voc数据集与yolo数据集格式 互相转换

 1. voc转yolo

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

sets = ['trainval','test']

classes = [ 'aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus', 'car', 'cat', 'chair', 'cow', 'diningtable', 'dog',
         'horse', 'motorbike', 'person', 'pottedplant', 'sheep', 'sofa', 'train', 'tvmonitor' ] # voc的20个类别


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('./model/dataset/VOCdevkit/VOC2007/Annotations/%s.xml' % (image_id))
    #填原来voc数据集xml标注数据文件所在路径
    out_file = open('./labels/test/%s.txt' % (image_id), 'w')
    #填转换后的yolov5需要labels文件所在路径
    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')

# if __name__ == "__main__":


wd = getcwd()

for image_set in sets:
    if not os.path.exists('./labels/'):
        os.makedirs('./labels/')
    #创建转换后labels存放文件路径

    image_ids = open('./model/dataset/VOCdevkit/VOC2007/ImageSets/Main/%s.txt' % (image_set)).read().strip().split()
    #list_file = open('./%s.txt' % (image_set), 'w')

    for image_id in image_ids:
        #list_file.write('dataset/VOCdevkit/VOC2007/JPEGImages/%s.jpg\n' % (image_id))
        convert_annotation(image_id)
    list_file.close()

以上代码可以将voc格式的xml注释文件转换成yolov5格式的labels注释文件，只需要将路径改为自己的，直接运行即可。

2.yolo转voc

import os
import glob
from PIL import Image

voc_annotations = 'voc_test/Annotations/'
yolo_txt = 'yolo_test/labels/'
img_path = 'yolo_test/images/'

labels = [ 'aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus', 'car', 'cat', 'chair', 'cow', 'diningtable', 'dog',
         'horse', 'motorbike', 'person', 'pottedplant', 'sheep', 'sofa', 'train', 'tvmonitor' ] # label for datasets


# 图像存储位置
src_img_dir = img_path 
# 图像的txt文件存放位置


src_txt_dir = yolo_txt
src_xml_dir = voc_annotations

img_Lists = glob.glob(src_img_dir + '/*.jpg')

img_basenames = []
for item in img_Lists:
    img_basenames.append(os.path.basename(item))

img_names = []
for item in img_basenames:
    temp1, temp2 = os.path.splitext(item)
    img_names.append(temp1)

for img in img_names:
    im = Image.open((src_img_dir + '/' + img + '.jpg'))
    width, height = im.size

    # 打开txt文件
    gt = open(src_txt_dir + '/' + img + '.txt').read().splitlines()
    print(gt)
    if gt:
        # 将主干部分写入xml文件中
        xml_file = open((src_xml_dir + '/' + img + '.xml'), 'w')
        xml_file.write('<annotation>\n')
        xml_file.write('    <folder>VOC2007</folder>\n')
        xml_file.write('    <filename>' + str(img) + '.jpg' + '</filename>\n')
        xml_file.write('    <size>\n')
        xml_file.write('        <width>' + str(width) + '</width>\n')
        xml_file.write('        <height>' + str(height) + '</height>\n')
        xml_file.write('        <depth>3</depth>\n')
        xml_file.write('    </size>\n')

        # write the region of image on xml file
        for img_each_label in gt:
            spt = img_each_label.split(' ')  # 这里如果txt里面是以逗号‘，’隔开的，那么就改为spt = img_each_label.split(',')。
            print(f'spt:{spt}')
            xml_file.write('    <object>\n')
            xml_file.write('        <name>' + str(labels[int(spt[0])]) + '</name>\n')
            xml_file.write('        <pose>Unspecified</pose>\n')
            xml_file.write('        <truncated>0</truncated>\n')
            xml_file.write('        <difficult>0</difficult>\n')
            xml_file.write('        <bndbox>\n')

            center_x = round(float(spt[1].strip()) * width)
            center_y = round(float(spt[2].strip()) * height)
            bbox_width = round(float(spt[3].strip()) * width)
            bbox_height = round(float(spt[4].strip()) * height)
            xmin = str(int(center_x - bbox_width / 2))
            ymin = str(int(center_y - bbox_height / 2))
            xmax = str(int(center_x + bbox_width / 2))
            ymax = str(int(center_y + bbox_height / 2))

            xml_file.write('            <xmin>' + xmin + '</xmin>\n')
            xml_file.write('            <ymin>' + ymin + '</ymin>\n')
            xml_file.write('            <xmax>' + xmax + '</xmax>\n')
            xml_file.write('            <ymax>' + ymax + '</ymax>\n')
            xml_file.write('        </bndbox>\n')
            xml_file.write('    </object>\n')

        xml_file.write('</annotation>')

yolo格式的txt文件转换成 voc的xml格式代码见上图，改路径直接运行（这个参考了Yolo标准数据集格式转Voc数据集_YANJINING-CSDN博客_yolo数据集转voc）

版权声明：本文为CSDN博主「kkcodeer」的原创文章，遵循CC 4.0 BY-SA版权协议，转载请附上原文出处链接及本声明。
原文链接：https://blog.csdn.net/weixin_42148914/article/details/121931849