【[labelimg]-- YOLO格式数据集和VOC格式数据集的相互转换】

问题描述

昨天做基于yolov5的缺陷检测，用labeliimg标注文件，直接用YOLO格式的标注方式了，最终生成了txt的文档。下一步要做的就是划分训练验证测试集了，看了各种博客，所以做个总结，以便自己以后使用。

labelimg

可视化标注工具。具体的下载和使用其他博主已经介绍的很详细了。
ubuntu版：labelimg
window版：labelimg

YOLO转VOC --(txt转xml)

import os
import glob
from PIL import Image

voc_annotations = "要保存的xml文件地址" 
yolo_txt = "标注后的txt存放文件" 
img_path = "标注的图片文件"
labels = ['class']  # 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>')

如出现UnicodeDecodeError: ‘utf-8’ 的错误就是编码方式的问题，另存为 utf-8的格式即可。

VOC转YOLO–（xml转txt）

这个文件最好格式规范（应该都懂）。代码出自大神bubbliiiing(不得不说，别人才是大神，咱只是代码的搬运工)

import os
import random
import xml.etree.ElementTree as ET

from utils.utils import get_classes

#--------------------------------------------------------------------------------------------------------------------------------#
#   annotation_mode用于指定该文件运行时计算的内容
#   annotation_mode为0代表整个标签处理过程，包括获得VOCdevkit/VOC2007/ImageSets里面的txt以及训练用的2007_train.txt、2007_val.txt
#   annotation_mode为1代表获得VOCdevkit/VOC2007/ImageSets里面的txt
#   annotation_mode为2代表获得训练用的2007_train.txt、2007_val.txt
#--------------------------------------------------------------------------------------------------------------------------------#
annotation_mode     = 2
#-------------------------------------------------------------------#
#   必须要修改，用于生成2007_train.txt、2007_val.txt的目标信息
#   与训练和预测所用的classes_path一致即可
#   如果生成的2007_train.txt里面没有目标信息
#   那么就是因为classes没有设定正确
#   仅在annotation_mode为0和2的时候有效
#-------------------------------------------------------------------#
classes_path        = 'model_data/voc_classes.txt'
#--------------------------------------------------------------------------------------------------------------------------------#
#   trainval_percent用于指定(训练集+验证集)与测试集的比例，默认情况下 (训练集+验证集):测试集 = 9:1 
#   train_percent用于指定(训练集+验证集)中训练集与验证集的比例，默认情况下 训练集:验证集 = 9:1 
#   仅在annotation_mode为0和1的时候有效
#--------------------------------------------------------------------------------------------------------------------------------#
trainval_percent    = 0.9
train_percent       = 0.9
#-------------------------------------------------------#
#   指向VOC数据集所在的文件夹
#   默认指向根目录下的VOC数据集
#-------------------------------------------------------#
VOCdevkit_path  = 'VOCdevkit'

VOCdevkit_sets  = [('2007', 'train'), ('2007', 'val')]
classes, _      = get_classes(classes_path)

def convert_annotation(year, image_id, list_file):
    in_file = open(os.path.join(VOCdevkit_path, 'VOC%s/Annotations/%s.xml'%(year, image_id)), encoding='utf-8')
    tree=ET.parse(in_file)
    root = tree.getroot()

    for obj in root.iter('object'):
        difficult = 0 
        if obj.find('difficult')!=None:
            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 = (int(float(xmlbox.find('xmin').text)), int(float(xmlbox.find('ymin').text)), int(float(xmlbox.find('xmax').text)), int(float(xmlbox.find('ymax').text)))
        list_file.write(" " + ",".join([str(a) for a in b]) + ',' + str(cls_id))
        
if __name__ == "__main__":
    random.seed(0)
    if annotation_mode == 0 or annotation_mode == 1:
        print("Generate txt in ImageSets.")
        xmlfilepath     = os.path.join(VOCdevkit_path, 'VOC2007/Annotations')
        saveBasePath    = os.path.join(VOCdevkit_path, 'VOC2007/ImageSets/Main')
        temp_xml        = os.listdir(xmlfilepath)
        total_xml       = []
        for xml in temp_xml:
            if xml.endswith(".xml"):
                total_xml.append(xml)

        num     = len(total_xml)  
        list    = range(num)  
        tv      = int(num*trainval_percent)  
        tr      = int(tv*train_percent)  
        trainval= random.sample(list,tv)  
        train   = random.sample(trainval,tr)  
        
        print("train and val size",tv)
        print("train size",tr)
        ftrainval   = open(os.path.join(saveBasePath,'trainval.txt'), 'w')  
        ftest       = open(os.path.join(saveBasePath,'test.txt'), 'w')  
        ftrain      = open(os.path.join(saveBasePath,'train.txt'), 'w')  
        fval        = open(os.path.join(saveBasePath,'val.txt'), 'w')  
        
        for i in list:  
            name=total_xml[i][:-4]+'\n'  
            if i in trainval:  
                ftrainval.write(name)  
                if i in train:  
                    ftrain.write(name)  
                else:  
                    fval.write(name)  
            else:  
                ftest.write(name)  
        
        ftrainval.close()  
        ftrain.close()  
        fval.close()  
        ftest.close()
        print("Generate txt in ImageSets done.")

    if annotation_mode == 0 or annotation_mode == 2:
        print("Generate 2007_train.txt and 2007_val.txt for train.")
        for year, image_set in VOCdevkit_sets:
            image_ids = open(os.path.join(VOCdevkit_path, 'VOC%s/ImageSets/Main/%s.txt'%(year, image_set)), encoding='utf-8').read().strip().split()
            list_file = open('%s_%s.txt'%(year, image_set), 'w', encoding='utf-8')
            for image_id in image_ids:
                list_file.write('%s/VOC%s/JPEGImages/%s.jpg'%(os.path.abspath(VOCdevkit_path), year, image_id))

                convert_annotation(year, image_id, list_file)
                list_file.write('\n')
            list_file.close()
        print("Generate 2007_train.txt and 2007_val.txt for train done.")

运行成功后直接划分了训练验证集，之后训练即可。