YOLO格式转PASCAL VOC格式

原作者代码限定了只能处理“jpg”文件，以及路径输入需要“/”等情况。

修改完善后可支持不同类型图片。

# -*-  coding = utf-8 -*-
# @Time : 2022/9/8 11:57
# @Autor : XinJunWei
# @File : yolo_2_voc.py
# @Software : PyCharm

import os
import cv2
import pathlib
from xml.dom.minidom import Document

# 支持多种格式图片,可以自己添加
# 这么做是为了适应不同文件名，比如 'xxx.xxx xx.jpeg'等
def search_file_name(file_path,img_root):
    file_format = ['.jpg','.JPG','.png','.PNG','.JPEG','.jpeg']
    file_path = pathlib.Path(file_path)
    file_name = file_path.stem
    for endsw in file_format:
        file_judge = file_name + endsw
        if os.path.isfile(os.path.join(img_root,file_judge)):
            return file_name,endsw
    return 'stop',0

def yolo2voc(src_img_root, src_label_root, dst_label_root,class_map):
    """
    src_img_root:图片路径（需要获取图片shape）
    src_label_root：输入label路径（YOLO的txt格式）
    dst_label_root：输出label路径（PASCAL VOC的xml格式）
    target：讲txt格式转为xml格式
    """
    not_have_img = []
    if not os.path.exists(dst_label_root):
        os.makedirs(dst_label_root)
    # 遍历所有txt文件
    for i, src_label_name in enumerate(os.listdir(src_label_root)):
        xmlBuilder = Document()
        annotation = xmlBuilder.createElement("annotation")  # 创建annotation标签
        xmlBuilder.appendChild(annotation)
        src_label_path = os.path.join(src_label_root,src_label_name)
        file_name,endsw = search_file_name(src_label_path,src_img_root)
        if file_name == 'stop':
            not_have_img.append(os.path.basename(src_label_path))
            continue
        with open(src_label_path, 'r') as fr:
            txtlines = fr.readlines()
        src_img_name = file_name + endsw
        src_img_path = os.path.join(src_img_root,src_img_name)
        image_np = cv2.imread(src_img_path)
        Pheight, Pwidth, Pdepth = image_np.shape
        folder = xmlBuilder.createElement("folder")  # folder标签
        foldercontent = xmlBuilder.createTextNode("driving_annotation_dataset")
        folder.appendChild(foldercontent)
        annotation.appendChild(folder)  # folder标签结束

        filename = xmlBuilder.createElement("filename")  # filename标签
        filenamecontent = xmlBuilder.createTextNode(src_img_name)
        filename.appendChild(filenamecontent)
        annotation.appendChild(filename)  # filename标签结束

        size = xmlBuilder.createElement("size")  # size标签
        width = xmlBuilder.createElement("width")  # size子标签width
        widthcontent = xmlBuilder.createTextNode(str(Pwidth))
        width.appendChild(widthcontent)
        size.appendChild(width)  # size子标签width结束

        height = xmlBuilder.createElement("height")  # size子标签height
        heightcontent = xmlBuilder.createTextNode(str(Pheight))
        height.appendChild(heightcontent)
        size.appendChild(height)  # size子标签height结束

        depth = xmlBuilder.createElement("depth")  # size子标签depth
        depthcontent = xmlBuilder.createTextNode(str(Pdepth))
        depth.appendChild(depthcontent)
        size.appendChild(depth)  # size子标签depth结束
        annotation.appendChild(size)  # size标签结束
        for line in txtlines:
            oneline = line.strip().split(" ")
            object = xmlBuilder.createElement("object")  # object 标签
            picname = xmlBuilder.createElement("name")  # name标签
            namecontent = xmlBuilder.createTextNode(class_map[oneline[0]])
            picname.appendChild(namecontent)
            object.appendChild(picname)  # name标签结束

            pose = xmlBuilder.createElement("pose")  # pose标签
            posecontent = xmlBuilder.createTextNode("Unspecified")
            pose.appendChild(posecontent)
            object.appendChild(pose)  # pose标签结束

            truncated = xmlBuilder.createElement("truncated")  # truncated标签
            truncatedContent = xmlBuilder.createTextNode("0")
            truncated.appendChild(truncatedContent)
            object.appendChild(truncated)  # truncated标签结束

            difficult = xmlBuilder.createElement("difficult")  # difficult标签
            difficultcontent = xmlBuilder.createTextNode("0")
            difficult.appendChild(difficultcontent)
            object.appendChild(difficult)  # difficult标签结束

            bndbox = xmlBuilder.createElement("bndbox")  # bndbox标签
            xmin = xmlBuilder.createElement("xmin")  # xmin标签
            mathData = int(((float(oneline[1])) * Pwidth + 1) - (float(oneline[3])) * 0.5 * Pwidth)
            xminContent = xmlBuilder.createTextNode(str(mathData))
            xmin.appendChild(xminContent)
            bndbox.appendChild(xmin)  # xmin标签结束

            ymin = xmlBuilder.createElement("ymin")  # ymin标签
            mathData = int(((float(oneline[2])) * Pheight + 1) - (float(oneline[4])) * 0.5 * Pheight)
            yminContent = xmlBuilder.createTextNode(str(mathData))
            ymin.appendChild(yminContent)
            bndbox.appendChild(ymin)  # ymin标签结束

            xmax = xmlBuilder.createElement("xmax")  # xmax标签
            mathData = int(((float(oneline[1])) * Pwidth + 1) + (float(oneline[3])) * 0.5 * Pwidth)
            xmaxContent = xmlBuilder.createTextNode(str(mathData))
            xmax.appendChild(xmaxContent)
            bndbox.appendChild(xmax)  # xmax标签结束

            ymax = xmlBuilder.createElement("ymax")  # ymax标签
            mathData = int(((float(oneline[2])) * Pheight + 1) + (float(oneline[4])) * 0.5 * Pheight)
            ymaxContent = xmlBuilder.createTextNode(str(mathData))
            ymax.appendChild(ymaxContent)
            bndbox.appendChild(ymax)  # ymax标签结束
            object.appendChild(bndbox)  # bndbox标签结束
            annotation.appendChild(object)  # object标签结束
        dst_label_path = os.path.join(dst_label_root,file_name + '.xml')
        with open(dst_label_path,'w') as f:
            xmlBuilder.writexml(f, indent='\t', newl='\n', addindent='\t', encoding='utf-8')
        print(src_img_path)
    print('not have img:',not_have_img,'\n',not_have_img.__len__())


if __name__ == "__main__":
    #注意： opencv 不支持中文路径，路径及文件名需要是英文数字符号等
    src_img_root = "/home/fnce"
    src_label_root = "/home/label"
    dst_label_root = "/home/dst_label"
    # txt文件中每列第一个为类别序号，分别对应label名
    class_map = {'0': "cross",'1': "person",'2':'ce'}
    yolo2voc(src_img_root, src_label_root, dst_label_root,class_map)