python批量将json文件转换成xml文件

由于在使用SSD进行训练时,使用的是VOC数据格式,但是手上标注的数据集是labelme标注的json格式
首先这是文件夹的文件目录,其中labeljson文件夹下放标注的json文件,trainset文件夹下面放标注的jpg和json文件,最终生成的xml文件会放在Annotations下
《python批量将json文件转换成xml文件》
代码如下:

#########################4、对.json格式的标签文件进行处理#######################
# coding=utf-8
import os
import numpy as np
import codecs
import json
from glob import glob
import cv2
import shutil
from sklearn.model_selection import train_test_split
#1.标签路径
labelme_path = "./labeljson/"                 # 原始xxx标注数据路径,需要更换成自己的数据集名称
saved_path = "./datasets/VOC2007/"      # 保存路径

#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")
files=os.listdir(labelme_path)
files = [i.split("/")[-1].split(".json")[0] for i in 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"))
    height, width, channels = cv2.imread("./trainset/"+json_file_ +".jpg").shape
    with codecs.open(saved_path + "Annotations/"+json_file_ + ".xml","w","utf-8") as xml:
        xml.write('<annotation>\n')
        xml.write('\t<folder>' + 'JPEGImages' + '</folder>\n')#训练时我的训练图片是放在JPEGImages下的
        xml.write('\t<filename>' + json_file_ + ".jpg" + '</filename>\n')
        xml.write('\t<source>\n')
        xml.write('\t\t<database>The Defect Detection</database>\n')
        xml.write('\t\t<annotation>Defect Detection</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>WZZ</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"])
            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>'+json_file["shapes"][0]["label"]+'</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(xmin) + '</xmin>\n')
                xml.write('\t\t\t<ymin>' + str(ymin) + '</ymin>\n')
                xml.write('\t\t\t<xmax>' + str(xmax) + '</xmax>\n')
                xml.write('\t\t\t<ymax>' + str(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
# image_files = glob(labelme_path + "*.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')
# total_files = glob("./VOC2007/Annotations/*.xml")
# total_files = [i.split("/")[-1].split(".xml")[0] for i in total_files]
# test_filepath = "./test"
# for file in total_files:
# ftrainval.write(file + "\n")
# #test
# for file in os.listdir(test_filepath):
# ftest.write(file.split(".jpg")[0] + "\n")
# #split
# train_files,val_files = train_test_split(total_files,test_size=0.15,random_state=42)
# #train
# for file in train_files:
# ftrain.write(file + "\n")
# #val
# for file in val_files:
# fval.write(file + "\n")

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

    原文作者:sereiiii_x
    原文地址: https://blog.csdn.net/qq_43050258/article/details/124584104
    本文转自网络文章,转载此文章仅为分享知识,如有侵权,请联系博主进行删除。
点赞