(日常搬砖)voc等xml格式的数据集转换为yolo可用的txt格式的数据集(亲测可用)

在用darknet训练voc数据集时,需要将xml格式的标签转换为txt格式的标签。
同时,用自定义数据集在darknet中进行训练时,如遇到xml格式转txt格式的问题,也可用本文方法。
废话不多,开始介绍。

  1. 新建文件夹VOCdevkit,文件结构为:
├── gen_files.py
└── VOCdevkit
    └── VOC2007
        ├── Annotations
        ├── ImageSets
        ├── JPEGImages
        └── labels

按照以上结构来建文件夹,并保持名字与上一致。
Annotations用来存放xml格式的标注文件;
JPEGImages存放图片数据集;
labels存放转换后的txt标注文件,目前是空文件夹。

  1. gen_files.py放至与VOCdevkit文件夹同级目录,代码内容如下:
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
import random

classes=["class1","class2"]


def clear_hidden_files(path):
    dir_list = os.listdir(path)
    for i in dir_list:
        abspath = os.path.join(os.path.abspath(path), i)
        if os.path.isfile(abspath):
            if i.startswith("._"):
                os.remove(abspath)
        else:
            clear_hidden_files(abspath)

def convert(size, box):
    dw = 1./size[0]
    dh = 1./size[1]
    x = (box[0] + box[1])/2.0
    y = (box[2] + box[3])/2.0
    w = box[1] - box[0]
    h = box[3] - box[2]
    x = x*dw
    w = w*dw
    y = y*dh
    h = h*dh
    return (x,y,w,h)

def convert_annotation(image_id):
    in_file = open('VOCdevkit/VOC2007/Annotations/%s.xml' %image_id)
    out_file = open('VOCdevkit/VOC2007/labels/%s.txt' %image_id, 'w')
    tree=ET.parse(in_file)
    root = tree.getroot()
    size = root.find('size')
    w = int(size.find('width').text)
    h = int(size.find('height').text)

    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 = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text), float(xmlbox.find('ymax').text))
        bb = convert((w,h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
    in_file.close()
    out_file.close()

wd = os.getcwd()
wd = os.getcwd()
work_sapce_dir = os.path.join(wd, "VOCdevkit/")
if not os.path.isdir(work_sapce_dir):
    os.mkdir(work_sapce_dir)
work_sapce_dir = os.path.join(work_sapce_dir, "VOC2007/")
if not os.path.isdir(work_sapce_dir):
    os.mkdir(work_sapce_dir)
annotation_dir = os.path.join(work_sapce_dir, "Annotations/")
if not os.path.isdir(annotation_dir):
        os.mkdir(annotation_dir)
clear_hidden_files(annotation_dir)
image_dir = os.path.join(work_sapce_dir, "JPEGImages/")
if not os.path.isdir(image_dir):
        os.mkdir(image_dir)
clear_hidden_files(image_dir)
VOC_file_dir = os.path.join(work_sapce_dir, "ImageSets/")
if not os.path.isdir(VOC_file_dir):
        os.mkdir(VOC_file_dir)
VOC_file_dir = os.path.join(VOC_file_dir, "Main/")
if not os.path.isdir(VOC_file_dir):
        os.mkdir(VOC_file_dir)

train_file = open(os.path.join(wd, "2007_train.txt"), 'w')
test_file = open(os.path.join(wd, "2007_test.txt"), 'w')
train_file.close()
test_file.close()
VOC_train_file = open(os.path.join(work_sapce_dir, "ImageSets/Main/train.txt"), 'w')
VOC_test_file = open(os.path.join(work_sapce_dir, "ImageSets/Main/test.txt"), 'w')
VOC_train_file.close()
VOC_test_file.close()
if not os.path.exists('VOCdevkit/VOC2007/labels'):
    os.makedirs('VOCdevkit/VOC2007/labels')
train_file = open(os.path.join(wd, "2007_train.txt"), 'a')
test_file = open(os.path.join(wd, "2007_test.txt"), 'a')
VOC_train_file = open(os.path.join(work_sapce_dir, "ImageSets/Main/train.txt"), 'a')
VOC_test_file = open(os.path.join(work_sapce_dir, "ImageSets/Main/test.txt"), 'a')
list = os.listdir(image_dir) # list image files
probo = random.randint(1, 100)
print("Probobility: %d" % probo)
for i in range(0,len(list)):
    path = os.path.join(image_dir,list[i])
    if os.path.isfile(path):
        image_path = image_dir + list[i]
        voc_path = list[i]
        (nameWithoutExtention, extention) = os.path.splitext(os.path.basename(image_path))
        (voc_nameWithoutExtention, voc_extention) = os.path.splitext(os.path.basename(voc_path))
        annotation_name = nameWithoutExtention + '.xml'
        annotation_path = os.path.join(annotation_dir, annotation_name)
    probo = random.randint(1, 100)
    print("Probobility: %d" % probo)
    if(probo < 75):
        if os.path.exists(annotation_path):
            train_file.write(image_path + '\n')
            VOC_train_file.write(voc_nameWithoutExtention + '\n')
            convert_annotation(nameWithoutExtention)
    else:
        if os.path.exists(annotation_path):
            test_file.write(image_path + '\n')
            VOC_test_file.write(voc_nameWithoutExtention + '\n')
            convert_annotation(nameWithoutExtention)
train_file.close()
test_file.close()
VOC_train_file.close()
VOC_test_file.close()

  1. classes=["class1","class2"]改成你要转换的数据集对应的类别即可(注意类别顺序),其他的默认即可。
  2. 运行gen_files.py,之后会在labels文件夹生成转换成功的txt文件,同时会在根目录下生成train.txt test.txt。
  • 2
    点赞
  • 13
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
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