yolo图像检测数据集格式转换：xml 与 txt格式相互转换

格式介绍

一图流介绍的比较详细，一般图像检测数据集格式为txt或者xml格式，在使用labelimg进行标注的时候，可以设置获得不同格式的数据集，以满足不同算法训练格式要求：

一般建议使用pascalVoc:即PASCAL VOC数据集格式，关于该数据集的参见：PASCAL VOC
因为这样的数据方便在标注软件中看到对应的框；

xml转txt

对于xml格式数据集，如果要用yolo对其进行使用时候，先将其转化为txt格式，再进行训练，转换代码：

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import copy
from lxml.etree import Element, SubElement, tostring, ElementTree

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

classes = ["0", "1", "2", "3"]  # 类别

CURRENT_DIR = os.path.dirname(os.path.abspath(__file__))


def convert(size, box):
    dw = 1. / size[0]
    dh = 1. / size[1]
    x = (box[0] + box[1]) / 2.0    # (x_min + x_max) / 2.0
    y = (box[2] + box[3]) / 2.0    # (y_min + y_max) / 2.0
    w = box[1] - box[0]   # x_max - x_min
    h = box[3] - box[2]   # y_max - y_min
    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('./label_xml\%s.xml' % (image_id), encoding='UTF-8')

    out_file = open('./label_txt\%s.txt' % (image_id), 'w')  # 生成txt格式文件
    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'):
        cls = obj.find('name').text
        # print(cls)
        if cls not in classes:
            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')

xml_path = os.path.join(CURRENT_DIR, './label_xml/')

# xml list
img_xmls = os.listdir(xml_path)
for img_xml in img_xmls:
    label_name = img_xml.split('.')[0]
    print(label_name)
    convert_annotation(label_name)

txt转xml

txt格式的数据不方便进行一些数据增强操作，可以先将其转换成xml格式后再进行相关标注工作或者
增强操作；

#!/user/bin/env python3
# _*_ coding:utf-8 -*_
# using: 将yolo txt label 转换成xml标签

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

def makexml(txtPath, xmlPath, picPath):  # 读取txt路径，xml保存路径，数据集图片所在路径
        dict = {'0': "0",  # 字典对类型进行转换
                '1': "1",
                '2': "2",
                '3': "3"}
        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
          flag = 0
          for i in txtList:
          	 flag += 1
             oneline = i.strip().split(" ")
             folder = xmlBuilder.createElement("folder")  # folder标签
             folderContent = xmlBuilder.createTextNode("VOC2007")
             folder.appendChild(folderContent)
             annotation.appendChild(folder)
             if flag == 1:
             	filename = xmlBuilder.createElement("filename")  # filename标签
             	filenameContent = xmlBuilder.createTextNode(name[0:-4]+".jpg")
             	filename.appendChild(filenameContent)
             	annotation.appendChild(filename)

             	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)
             	height = xmlBuilder.createElement("height")  # size子标签height
             	heightContent = xmlBuilder.createTextNode(str(Pheight))
             	height.appendChild(heightContent)
             	size.appendChild(height)
             	depth = xmlBuilder.createElement("depth")  # size子标签depth
             	depthContent = xmlBuilder.createTextNode(str(Pdepth))
             	depth.appendChild(depthContent)
             	size.appendChild(depth)
             	annotation.appendChild(size)

             object = xmlBuilder.createElement("object")
             picname = xmlBuilder.createElement("name")
             nameContent = xmlBuilder.createTextNode(dict[oneline[0]])
             picname.appendChild(nameContent)
             object.appendChild(picname)
             pose = xmlBuilder.createElement("pose")
             poseContent = xmlBuilder.createTextNode("Unspecified")
             pose.appendChild(poseContent)
             object.appendChild(pose)
             truncated = xmlBuilder.createElement("truncated")
             truncatedContent = xmlBuilder.createTextNode("0")
             truncated.appendChild(truncatedContent)
             object.appendChild(truncated)
             difficult = xmlBuilder.createElement("difficult")
             difficultContent = xmlBuilder.createTextNode("0")
             difficult.appendChild(difficultContent)
             object.appendChild(difficult)
             bndbox = xmlBuilder.createElement("bndbox")
             xmin = xmlBuilder.createElement("xmin")
             mathData=int(((float(oneline[1]))*Pwidth+1)-(float(oneline[3]))*0.5*Pwidth)
             xminContent = xmlBuilder.createTextNode(str(mathData))
             xmin.appendChild(xminContent)
             bndbox.appendChild(xmin)
             ymin = xmlBuilder.createElement("ymin")
             mathData = int(((float(oneline[2]))*Pheight+1)-(float(oneline[4]))*0.5*Pheight)
             yminContent = xmlBuilder.createTextNode(str(mathData))
             ymin.appendChild(yminContent)
             bndbox.appendChild(ymin)
             xmax = xmlBuilder.createElement("xmax")
             mathData = int(((float(oneline[1]))*Pwidth+1)+(float(oneline[3]))*0.5*Pwidth)
             xmaxContent = xmlBuilder.createTextNode(str(mathData))
             xmax.appendChild(xmaxContent)
             bndbox.appendChild(xmax)
             ymax = xmlBuilder.createElement("ymax")
             mathData = int(((float(oneline[2]))*Pheight+1)+(float(oneline[4]))*0.5*Pheight)
             ymaxContent = xmlBuilder.createTextNode(str(mathData))
             ymax.appendChild(ymaxContent)
             bndbox.appendChild(ymax)
             object.appendChild(bndbox)

             annotation.appendChild(object)

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


makexml("./label_txt/","./label_xml/","./image/")

其中：

• label_txt: 存放txt格式的文件
• label_xml: 存放xml格式的文件
• image: 存放本地图片

参考

• https://arleyzhang.github.io/articles/1dc20586/
• https://zhuanlan.zhihu.com/p/58392978