labelme转VOC2007格式

$$labelme转VOC2007格式$$

运行labelme2voc.py文件需要 图片和json文件在同一文件夹下面

cmd 打开

输入

python labelme2voc.py

得到

labelme2voc.py

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 = "./"              #原始labelme标注数据路径
saved_path = "./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 = [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(labelme_path + 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>' + 'UAV_data' + '</folder>\n')
        xml.write('\t<filename>' + json_file_ + ".jpg" + '</filename>\n')
        xml.write('\t<source>\n')
        xml.write('\t\t<database>The UAV autolanding</database>\n')
        xml.write('\t\t<annotation>UAV AutoLanding</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>ChaojieZhu</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>'+"class_name"+'</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 = ""
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()

训练集和验证集的划分方法是采用 sklearn.model_selection.train_test_split 进行分割的。
默认图片格式 .jpg，如果图片格式有变化，请自行修改代码中的 .jpg 名称。
默认不添加测试集，如果有需要，自行解开注释即可。

voc2annotation

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

sets=[('2007', 'train'), ('2007', 'val'), ('2007', 'test')]

wd = getcwd()
classes = ["fire"]

def convert_annotation(year, image_id, list_file):
    in_file = open('VOCdevkit/VOC%s/Annotations/%s.xml'%(year, image_id))
    tree=ET.parse(in_file)
    root = tree.getroot()
    list_file.write('%s/VOCdevkit/VOC%s/JPEGImages/%s.jpg'%(wd, 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('./VOCdevkit/VOC%s/ImageSets/Main/%s.txt'%(year, image_set)).read().strip().splitlines()
    list_file = open('%s_%s.txt'%(year, image_set), 'w')
    for image_id in image_ids:
        convert_annotation(year, image_id, list_file)
    list_file.close()