模型训练时的互转标注文件格式以及标注验证代码（标注文件格式转换和标注验证）

一、标注文件格式转换

1、XML格式转到YOLO格式

# -*- coding: utf-8 -*-
import xml.etree.ElementTree as ET
import os

sets = ['train', 'val', 'test']  # 如果你的Main文件夹没有test.txt，就删掉'test'
# classes = ["a", "b"]   # 改成自己的类别，VOC数据集有以下20类别
classes = ['person']  # class names
abs_path = os.getcwd()


def convert(size, box):
    dw = 1. / (size[0])
    dh = 1. / (size[1])
    x = (box[0] + box[1]) / 2.0 - 1
    y = (box[2] + box[3]) / 2.0 - 1
    w = box[1] - box[0]
    h = box[3] - box[2]
    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(abs_path + '/INRIAPerson/VOCperson/Annotations/%s.xml' % (image_id))
    out_file = open(abs_path + '/INRIAPerson/VOCperson/label/%s.txt' % (image_id), 'w')
    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'):
        difficult = obj.find('difficult').text
        # 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))
        b1, b2, b3, b4 = b
        # 标注越界修正
        if b2 > w:
            b2 = w
        if b4 > h:
            b4 = h
        b = (b1, b2, b3, b4)
        bb = convert((w, h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')


for image_set in sets:
    if not os.path.exists(abs_path + '/INRIAPerson/VOCperson/label/'):
        os.makedirs(abs_path + '/INRIAPerson/VOCperson/label/')

    image_ids = open(abs_path + '/INRIAPerson/VOCperson/ImageSets/Main/%s.txt' % (image_set)).read().strip().split()
    list_file = open(abs_path + '/INRIAPerson/VOCperson/VOC2007/%s.txt' % (image_set), 'w')#文件输出的路径
    for image_id in image_ids:
        list_file.write(abs_path + '/INRIAPerson/VOCperson/JPEGImages/%s.jpg\n' % (image_id))  # 要么自己补全路径，只写一半可能会报错
        convert_annotation(image_id)
    list_file.close()

实现两个功能（1）XML格式标注文件转换到YOLO格式标注文件

                     （2）产生train.txt、val.txt以及test.txt文件的路径形式

下面代码只实现（2）的功能

# -*- coding: utf-8 -*-
import xml.etree.ElementTree as ET
import os

sets = ['train', 'val','test']  # 如果你的Main文件夹没有test.txt，就删掉'test'
# classes = ["a", "b"]   # 改成自己的类别，VOC数据集有以下20类别
classes = ['person']  # class names
abs_path = os.getcwd()

for image_set in sets:


    image_ids = open(abs_path + '/KAIST/ImageSets/Main/%s.txt' % (image_set)).read().strip().split()
    list_file = open(abs_path + '/KAIST/%s.txt' % (image_set), 'w')#文件输出的路径
    for image_id in image_ids:
        list_file.write(abs_path + '/KAIST/Images/%s.jpg\n' % (image_id))  # 要么自己补全路径，只写一半可能会报错

    list_file.close()

2、YOLO格式转到XML格式

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


# def makexml(txtPath, xmlPath, picPath):  # txt所在文件夹路径，xml文件保存路径，图片所在文件夹路径
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
    在自己的标注图片文件夹下建三个子文件夹，分别命名为picture、txt、xml
    """
    dic = {'0': "person",  # 创建字典用来对类型进行转换

           }
    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()
        for root,dirs,filename in os.walk(picPath):
            img = cv2.imread(root+ '\\'+filename[i])
            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 = r"D:\MOT17\images\train"  # 图片所在文件夹路径，后面的/一定要带上
    txtPath = r"D:\MOT17\labels\train"  # yolo txt所在文件夹路径，后面的/一定要带上
    xmlPath = r"D:\MOT17\xml"  # xml文件保存路径，后面的/一定要带上
    makexml(picPath, txtPath, xmlPath)

二、标注验证

1、XML格式文件的验证

# -*- coding: utf-8 -*-
from __future__ import division
import os
import xml.dom.minidom
import cv2
import sys
import numpy as np
# from imp import reload
# reload(sys)

def read_xml(ImgPath, AnnoPath, Savepath):
    imagelist = os.listdir(AnnoPath)
    for image in imagelist:
        image_pre, ext = os.path.splitext(image)
        # imgfile =  +'/'+ image_pre+ '.JPG'
        imgfile = os.path.join(ImgPath,image_pre+ '.jpg')
        # xmlfile = AnnoPath +'/'+ image_pre+ '.xml'
        xmlfile = os.path.join(AnnoPath, image_pre + '.xml')
        print(imgfile)
        print(xmlfile)
        # im = cv2.imread(imgfile)
        im = cv2.imdecode(np.fromfile(imgfile,dtype=np.uint8),cv2.IMREAD_UNCHANGED)#imdecode()读取图像数据并转换成图片格式
        #fromfile()读数据时需要用户指定元素类型，并对数组的形状进行适当的修改，cv2.IMREAD_UNCHANGED加载图像
        DomTree = xml.dom.minidom.parse(xmlfile)#读取xml文件中的值
        annotation = DomTree.documentElement #documentElement 属性可返回文档的根节点。
        filenamelist = annotation.getElementsByTagName('filename')#getElementById()可以访问Documnent中的某一特定元素，顾名思义，就是通过ID来取得元素，所以只能访问设置了ID的元素。
        filename = filenamelist[0].childNodes[0].data
        objectlist = annotation.getElementsByTagName('object')
        i = 1
        for objects in objectlist:
            namelist = objects.getElementsByTagName('name')
            objectname = namelist[0].childNodes[0].data #通过xml文件给图像加目标框
            bndbox = objects.getElementsByTagName('bndbox')
            for box in bndbox:
                try:
                    x1_list = box.getElementsByTagName('xmin')
                    x1 = int(x1_list[0].childNodes[0].data)

                    y1_list = box.getElementsByTagName('ymin')
                    y1 = int(y1_list[0].childNodes[0].data)

                    x2_list = box.getElementsByTagName('xmax')
                    x2 = int(x2_list[0].childNodes[0].data)

                    y2_list = box.getElementsByTagName('ymax')
                    y2 = int(y2_list[0].childNodes[0].data)

                    minX = x1
                    minY = y1
                    maxX = x2
                    maxY = y2
                    if(i % 3 == 0):
                        color = (128,0,0)
                    elif (i % 3 == 1):
                        color = (153, 51, 0)
                    elif (i % 3 == 2):
                        color = (255, 204, 0)
                    elif (i % 3 == 3):
                        color = (0, 51, 0)
                    elif (i % 9 == 4):
                        color = (51, 204, 204)
                    elif (i % 9 == 5):
                        color = (128, 0, 128)
                    elif (i % 9 == 6):
                        color = (0, 255, 255)
                    elif (i % 9 == 7):
                        color = (60, 179, 113)
                    elif (i % 9 == 8):
                        color = (255, 127, 80)
                    elif (i % 9 == 9):
                        color = (0, 255, 0)

                    cv2.rectangle(im,(minX,minY),(maxX,maxY),color,8)
                    if not os.path.exists(Savepath):
                        os.makedirs(Savepath)
                    path = os.path.join(Savepath, image_pre + '.jpg')
                    font = cv2.FONT_HERSHEY_SIMPLEX
                    cv2.putText(im, objectname, (minX,minY - 7), font, 0.7, (0, 0, 255), 2)
                    cv2.imencode(".jpg",im)[1].tofile(path)
                    i += 1
                except Exception as e:
                    print(e)

if __name__ == "__main__":
    img_path = r'D:\person\newtrain\JPEG/'
    xml_path = r'D:\person\newtrain\Annotation/'
    save_path = r'D:\person\newJPEG/'
    read_xml(img_path, xml_path,save_path)

2、YOLO格式文件的验证

import cv2
import os

def draw_box_in_single_image(image_path, txt_path):
    # 读取图像
    image = cv2.imread(image_path)

    # 读取txt文件信息
    def read_list(txt_path):
        pos = []
        with open(txt_path, 'r') as file_to_read:
            while True:
                lines = file_to_read.readline()  # 整行读取数据
                if not lines:
                    break
                # 将整行数据分割处理，如果分割符是空格，括号里就不用传入参数，如果是逗号， 则传入‘，'字符。
                p_tmp = [float(i) for i in lines.split(' ')]
                pos.append(p_tmp)  # 添加新读取的数据
                # Efield.append(E_tmp)
                pass
        return pos


    # txt转换为box
    def convert(size, box):
        xmin = (box[1]-box[3]/2.)*size[1]
        xmax = (box[1]+box[3]/2.)*size[1]
        ymin = (box[2]-box[4]/2.)*size[0]
        ymax = (box[2]+box[4]/2.)*size[0]
        box = (int(xmin), int(ymin), int(xmax), int(ymax))
        return box

    pos = read_list(txt_path)
    print(pos)
    tl = int((image.shape[0]+image.shape[1])/2)
    lf = max(tl-1,1)
    for i in range(len(pos)):
        label = str(int(pos[i][0]))
        print('label is '+label)
        box = convert(image.shape, pos[i])
        image = cv2.rectangle(image,(box[0], box[1]),(box[2],box[3]),(0,0,255),2)
        cv2.putText(image,label,(box[0],box[1]-2), 0, 1, [0,0,255], thickness=2, lineType=cv2.LINE_AA)
        pass

    if pos:
        cv2.imwrite('./VOCData/see_images/{}.png'.format(image_path.split('\\')[-1][:-4]), image)
    else:
        print('None')

    print('./VOCData/see_images/{}.png'.format(image_path.split('\\')[-1][:-4]))
    # cv2.imshow("images", image)
    # cv2.waitKey(0)
    # cv2.destroyAllWindows()


img_folder = "./image/train"
img_list = os.listdir(img_folder)
img_list.sort()

label_folder = "./label/train"
label_list = os.listdir(label_folder)
label_list.sort()
if not os.path.exists('./VOCData/see_images'):
    os.makedirs('./VOCData/see_images')
for i in range(len(img_list)):
    image_path = img_folder + "\\" + img_list[i]
    txt_path = label_folder + "\\" + label_list[i]
    draw_box_in_single_image(image_path, txt_path)