VOC格式数据集转yolo格式

一、VOC格式

VOC格式数据集转yolo格式_第1张图片

二、yolo格式

VOC格式数据集转yolo格式_第2张图片

三、VOC转yolo格式

将已经下载好的VOC数据集图片全放在JPEGImages文件夹里面,如果想要VOC所有的数据集,就将其他版本的数据集拷贝进来(比如我是将VOC2007的所有数据集拷贝了进来),xml文件放到Annotations文件夹下
  1. 目录机构
    VOC格式数据集转yolo格式_第3张图片
  2. 注意如果有其他拷贝进来的数据集,要将main文件夹下的train.txt、val.txt、trainval.txt、test.txt全部合并。
  3. main.py代码
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join

sets = [('2012', 'train'), ('2012', 'val'), ('2012', 'test')]

classes = ["aeroplane", "bicycle", "bird", "boat", "bottle", "bus",
           "car", "cat", "chair", "cow", "diningtable", "dog", "horse",
           "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"]


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(year, image_id):
    in_file = open('VOCdevkit/VOC%s/Annotations/%s.xml' % (year, image_id))
    out_file = open('VOCdevkit/VOC%s/labels/%s.txt' % (year, 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')


wd = getcwd()

for year, image_set in sets:
    if not os.path.exists('VOCdevkit/VOC%s/labels/' % (year)):
        os.makedirs('VOCdevkit/VOC%s/labels/' % (year))
    image_ids = open('VOCdevkit/VOC%s/ImageSets/Main/%s.txt'
                     % (year, image_set)).read().strip().split()

    list_file = open('%s_%s.txt' % (year, image_set), 'w')

    for image_id in image_ids:
        list_file.write('%s/VOCdevkit/VOC%s/JPEGImages/%s.jpg\n'
                        % (wd, year, image_id))
        convert_annotation(year, image_id)
    list_file.close()

  1. 注意核对自己的路径
    VOC格式数据集转yolo格式_第4张图片
  2. 运行程序之后的目录结构
    会多出来一个文件夹+四个文件
    VOC格式数据集转yolo格式_第5张图片
    labels下面是所有的VOC转化为yolo之后的txt文件
    2012_test.txt、2012_train.txt、2012_val.txt里面存放的是测试集、训练集、验证集的图片存放路径
    VOC格式数据集转yolo格式_第6张图片

注:本文是参考这篇博客的基础上自己写的文章,感兴趣的朋友也可以看看

另外:

只讲xml格式转换为yolo格式(文件名是xml的文件名)

import re
import os


def to_one(name_list, xmin, ymin, xmax, ymax, width, height, name):
    data = []
    num = 0
    for x1, y1, x2, y2 in zip(xmin, ymin, xmax, ymax):
        x1 = float(x1)
        y1 = float(y1)
        x2 = float(x2)
        y2 = float(y2)
        w1 = float(width[0])
        h1 = float(height[0])

        x = (x2 - x1) / 2 + x1
        y = (y2 - y1) / 2 + y1
        w = x2 - x1
        h = y2 - y1
        x = x / w1
        y = y / h1
        w = w / w1
        h = h / h1
        data.append(' '.join([str(num), str(x), str(y), str(w), str(h),'\n']))
     #   num += 1
    # print(data)
    with open("%s.txt" % name, 'w') as f:
        f.writelines(data)


def xml_to_yolo(path):
    files_list = os.listdir(path)
    files_path = []
    for file in files_list:
        files_path.append(os.path.join(path, file))
    for file in files_path:
        with open(file, 'r') as f:
            data = f.read()
            name_list = re.findall('(.*?)', data)
            xmin = re.findall('(.*?)', data)
            ymin = re.findall('(.*?)', data)
            xmax = re.findall('(.*?)', data)
            ymax = re.findall('(.*?)', data)
            width = re.findall('(.*?)', data)
            height = re.findall('(.*?)', data)
            to_one(name_list, xmin, ymin, xmax, ymax, width, height,file.split('\\')[6].split('.')[0])

def make_dir():
    if os.path.exists('.//lables'):
        os.chdir(".//lables")
    else:
        os.makedirs(".//lables")
        os.chdir(".//lables")


if __name__ == '__main__':
    i = 1
    make_dir()
    xml_to_yolo('E:\\pythonProject\\pascalVOC2yolov5\\VOCdevkit\\VOC2012\\Annotations')
    print('完成')

你可能感兴趣的:(yolov5,深度学习)