories[trans_id(category_id)]
    
            # add new object
            xml_content.append("    <object>")
            xml_content.append("        <name>" + cate_name + "</name>")
            xml_content.append("        <truncated>0</truncated>")
            xml_content.append("        <difficult>0</difficult>")
            xml_content.append("        <bndbox>")
            xml_content.append("            <xmin>" + str(int(bbox[0])) + "</xmin>")
            xml_content.append("            <ymin>" + str(int(bbox[1])) + "</ymin>")
            xml_content.append("            <xmax>" + str(int(bbox[0] + bbox[2])) + "</xmax>")
            xml_content.append("            <ymax>" + str(int(bbox[1] + bbox[3])) + "</ymax>")
            xml_content.append("        </bndbox>")
            xml_content.append("    </object>")
        xml_content.append("</annotation>")
    
        x = xml_content
        xml_content = [x[i] for i in range(0, len(x)) if x[i] != "\n"]
        ### list存入文件
        #xml_path = os.path.join(xml_dir, file_name.replace('.xml', '.jpg'))
        xml_path = os.path.join(xml_dir, file_name.split('j')[0]+'xml')
        print(xml_path)
        with open(xml_path, 'w+', encoding="utf8") as f:
            f.write('\n'.join(xml_content))
        xml_content[:] = []

if __name__ == '__main__':
    convert(anno,xml_dir)

二、xml和txt相互转化

1、xml转txt

# xml解析包
import xml.etree.ElementTree as ET
import pickle
import os
# os.listdir() 方法用于返回指定的文件夹包含的文件或文件夹的名字的列表
from os import listdir, getcwd
from os.path import join
from PIL import Image

sets = ['train', 'test', 'val']
classes = ['two_wheeler']   #类别
#根目录下设置data文件夹，data下放置Annotations和labels文件夹，Annotations里面为要转换的xml文件，labels用来存放转化好的txt文件。

# 进行归一化操作
def convert(size, box): # size:(原图w,原图h) , box:(xmin,xmax,ymin,ymax)
    dw = 1./size[0]     # 1/w
    dh = 1./size[1]     # 1/h
    x = (box[0] + box[1])/2.0   # 物体在图中的中心点x坐标
    y = (box[2] + box[3])/2.0   # 物体在图中的中心点y坐标
    w = box[1] - box[0]         # 物体实际像素宽度
    h = box[3] - box[2]         # 物体实际像素高度
    x = x*dw    # 物体中心点x的坐标比(相当于 x/原图w)
    w = w*dw    # 物体宽度的宽度比(相当于 w/原图w)
    y = y*dh    # 物体中心点y的坐标比(相当于 y/原图h)
    h = h*dh    # 物体宽度的宽度比(相当于 h/原图h)
    return (x, y, w, h)    # 返回 相对于原图的物体中心点的x坐标比,y坐标比,宽度比,高度比,取值范围[0-1]


# year ='2012', 对应图片的id（文件名）
def convert_annotation(image_id):
    '''
    将对应文件名的xml文件转化为label文件，xml文件包含了对应的bunding框以及图片长款大小等信息，
    通过对其解析，然后进行归一化最终读到label文件中去，也就是说
    一张图片文件对应一个xml文件，然后通过解析和归一化，能够将对应的信息保存到唯一一个label文件中去
    labal文件中的格式：calss x y w h　　同时，一张图片对应的类别有多个，所以对应的ｂｕｎｄｉｎｇ的信息也有多个
    '''
    # 对应的通过year 找到相应的文件夹，并且打开相应image_id的xml文件，其对应bund文件
    in_file = open('data/Annotations/%s.xml' % (image_id), encoding='utf-8')
    # print(in_file.name)
    # 准备在对应的image_id 中写入对应的label，分别为
    # <object-class> <x> <y> <width> <height>
    out_file = open('data/labels/%s.txt' % (image_id), 'w', encoding='utf-8')
    # print(out_file.name)
    # 解析xml文件
    tree = ET.parse(in_file)
    # 获得对应的键值对
    root = tree.getroot()
    # 获得图片的尺寸大小
    size = root.find('size')
    # 获得宽
    w = int(size.find('width').text)
    # 获得高
    h = int(size.find('height').text)
    # 遍历目标obj
    for obj in root.iter('object'):
        # 获得difficult ？？
        difficult = obj.find('difficult').text
        # 获得类别 =string 类型
        cls = obj.find('name').text
        # 如果类别不是对应在我们预定好的class文件中，或difficult==1则跳过
        if cls not in classes or int(difficult) == 1:
            continue
        # 通过类别名称找到id
        cls_id = classes.index(cls)
        # 找到bndbox 对象
        xmlbox = obj.find('bndbox')
        # 获取对应的bndbox的数组 = ['xmin','xmax','ymin','ymax']
        b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text),
             float(xmlbox.find('ymax').text))
        print(image_id, cls, b)
        # 带入进行归一化操作
        # w = 宽, h = 高， b= bndbox的数组 = ['xmin','xmax','ymin','ymax']
        bb = convert((w, h), b)
        # bb 对应的是归一化后的(x,y,w,h)
        # 生成 calss x y w h 在label文件中
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')


# 返回当前工作目录
wd = getcwd()
print(wd)


for image_set in sets:
    '''
    对所有的文件数据集进行遍历
    做了两个工作：
　　　　１．讲所有图片文件都遍历一遍，并且将其所有的全路径都写在对应的txt文件中去，方便定位
　　　　２．同时对所有的图片文件进行解析和转化，将其对应的bundingbox 以及类别的信息全部解析写到label 文件中去
    　　　　　最后再通过直接读取文件，就能找到对应的label 信息
    '''
    # 先找labels文件夹如果不存在则创建
    if not os.path.exists('data/labels/'):
        os.makedirs('data/labels/')
    # 读取在ImageSets/Main 中的train、test..等文件的内容
    # 包含对应的文件名称
    image_ids = open('data/ImageSets/%s.txt' % (image_set)).read().strip().split()
    # 打开对应的2012_train.txt 文件对其进行写入准备
    list_file = open('data/%s.txt' % (image_set), 'w')
    # 将对应的文件_id以及全路径写进去并换行
    for image_id in image_ids:
        list_file.write('data/images/%s.jpg\n' % (image_id))
        # 调用  year = 年份  image_id = 对应的文件名_id
        convert_annotation(image_id)
    # 关闭文件
    list_file.close()

2、txt转xml

import glob
import cv2

xml_head = '''<annotation>
    <folder>VOC2007</folder>
    <filename>{}</filename>.
    <source>
        <database>The VOC2007 Database</database>
        <annotation>PASCAL VOC2007</annotation>
        <image>flickr</image>
    </source>   
    <size>
        <width>{}</width>
        <height>{}</height>
        <depth>{}</depth>
    </size>
    <segmented>0</segmented>
    '''
xml_obj = '''
    <object>        
        <name>{}</name>
        <pose>Unspecified</pose>
        <truncated>0</truncated>
        <difficult>0</difficult>
        <bndbox>
            <xmin>{}</xmin>
            <ymin>{}</ymin>
            <xmax>{}</xmax>
            <ymax>{}</ymax>
        </bndbox>
    </object>
    '''
xml_end = '''
</annotation>'''

#文件夹设置
#--data
#----train 训练集图片
#----train_txt 对应的txt标签
#----train_xml 对应的xml标签

root='D:/A-new-tjw/works/2022.14-/data/'
labels = ['mask', 'face', 'incorrect mask']  # 数据集类别名
txt_Lists = glob.glob(root +'train'+ '/*.jpg')
print(len(txt_Lists))
# print(txt_Lists)
cnt=0

for txt_path in txt_Lists:
    filename=txt_path.split('\\')
    filename=filename[-1]
    filename=filename.split('.')
    filename=filename[0]

    txt = root+'train_txt/'+filename+'.txt'
    jpg=root+'train/'+filename+'.jpg' #jpg path
    xml=root+'train_xml/'+filename+'.xml'

    print(txt)
    print(jpg)
    print(xml)

    obj = ''

    img = cv2.imread(jpg)
    img_h, img_w = img.shape[0], img.shape[1]

    print('h_factor:',img_h,'  w_factor:',img_w)
    # cv2.imshow("img", img)  #显示图片
    # cv2.waitKey(0)
    # cv2.destroyWindow("img")

    head = xml_head.format(str(filename), str(img_w), str(img_h), "3")

    with open(txt, 'r') as f:
        for line in f.readlines():
            yolo_datas = line.strip().split(' ')
            label = int(float(yolo_datas[0].strip()))
            center_x = round(float(str(yolo_datas[1]).strip()) * img_w)
            center_y = round(float(str(yolo_datas[2]).strip()) * img_h)
            bbox_width = round(float(str(yolo_datas[3]).strip()) * img_w)
            bbox_height = round(float(str(yolo_datas[4]).strip()) * img_h)

            xmin = str(int(center_x - bbox_width / 2))
            ymin = str(int(center_y - bbox_height / 2))
            xmax = str(int(center_x + bbox_width / 2))
            ymax = str(int(center_y + bbox_height / 2))

            obj += xml_obj.format(labels[label], xmin, ymin, xmax, ymax)

    with open(xml, 'w') as f_xml:
        f_xml.write(head + obj + xml_end)
    cnt += 1
    print(cnt)

三、txt和json相互转化

1、txt转json

import os
import json
import cv2
import random
import time
from PIL import Image

coco_format_save_path='D:\\A-new-tjw\\works\\2022.5.19\\people\\labels_json\\val'    #要生成的标准coco格式标签所在文件夹
yolo_format_classes_path='D:\\A-new-tjw\\works\\2022.5.19\\people\\people.names'     #类别文件，一行一个类
yolo_format_annotation_path='D:\\A-new-tjw\\works\\2022.5.19\\people\\labels_txt\\val'        #yolo格式标签所在文件夹
img_pathDir='D:\\A-new-tjw\\works\\2022.5.19\\people\\images\\val'                        #图片所在文件夹

with open(yolo_format_classes_path,'r') as fr:                               #打开并读取类别文件
    lines1=fr.readlines()
# print(lines1)
categories=[]                                                                 #存储类别的列表
for j,label in enumerate(lines1):
    label=label.strip()
    categories.append({'id':j+1,'name':label,'supercategory':'None'})         #将类别信息添加到categories中
# print(categories)

write_json_context=dict()                                                      #写入.json文件的大字典
write_json_context['info']= {'description': '', 'url': '', 'version': '', 'year': 2021, 'contributor': '', 'date_created': '2021-07-25'}
write_json_context['licenses']=[{'id':1,'name':None,'url':None}]
write_json_context['categories']=categories
write_json_context['images']=[]
write_json_context['annotations']=[]

#接下来的代码主要添加'images'和'annotations'的key值
imageFileList=os.listdir(img_pathDir)                                           #遍历该文件夹下的所有文件，并将所有文件名添加到列表中
for i,imageFile in enumerate(imageFileList):
    imagePath = os.path.join(img_pathDir,imageFile)                             #获取图片的绝对路径
    image = Image.open(imagePath)                                               #读取图片，然后获取图片的宽和高
    W, H = image.size

    img_context={}                                                              #使用一个字典存储该图片信息
    #img_name=os.path.basename(imagePath)                                       #返回path最后的文件名。如果path以/或\结尾，那么就会返回空值
    img_context['file_name']=imageFile
    img_context['height']=H
    img_context['width']=W
    img_context['date_captured']='2021-07-25'
    img_context['id']=i                                                         #该图片的id
    img_context['license']=1
    img_context['color_url']=''
    img_context['flickr_url']=''
    write_json_context['images'].append(img_context)                            #将该图片信息添加到'image'列表中


    txtFile=imageFile[:6]+'.txt'                                               #获取该图片获取的txt文件，这个数字"6"要根据自己图片名修改
    with open(os.path.join(yolo_format_annotation_path,txtFile),'r') as fr:
        lines=fr.readlines()                                                   #读取txt文件的每一行数据，lines2是一个列表，包含了一个图片的所有标注信息
    for j,line in enumerate(lines):

        bbox_dict = {}                                                          #将每一个bounding box信息存储在该字典中
        # line = line.strip().split()
        # print(line.strip().split(' '))

        class_id,x,y,w,h=line.strip().split(' ')                                          #获取每一个标注框的详细信息
        class_id,x, y, w, h = int(class_id), float(x), float(y), float(w), float(h)       #将字符串类型转为可计算的int和float类型

        xmin=(x-w/2)*W                                                                    #坐标转换
        ymin=(y-h/2)*H
        xmax=(x+w/2)*W
        ymax=(y+h/2)*H
        w=w*W
        h=h*H

        bbox_dict['id']=i*10000+j                                                         #bounding box的坐标信息
        bbox_dict['image_id']=i
        bbox_dict['category_id']=class_id+1                                               #注意目标类别要加一
        bbox_dict['iscrowd']=0
        height,width=abs(ymax-ymin),abs(xmax-xmin)
        bbox_dict['area']=height*width
        bbox_dict['bbox']=[xmin,ymin,w,h]
        bbox_dict['segmentation']=[[xmin,ymin,xmax,ymin,xmax,ymax,xmin,ymax]]
        write_json_context['annotations'].append(bbox_dict)                               #将每一个由字典存储的bounding box信息添加到'annotations'列表中

name = os.path.join(coco_format_save_path,"val"+ '.json')
with open(name,'w') as fw:                                                                #将字典信息写入.json文件中
    json.dump(write_json_context,fw,indent=2)

2、json转txt

# 处理同一个数据集下多个json文件时，仅运行一次class_txt即可
import json
import os


"存储标签与预测框到txt文件中"
def json_txt(json_path, txt_path):
    "json_path: 需要处理的json文件的路径"
    "txt_path: 将json文件处理后txt文件存放的文件夹名"
    # 生成存放json文件的路径
    if not os.path.exists(txt_path):
        os.mkdir(txt_path)
    # 读取json文件
    with open(json_path, 'r') as f:
        dict = json.load(f)
    # 得到images和annotations信息
    images_value = dict.get("images")  # 得到某个键下对应的值
    annotations_value = dict.get("annotations")  # 得到某个键下对应的值
    # 使用images下的图像名的id创建txt文件
    list=[]  # 将文件名存储在list中
    for i in images_value:
        open(txt_path + str(i.get("id")) + '.txt', 'w')
        list.append(i.get("id"))


    # 将id对应图片的bbox写入txt文件中
    for i in list:
        for j in annotations_value:
            if j.get("image_id") == i:
                # bbox标签归一化处理
                num = sum(j.get('bbox'))
                new_list = [round(m / num, 6) for m in j.get('bbox')]  # 保留六位小数
                with open(txt_path + str(i) + '.txt', 'a') as file1:  # 写入txt文件中
                    print(j.get("category_id"), new_list[0], new_list[1], new_list[2], new_list[3], file=file1)


"将id对应的标签存储在class.txt中"
def class_txt(json_path, class_txt_path):
    "json_path: 需要处理的json文件的路径"
    "txt_path: 将json文件处理后存放所需的txt文件名"
    # 生成存放json文件的路径
    with open(json_path, 'r') as f:
        dict = json.load(f)
    # 得到categories下对应的信息
    categories_value = dict.get("categories")  # 得到某个键下对应的值
    # 将每个类别id与类别写入txt文件中
    with open(class_txt_path, 'a') as file0:
        for i in categories_value:
            print(i.get("id"), i.get('name'), file=file0)


json_txt("train.json", "train_annotations/")
# class_txt("eval.json", "id_categories.txt")