数据转换指南：从JSON到XML格式

数据转换篇—json to xml格式

1、json to xml

# -*- coding:UTF-8 -*-
'''
将json文件转为类似voc中的xml格式
'''
import os
import numpy as np
import codecs
from sklearn.model_selection import train_test_split

import json
from glob import glob
import cv2
import shutil


# 1.fixme: 原始labelme标注数据路径json文件（需要修改路径）
labelme_path = "/app/dataset/json/"
# 保存路径xml
saved_path = "/app/dataset/"

isUseTest=True#是否创建test集
# 2.创建要求文件夹
if not os.path.exists(saved_path + "Annotations"):
    os.makedirs(saved_path + "Annotations")
if not os.path.exists(saved_path + "JPEGImages/"):
    os.makedirs(saved_path + "JPEGImages/")
if not os.path.exists(saved_path + "ImageSets/Main/"):
    os.makedirs(saved_path + "ImageSets/Main/")
# 3.获取待处理文件
files = glob(labelme_path + "*.json")
## windows路径
files = [i.replace("\\","/").split("/")[-1].split(".json")[0] for i in files]
print(files)
# 4.读取标注信息并写入 xml
for json_file_ in files:
    json_filename = labelme_path + json_file_ + ".json"
    json_file = json.load(open(json_filename, "r", encoding="utf-8"))
    #原图文件地址:saved_path+'img/'(需要更换)
    height, width, channels = cv2.imread(saved_path + 'img/' + json_file_ + ".jpg").shape #原图地址
    with codecs.open(saved_path + "Annotations/" + json_file_ + ".xml", "w", "utf-8") as xml:

        xml.write('<annotation>\n')
        xml.write('\t<folder>' + 'ECM' + '</folder>\n')
        xml.write('\t<filename>' + json_file_ + ".jpg" + '</filename>\n')
        xml.write('\t<source>\n')
        xml.write('\t\t<database>ECM_Data</database>\n')
        xml.write('\t\t<annotation>ECM</annotation>\n')
        xml.write('\t\t<image>flickr</image>\n')
        xml.write('\t\t<flickrid>NULL</flickrid>\n')
        xml.write('\t</source>\n')
        xml.write('\t<owner>\n')
        xml.write('\t\t<flickrid>NULL</flickrid>\n')
        xml.write('\t\t<name>XT</name>\n')
        xml.write('\t</owner>\n')
        xml.write('\t<size>\n')
        xml.write('\t\t<width>' + str(width) + '</width>\n')
        xml.write('\t\t<height>' + str(height) + '</height>\n')
        xml.write('\t\t<depth>' + str(channels) + '</depth>\n')
        xml.write('\t</size>\n')
        xml.write('\t\t<segmented>0</segmented>\n')
        for multi in json_file["shapes"]:
            points = np.array(multi["points"])
            labelName=multi["label"]
            xmin = min(points[:, 0])
            xmax = max(points[:, 0])
            ymin = min(points[:, 1])
            ymax = max(points[:, 1])
            label = multi["label"]
            if xmax <= xmin:
                pass
            elif ymax <= ymin:
                pass
            else:
                xml.write('\t<object>\n')
                xml.write('\t\t<name>' + labelName+ '</name>\n')
                xml.write('\t\t<pose>Unspecified</pose>\n')
                xml.write('\t\t<truncated>1</truncated>\n')
                xml.write('\t\t<difficult>0</difficult>\n')
                xml.write('\t\t<bndbox>\n')
                xml.write('\t\t\t<xmin>' + str(int(xmin)) + '</xmin>\n')
                xml.write('\t\t\t<ymin>' + str(int(ymin)) + '</ymin>\n')
                xml.write('\t\t\t<xmax>' + str(int(xmax)) + '</xmax>\n')
                xml.write('\t\t\t<ymax>' + str(int(ymax)) + '</ymax>\n')
                xml.write('\t\t</bndbox>\n')
                xml.write('\t</object>\n')
                print(json_filename, xmin, ymin, xmax, ymax, label)
        xml.write('</annotation>')
# 5.复制图片到 VOC2007/JPEGImages/下

# fixme:自己的图片路径（需要修改路径）
image_files = glob("/app/dataset/img/" + "*.jpg")
print("copy image files to VOC007/JPEGImages/")
for image in image_files:
    shutil.copy(image, saved_path + "JPEGImages/")

2、分割数据集

import random
import os


XML_FILE_PATH = "/app/dataset/Annotations/"
SAVE_BASE_PATH = "/app/dataset/ImageSets/Main"

train_percent = 0.9   # 0.9
trainval_percent = 1

temp_xml = os.listdir(XML_FILE_PATH)
total_xml = []
for xml in temp_xml:
    if xml.endswith(".xml"):
        total_xml.append(xml)

num = len(total_xml)
list = range(num)
tv = int(num * trainval_percent)
tr = int(tv * train_percent)
trainval = random.sample(list, tv)
train = random.sample(trainval, tr)

print("train and val size", tv)
print("traub size", tr)
ftrainval = open(os.path.join(SAVE_BASE_PATH, 'trainval.txt'), 'w')
ftest = open(os.path.join(SAVE_BASE_PATH, 'test.txt'), 'w')
ftrain = open(os.path.join(SAVE_BASE_PATH, 'train.txt'), 'w')
fval = open(os.path.join(SAVE_BASE_PATH, 'val.txt'), 'w')

for i in list:
    name = total_xml[i][:-4] + '\n'
    if i in trainval:
        ftrainval.write(name)
        if i in train:
            ftrain.write(name)
        else:
            fval.write(name)
    else:
        ftest.write(name)

ftrainval.close()
ftrain.close()
fval.close()
ftest .close()

3、提取数据

import xml.etree.ElementTree as ET
from os import getcwd
import os


DATA_TXT = "../data/data_txt/{}_{}.txt"
IMAGE_IDS = "/app/project/error_dataset{}/ImageSets/Main/{}.txt"
OPEN_XML_PATH = "/app/project/error_dataset{}/Annotations/{}.xml"
IMAGE_WRITER_PATH = "/app/project/error_dataset{}/JPEGImages/{}.jpg"


sets = [('2022', 'train'), ('2022', 'val'), ('2022', 'test')]

wd = getcwd()

classes = ["ElectricBox", "Dustbin_opening"]


def convert_annotation(year, image_id, list_file):
    in_file = open(OPEN_XML_PATH.format(year, image_id))
    tree = ET.parse(in_file)
    root = tree.getroot()
    list_file.write(IMAGE_WRITER_PATH.format(year, image_id))
    for obj in root.iter('object'):
        difficult = obj.find('difficult').text
        cls = obj.find('name').text
        if cls not in classes or int(difficult) == 1:
            continue
        cls_id = classes.index(cls)
        xmlbox = obj.find('bndbox')
        b = (int(xmlbox.find('xmin').text), int(xmlbox.find('ymin').text), int(xmlbox.find('xmax').text), int(xmlbox.find('ymax').text))
        list_file.write(" " + ",".join([str(a) for a in b]) + ',' + str(cls_id))

    list_file.write('\n')


for year, image_set in sets:
    image_ids = open(IMAGE_IDS.format(year, image_set)).read().strip().split()
    save_data_path = '/'.join(DATA_TXT.split('/')[:-1])
    if not os.path.exists(save_data_path):
        os.makedirs(save_data_path)
    list_file = open(DATA_TXT.format(year, image_set), 'w')
    for image_id in image_ids:
        convert_annotation(year, image_id, list_file)
    list_file.close()

参考

# -*- coding:UTF-8 -*-
'''
将json文件转为类似voc中的xml格式
'''
import os
import numpy as np
import codecs
from sklearn.model_selection import train_test_split

import json
from glob import glob
import cv2
import shutil


# 1.fixme: 原始labelme标注数据路径json文件（需要修改路径）
labelme_path = "/app/dataset/json/"
# 保存路径xml
saved_path = "/app/dataset/"

isUseTest=True#是否创建test集
# 2.创建要求文件夹
if not os.path.exists(saved_path + "Annotations"):
    os.makedirs(saved_path + "Annotations")
if not os.path.exists(saved_path + "JPEGImages/"):
    os.makedirs(saved_path + "JPEGImages/")
if not os.path.exists(saved_path + "ImageSets/Main/"):
    os.makedirs(saved_path + "ImageSets/Main/")
# 3.获取待处理文件
files = glob(labelme_path + "*.json")
## windows路径
files = [i.replace("\\","/").split("/")[-1].split(".json")[0] for i in files]
print(files)
# 4.读取标注信息并写入 xml
for json_file_ in files:
    json_filename = labelme_path + json_file_ + ".json"
    json_file = json.load(open(json_filename, "r", encoding="utf-8"))
    #原图文件地址:saved_path+'img/'(需要更换)
    height, width, channels = cv2.imread(saved_path + 'img/' + json_file_ + ".jpg").shape #原图地址
    with codecs.open(saved_path + "Annotations/" + json_file_ + ".xml", "w", "utf-8") as xml:

        xml.write('<annotation>\n')
        xml.write('\t<folder>' + 'ECM' + '</folder>\n')
        xml.write('\t<filename>' + json_file_ + ".jpg" + '</filename>\n')
        xml.write('\t<source>\n')
        xml.write('\t\t<database>ECM_Data</database>\n')
        xml.write('\t\t<annotation>ECM</annotation>\n')
        xml.write('\t\t<image>flickr</image>\n')
        xml.write('\t\t<flickrid>NULL</flickrid>\n')
        xml.write('\t</source>\n')
        xml.write('\t<owner>\n')
        xml.write('\t\t<flickrid>NULL</flickrid>\n')
        xml.write('\t\t<name>XT</name>\n')
        xml.write('\t</owner>\n')
        xml.write('\t<size>\n')
        xml.write('\t\t<width>' + str(width) + '</width>\n')
        xml.write('\t\t<height>' + str(height) + '</height>\n')
        xml.write('\t\t<depth>' + str(channels) + '</depth>\n')
        xml.write('\t</size>\n')
        xml.write('\t\t<segmented>0</segmented>\n')
        for multi in json_file["shapes"]:
            points = np.array(multi["points"])
            labelName=multi["label"]
            xmin = min(points[:, 0])
            xmax = max(points[:, 0])
            ymin = min(points[:, 1])
            ymax = max(points[:, 1])
            label = multi["label"]
            if xmax <= xmin:
                pass
            elif ymax <= ymin:
                pass
            else:
                xml.write('\t<object>\n')
                xml.write('\t\t<name>' + labelName+ '</name>\n')
                xml.write('\t\t<pose>Unspecified</pose>\n')
                xml.write('\t\t<truncated>1</truncated>\n')
                xml.write('\t\t<difficult>0</difficult>\n')
                xml.write('\t\t<bndbox>\n')
                xml.write('\t\t\t<xmin>' + str(int(xmin)) + '</xmin>\n')
                xml.write('\t\t\t<ymin>' + str(int(ymin)) + '</ymin>\n')
                xml.write('\t\t\t<xmax>' + str(int(xmax)) + '</xmax>\n')
                xml.write('\t\t\t<ymax>' + str(int(ymax)) + '</ymax>\n')
                xml.write('\t\t</bndbox>\n')
                xml.write('\t</object>\n')
                print(json_filename, xmin, ymin, xmax, ymax, label)
        xml.write('</annotation>')
# 5.复制图片到 VOC2007/JPEGImages/下

# fixme:自己的图片路径（需要修改路径）
image_files = glob("/app/dataset/img/" + "*.jpg")
print("copy image files to VOC007/JPEGImages/")
for image in image_files:
    shutil.copy(image, saved_path + "JPEGImages/")
# 6.split files for txt
txtsavepath = saved_path + "ImageSets/Main/"
ftrainval = open(txtsavepath + '/trainval.txt', 'w')
ftest = open(txtsavepath + '/test.txt', 'w')
ftrain = open(txtsavepath + '/train.txt', 'w')
fval = open(txtsavepath + '/val.txt', 'w')
# fixme: 需要修改路径
total_files = glob("/app/dataset/Annotations/*.xml")
total_files = [i.replace("\\","/").split("/")[-1].split(".xml")[0] for i in total_files]
trainval_files=[]
test_files=[]
if isUseTest:
    trainval_files, test_files = train_test_split(total_files, test_size=0.2, random_state=42)
else:
    trainval_files=total_files
for file in trainval_files:
    ftrainval.write(file + "\n")
# split
train_files, val_files = train_test_split(trainval_files, test_size=0.15, random_state=55)
# train
for file in train_files:
    ftrain.write(file + "\n")
# val
for file in val_files:
    fval.write(file + "\n")
for file in test_files:
    print(file)
    ftest.write(file + "\n")
ftrainval.close()
ftrain.close()
fval.close()
ftest.close()