VOC数据集提取自己需要的类

最近在做一项工作,想要从VOC数据集中自己想要的特定类。

如果与我有相同需求的朋友,可以参考我下面的代码。

VOC2007,VOC2012数据集均可用

# -*- coding: utf-8 -*-
# @Function:There are 20 classes in VOC data set. If you need to extract specific classes, you can use this program to extract them.

import os
import shutil
ann_filepath='E:/datasets/VOCdevkit/VOC2012/Annotations/'
img_filepath='E:/datasets/VOCdevkit/VOC2012/JPEGImages/'
img_savepath='E:/datasets/VOCdevkit/VOC2012/JPEGImages_ssd/'
ann_savepath='E:/datasets/VOCdevkit/VOC2012/Annotations_ssd/'
if not os.path.exists(img_savepath):
    os.mkdir(img_savepath)

if not os.path.exists(ann_savepath):
    os.mkdir(ann_savepath)
names = locals()
classes = ['aeroplane','bicycle','bird', 'boat', 'bottle',
           'bus', 'car', 'cat', 'chair', 'cow','diningtable',
           'dog', 'horse', 'motorbike', 'pottedplant',
           'sheep', 'sofa', 'train', 'tvmonitor', 'person']


for file in os.listdir(ann_filepath):
    print(file)
    fp = open(ann_filepath + '\\' + file)
    ann_savefile=ann_savepath+file
    fp_w = open(ann_savefile, 'w')
    lines = fp.readlines()

    ind_start = []
    ind_end = []
    lines_id_start = lines[:]
    lines_id_end = lines[:]

    classes1 = '\t\t<name>bicycle</name>\n'
    classes2 = '\t\t<name>motorbike</name>\n'
    classes3 = '\t\t<name>bus</name>\n'
    classes4 = '\t\t<name>car</name>\n'
    classes5 = '\t\t<name>person</name>\n'

    #在xml中找到object块,并将其记录下来
    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"

    #names中存放所有的object块
    i = 0
    for k in range(0, len(ind_start)):
        names['block%d' % k] = []
        for j in range(0, len(classes)):
            if classes[j] in lines[ind_start[i] + 1]:
                a = ind_start[i]
                for o in range(ind_end[i] - ind_start[i] + 1):
                    names['block%d' % k].append(lines[a + o])
                break
        i += 1
        #print(names['block%d' % k])


    #xml头
    string_start = lines[0:ind_start[0]]
    #xml尾
    string_end = [lines[len(lines) - 1]]


    #在给定的类中搜索,若存在则,写入object块信息
    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]
        if classes2 in names['block%d' % k]:
            a += 1
            string_start += names['block%d' % k]
        if classes3 in names['block%d' % k]:
            a += 1
            string_start += names['block%d' % k]
        if classes4 in names['block%d' % k]:
            a += 1
            string_start += names['block%d' % k]
        if classes5 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()
    #如果没有我们寻找的模块,则删除此xml,有的话拷贝图片
    if a == 0:
        os.remove(ann_savepath+file)
    else:
        name_img = img_filepath + os.path.splitext(file)[0] + ".jpg"
        shutil.copy(name_img, img_savepath)
    fp.close()

参考:http://blog.csdn.net/samylee/article/details/61919677 

评论 24
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值