voc中xml提取类别再转txt

voc中xml提取类别再转txt

一，xml提取想要的类别

'''
需要修改：
1.fileDir_ann
2.fileDir_img 
3.saveDir_img
4.saveDir_ann
5.classes = ['aeroplane','bicycle','bird','boat','bottle','bus','car','cat','chair','cow']需要包含原始标签中所有的类
6.classes1 = '\t\t<name>bird</name>\n'中间的类别修改为自己想要的。
'''

import os
import os.path
import shutil
#原始数据
fileDir_ann = r'/home/jun/VOCdevkit/VOC2007/Annotations/'
fileDir_img = r'/home/jun/VOCdevkit/VOC2007/JPEGImages/'
 
#存放包含需要的类的图片
saveDir_img = r'/home/jun/VOCdevkit/VOC2007/image/'
        
if not os.path.exists(saveDir_img):
    os.mkdir(saveDir_img)
 
 
names = locals()
 
for files in os.walk(fileDir_ann):
    #遍历Annotations中的所有文件
    for file in files[2]:
        
 
        #存放包含需要的类的图片对应的xml文件
        saveDir_ann = r'/home/jun/VOCdevkit/VOC2007/Annotations_ctpn/'
 
        if not os.path.exists(saveDir_ann):
            os.mkdir(saveDir_ann)
        fp = open(fileDir_ann + file)       
        saveDir_ann = saveDir_ann + file
        fp_w = open(saveDir_ann, 'w')
        classes = ['aeroplane','bicycle','bird','boat','bottle','bus','car','cat','chair','cow']
 
        lines = fp.readlines()
 
        
        ind_start = []
 
        
        ind_end = []
 
        lines_id_start = lines[:]
        lines_id_end = lines[:]
 
        while "\t<object>\n" in lines_id_start:
            a = lines_id_start.index("\t<object>\n")
            ind_start.append(a)
            lines_id_start[a] = "delete"
 
        while "\t</object>\n" in lines_id_end:
            b = lines_id_end.index("\t</object>\n")
            ind_end.append(b)
            lines_id_end[b] = "delete"
 
        for k in range(0,len(ind_start)):
            for j in range(0,len(classes)):
                if classes[j] in lines[ind_start[k]+1]:
                    a = ind_start[k]
                    names['block%d'%k] = lines[a:ind_end[k]+1]
                    break
        #需要的类
        classes1 = '\t\t<name>bird</name>\n'
 
        string_start = lines[0:ind_start[0]]
        string_end = lines[ind_end[-1] + 1:]
 
        a = 0
        for k in range(0,len(ind_start)):
            if classes1 in names['block%d'%k]:
                a += 1
                string_start += names['block%d'%k]
 
        string_start += string_end
        for c in range(0,len(string_start)):
            fp_w.write(string_start[c])
        fp_w.close()
 
        if a == 0:
            os.remove(saveDir_ann)
        else:
            name_img = fileDir_img + os.path.splitext(file)[0] + ".jpg"
            shutil.copy(name_img,saveDir_img)
        fp.close()

二，xml转txt

import xml.etree.ElementTree as ET
import os
import sys

if __name__ == "__main__":
    xmls_path = "/home/jun/VOCdevkit/VOC2007/mlt/label"
    target_path = "/home/jun/VOCdevkit/VOC2007/mlt/txt"

    for xmlFilePath in os.listdir(xmls_path):
        print(os.path.join(xmls_path,xmlFilePath))
        try:
            tree = ET.parse(os.path.join(xmls_path,xmlFilePath))

            # 获得根节点
            root = tree.getroot()
        except Exception as e:  # 捕获除与程序退出sys.exit()相关之外的所有异常
            print("parse test.xml fail!")
            sys.exit()

        # objects = root.find("object")
        # print(len(objects))
        f = open(target_path +"/" + os.path.splitext(xmlFilePath)[0] + ".txt", 'w')
        # print(f)

 

        for bndbox in root.iter('bndbox'):
            node = []
            for child in bndbox:
                node.append(int(child.text))
            x1, y1 = node[0],node[1]
            x3, y3 = node[2],node[3]
            '''
            x2 ,y2 = x3 ,y1
            x4, y4 = x1, y3
            '''
            string = ''+str(x1)+','+str(y1)+','+str(x3)+','+str(y3);
            # print(string)
            f.write(string+'\n')

            
        f.close()