VOC格式数据集转yolo格式数据集的方法

现在开源的多数数据集都是VOC格式,但是往往我们使用的时候需要用到其它格式的数据集,愁的很,是不是需要重新一个一个的打标签呢?其实不用,只需要一段简单的代码就可以直接将VOC格式数据集转为yolo格式数据集,以下代码是可以直接自动分几个文件夹存放好训练集,验证集,以及对应对应标签的,数据集的分配比例也是可以自定义修改的。具体代码见下:

import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
import random
from shutil import copyfile

classes = ["Before a whole","After a whole","Chest former","Chest after","Raise hand before","Raise hand after","Global left position","Global right position","Front face","Left face","Right face"]        ##这里要写好标签对应的类
# classes=["ball"]

TRAIN_RATIO = 80     #表示将数据集划分为训练集和验证集,按照2:8比例来的


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/YOLOLabels/%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()
data_base_dir = os.path.join(wd, "VOCdevkit/")
if not os.path.isdir(data_base_dir):
    os.mkdir(data_base_dir)
work_sapce_dir = os.path.join(data_base_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)
yolo_labels_dir = os.path.join(work_sapce_dir, "YOLOLabels/")
if not os.path.isdir(yolo_labels_dir):
    os.mkdir(yolo_labels_dir)
clear_hidden_files(yolo_labels_dir)
yolov5_images_dir = os.path.join(data_base_dir, "images/")
if not os.path.isdir(yolov5_images_dir):
    os.mkdir(yolov5_images_dir)
clear_hidden_files(yolov5_images_dir)
yolov5_labels_dir = os.path.join(data_base_dir, "labels/")
if not os.path.isdir(yolov5_labels_dir):
    os.mkdir(yolov5_labels_dir)
clear_hidden_files(yolov5_labels_dir)
yolov5_images_train_dir = os.path.join(yolov5_images_dir, "train/")
if not os.path.isdir(yolov5_images_train_dir):
    os.mkdir(yolov5_images_train_dir)
clear_hidden_files(yolov5_images_train_dir)
yolov5_images_test_dir = os.path.join(yolov5_images_dir, "val/")
if not os.path.isdir(yolov5_images_test_dir):
    os.mkdir(yolov5_images_test_dir)
clear_hidden_files(yolov5_images_test_dir)
yolov5_labels_train_dir = os.path.join(yolov5_labels_dir, "train/")
if not os.path.isdir(yolov5_labels_train_dir):
    os.mkdir(yolov5_labels_train_dir)
clear_hidden_files(yolov5_labels_train_dir)
yolov5_labels_test_dir = os.path.join(yolov5_labels_dir, "val/")
if not os.path.isdir(yolov5_labels_test_dir):
    os.mkdir(yolov5_labels_test_dir)
clear_hidden_files(yolov5_labels_test_dir)

train_file = open(os.path.join(wd, "yolov5_train.txt"), 'w')
test_file = open(os.path.join(wd, "yolov5_val.txt"), 'w')
train_file.close()
test_file.close()
train_file = open(os.path.join(wd, "yolov5_train.txt"), 'a')
test_file = open(os.path.join(wd, "yolov5_val.txt"), 'a')
list_imgs = os.listdir(image_dir)  # list image files
prob = random.randint(1, 100)
print("Probability: %d" % prob)
for i in range(0, len(list_imgs)):
    path = os.path.join(image_dir, list_imgs[i])
    if os.path.isfile(path):
        image_path = image_dir + list_imgs[i]
        voc_path = list_imgs[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)
        label_name = nameWithoutExtention + '.txt'
        label_path = os.path.join(yolo_labels_dir, label_name)
    prob = random.randint(1, 100)
    print("Probability: %d" % prob)
    if (prob < TRAIN_RATIO):  # train dataset
        if os.path.exists(annotation_path):
            train_file.write(image_path + '\n')
            convert_annotation(nameWithoutExtention)  # convert label
            copyfile(image_path, yolov5_images_train_dir + voc_path)
            copyfile(label_path, yolov5_labels_train_dir + label_name)
    else:  # test dataset
        if os.path.exists(annotation_path):
            test_file.write(image_path + '\n')
            convert_annotation(nameWithoutExtention)  # convert label
            copyfile(image_path, yolov5_images_test_dir + voc_path)
            copyfile(label_path, yolov5_labels_test_dir + label_name)
train_file.close()
test_file.close()

关于文件之间的关系,可能有的学者有些迷惑,原始的VOC格式数据集文件该怎么存放,以及新生成的yolo格式数据集又会被存放到哪里,关于这些疑惑看下面讲解。

先复制VOC格式的数据集文件夹到上面代码所在的根目录下,见下:
在这里插入图片描述

在文件VOCdevkit中包含的内容见下:
在这里插入图片描述

运行上面的代码后就得到了新的yolo格式数据集,关于新数据集的文件关系见下:

在这里插入图片描述

上图中,我已经标明了哪个文件中存放训练用的数据集,验证集和哪个文件存放标签等的对应文件位置。

以上就是VOC格式数据集转yolo格式数据集的方法,希望能帮到和我一样正在掉头发的你,多多支持,谢谢!

  • 4
    点赞
  • 23
    收藏
  • 打赏
    打赏
  • 3
    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
©️2022 CSDN 皮肤主题:1024 设计师:我叫白小胖 返回首页
评论 3

打赏作者

佐咖

你的鼓励将是我创作的最大动力

¥2 ¥4 ¥6 ¥10 ¥20
输入1-500的整数
余额支付 (余额:-- )
扫码支付
扫码支付:¥2
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

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、C币套餐、付费专栏及课程。

余额充值