YOLO格式数据集和VOC格式数据集互转（txt&xml）

缺乏、安全感 2024-04-03 12:49 97阅读 0赞

> 前言
> 
> 一、voc转yolo（xml转txt）
> 
> 二、yolo转voc（txt转xml）

--------------------

## 前言 ##

在使用labelimg进行数据标注时可以将结果保存为yolo格式或者voc格式，但是发现要是想用labelimg打开yolo识别后的txt就不行了，在训练ai的时候我们可以用已经有的结果识别一遍图片，然后再进行查漏补缺，这样子效率会更高，这里出一个YOLO的txt与voc的xml相互转换源代码

--------------------

## 一、voc转yolo（xml转txt） ##

import xml.etree.ElementTree as ET
    import pickle
    import os
    from os import listdir, getcwd
    from os.path import join
     
     
    def convert(size, box):
     
        x_center = (box[0] + box[1]) / 2.0
        y_center = (box[2] + box[3]) / 2.0
        x = x_center / size[0]
        y = y_center / size[1]
     
        w = (box[1] - box[0]) / size[0]
        h = (box[3] - box[2]) / size[1]
        
        return (x, y, w, h)
     
     
    def convert_annotation(xml_files_path, save_txt_files_path, classes):
        xml_files = os.listdir(xml_files_path)
        print(xml_files)
        for xml_name in xml_files:
            print(xml_name)
            xml_file = os.path.join(xml_files_path, xml_name)
            out_txt_path = os.path.join(save_txt_files_path, xml_name.split('.')[0] + '.txt')
            out_txt_f = open(out_txt_path, 'w')
            tree = ET.parse(xml_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))
                # b=(xmin, xmax, ymin, ymax)
                print(w, h, b)
                bb = convert((w, h), b)
                out_txt_f.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
     
     
    if __name__ == "__main__":
        # 把voc的xml标签文件转化为yolo的txt标签文件
        # 1、类别
        classes1 = ['1','4']
        # 2、voc格式的xml标签文件路径
        xml_files1 = r'xml2'
        # 3、转化为yolo格式的txt标签文件存储路径
        save_txt_files1 = r'txt3'
        convert_annotation(xml_files1, save_txt_files1, classes1)

将以上代码拷贝到一个py文件里，修改xml\_files1与save\_txt\_files1为自己文件所在的相对路径，修改classes为自己标注的类别，cmd切换到当前py文件路径下，python \*\*\*.py 即可。

## 二、yolo转voc（txt转xml） ##

与上面代码一样，这里需要修改如下四条为自己对应的路径与类别

1.  voc\_annotations = r'1010-01xml'
2.  yolo\_txt = r'1010-01txt'
3.  img\_path = r'1010-01photo'
4.  labels = \['1','4'\] \# label for datasets

import os
    import glob
    from PIL import Image
    
    voc_annotations = r'1010-01xml'
    yolo_txt = r'1010-01txt'
    img_path = r'1010-01photo'
    labels = ['1','4']  # label for datasets
    # 图像存储位置
    src_img_dir = img_path  # 添加你的路径
    # 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>')