Labelme标注的json文件转成xml文件（voc2007所需格式）
用labelme标注的文件（如下图所示）是json格式，不能直接用于目标检测
目标检测需要的是voc2007格式数据，其中的标注文件是xml格式的。
VOC2007数据文件夹说明
1)JPEGImages文件夹
文件夹里包含了训练图片和测试图片，混放在一起
2)Annatations文件夹
文件夹存放的是xml格式的标签文件，每个xml文件都对应于JPEGImages文件夹的一张图片
3)ImageSets文件夹
Main存放的是图像物体识别的数据，Main里面有test.txt, train.txt, val.txt,trainval.txt.这四个文件我们后面会生成
转换代码如下，程序会自动生成所需voc2007格式以及所需所有文件：
# -*- coding: utf-8 -*-
"""
Created on Sun May 31 10:19:23 2020
@author: ywx
"""
import os
from typing import List, Any
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 = "labelmedataset/labels/"
#原始labelme标注数据路径
saved_path = "VOC2007/"
# 保存路径
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")
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"))
height, width, channels = cv2.imread('labelmedataset/images/' + json_file_ + ".jpg").shape
with codecs.open(saved_path + "Annotations/" + json_file_ + ".xml", "w", "utf-8") as xml:
xml.write('\n')
xml.write('\t' + 'WH_data' + ' \n')
xml.write('\t' + json_file_ + ".jpg" + ' \n')
xml.write('\t\n')
xml.write('\t\tWH Data \n')
xml.write('\t\tWH \n')
xml.write('\t\tflickr \n')
xml.write('\t\tNULL \n')
xml.write('\t \n')
xml.write('\t\n')
xml.write('\t\tNULL \n')
xml.write('\t\tWH \n')
xml.write('\t \n')
xml.write('\t\n')
xml.write('\t\t' + str(width) + ' \n')
xml.write('\t\t' + str(height) + ' \n')
xml.write('\t\t' + str(channels) + ' \n')
xml.write('\t \n')
xml.write('\t\t0 \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\n')
print(json_filename, xmin, ymin, xmax, ymax, label)
xml.write(' ')
# 5.复制图片到 VOC2007/JPEGImages/下
image_files = glob("labelmedataset/images/" + "*.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.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=0.15, random_state=55)
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()检验是否转换成功以及准不准确：
可以打开labelimg标注软件，查看标注的框是不是和之前用labelme标注的一样。
查看步骤：
1、打开labelimg软件
2、Open Dir，选择标注文件所在文件夹Annatations
3、Change Save Dir，选择图片所在文件夹JPEGImages
4、点击Next Image，一个一个查看，是否标注正确