voc与txt互转

voc2txt

# coding:utf-8
from __future__ import print_function

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


def xml_reader(filename):
    """ Parse a PASCAL VOC xml file """
    tree = ET.parse(filename)
    size = tree.find('size')
    width = int(size.find('width').text)
    height = int(size.find('height').text)
    objects = []
    for obj in tree.findall('object'):
        obj_struct = {}
        obj_struct['name'] = obj.find('name').text
        bbox = obj.find('bndbox')
        obj_struct['bbox'] = [int(bbox.find('xmin').text),
                              int(bbox.find('ymin').text),
                              int(bbox.find('xmax').text),
                              int(bbox.find('ymax').text)]
        objects.append(obj_struct)
    return width, height, objects


def voc2yolo(filename):
    classes_dict = {}
    with open("classes.names的路径") as f:
        for idx, line in enumerate(f.readlines()):
            class_name = line.strip()
            classes_dict[class_name] = idx

    width, height, objects = xml_reader(filename)

    lines = []
    for obj in objects:
        x, y, x2, y2 = obj['bbox']
        class_name = obj['name']
        label = classes_dict[class_name]
        cx = (x2 + x) * 0.5 / width
        cy = (y2 + y) * 0.5 / height
        w = (x2 - x) * 1. / width
        h = (y2 - y) * 1. / height
        line = "%s %.6f %.6f %.6f %.6f\n" % (label, cx, cy, w, h)
        lines.append(line)

    txt_name = filename.replace(".xml", ".txt").replace("voc_labels", "labels")
    with open(txt_name, "w") as f:
        f.writelines(lines)


def get_image_list(image_dir, suffix=['jpg', 'jpeg', 'JPG', 'JPEG', 'png']):
    '''get all image path ends with suffix'''
    if not os.path.exists(image_dir):
        print("PATH:%s not exists" % image_dir)
        return []
    imglist = []
    for root, sdirs, files in os.walk(image_dir):
        if not files:
            continue
        for filename in files:
            filepath = os.path.join(root, filename) + "\n"
            if filename.split('.')[-1] in suffix:
                imglist.append(filepath)
    return imglist


def imglist2file(imglist):
    random.shuffle(imglist)
    train_list = imglist[:-100]
    valid_list = imglist[-100:]
    with open("train.txt", "w") as f:
        f.writelines(train_list)
    with open("valid.txt", "w") as f:
        f.writelines(valid_list)


if __name__ == "__main__":
    xml_path_list = glob.glob("xml类型的标注文件目录/*.xml")
    for xml_path in xml_path_list:
        voc2yolo(xml_path)

    imglist = get_image_list("标注原图位置")
    imglist2file(imglist)

txt2voc

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


def makexml(picPath, txtPath, xmlPath):  # txt所在文件夹路径，xml文件保存路径，图片所在文件夹路径
    """此函数用于将yolo格式txt标注文件转换为voc格式xml标注文件
    """
    dic = {'0': "boat"}
    files = os.listdir(txtPath)
    for i, name in enumerate(files):
        xmlBuilder = Document()
        annotation = xmlBuilder.createElement("annotation")  # 创建annotation标签
        xmlBuilder.appendChild(annotation)
        txtFile = open(txtPath + name)
        txtList = txtFile.readlines()
        img = cv2.imread(picPath + name[0:-4] + ".jpg")
        Pheight, Pwidth, Pdepth = img.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(name[0:-4] + ".jpg")
        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 j in txtList:
            oneline = j.strip().split(" ")
            object = xmlBuilder.createElement("object")  # object 标签
            picname = xmlBuilder.createElement("name")  # name标签
            namecontent = xmlBuilder.createTextNode(dic[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

        f = open(xmlPath + name[0:-4] + ".xml", 'w')
        xmlBuilder.writexml(f, indent='\t', newl='\n', addindent='\t', encoding='utf-8')
        f.close()


if __name__ == "__main__":
    picPath = "images_test/images/"  # 图片所在文件夹路径，后面的/一定要带上
    txtPath = "images_test/labels/"  # txt所在文件夹路径，后面的/一定要带上
    xmlPath = "images_test/xml/"  # xml文件保存路径，后面的/一定要带上
    makexml(picPath, txtPath, xmlPath)