yolo训练数据集将xml文件转为txt文件

最新推荐文章于 2023-11-07 19:12:32 发布

claire6161

最新推荐文章于 2023-11-07 19:12:32 发布

阅读量4.2k

点赞数 1

分类专栏： python 文章标签： yolo

本文链接：https://blog.csdn.net/weixin_43802384/article/details/103049499

版权

python 专栏收录该内容

3 篇文章 0 订阅

订阅专栏

代码如下，记得删掉注释！

import xml.etree.ElementTree as ET
import pickle
import string
import os
import shutil
from os import listdir, getcwd
from os.path import join
import cv2
 
sets=[('2012', 'train')] 　#不用管
 
classes = ["car","person"]　　#类别 0是车  1是人
 
def convert(size, box):
    dw = 1./size[0]
    dh = 1./size[1]
    x = (box[0] + box[1])/2.0
    y = (box[2] + box[3])/2.0
    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,flag,savepath):
 
    if flag == 0:
        in_file = open(savepath+'/trainImageXML/%s.xml' % (os.path.splitext(image_id)[0]))  #输入：xml文件夹名字
        out_file = open(savepath+'/trainImage/%s.txt' % (os.path.splitext(image_id)[0]), 'w')  #输出：txt文件夹名字
        tree = ET.parse(in_file)
        root = tree.getroot()
        size = root.find('size')
 
        img = cv2.imread('./trainImage/'+str(image_id)) #读取图像文件夹
        h = img.shape[0]
        w = img.shape[1]
 
    elif flag == 1:
        in_file = open(savepath+'/validateImageXML/%s.xml' % (os.path.splitext(image_id)[0]))
        out_file = open(savepath+'/validateImage/%s.txt' % (os.path.splitext(image_id)[0]), 'w')
 
        tree = ET.parse(in_file)
        root = tree.getroot()
        size = root.find('size')
 
        img = cv2.imread('./validateImage/' + str(image_id))
        h = img.shape[0]
        w = img.shape[1]
 
    for obj in root.iter('object'):
        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))
        bb = convert((w,h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
 
wd = getcwd()
 
for year, image_set in sets:
    savepath = os.getcwd();
    idtxt = savepath + "/validateImageId.txt";
    pathtxt = savepath + "/validateImagePath.txt";
    image_ids = open(idtxt).read().strip().split()
    list_file = open(pathtxt, 'w')
    s = '\xef\xbb\xbf'
    for image_id in image_ids:
        nPos = image_id.find(s)
        if nPos >= 0:
            image_id = image_id[3:]
        list_file.write('%s/validateImage/%s\n' % (wd, image_id))
        print(image_id)
        convert_annotation(image_id, 1, savepath)
    list_file.close()
 
    idtxt = savepath + "/trainImageId.txt";  #只包含图像名字的文件，没有路径
    pathtxt = savepath + "/trainImagePath.txt" ;   #保存的txt文件名，里面包含图片的地址路径
    image_ids = open(idtxt).read().strip().split()
    list_file = open(pathtxt, 'w')
    s = '\xef\xbb\xbf'
    for image_id in image_ids:
        nPos = image_id.find(s)
        if nPos >= 0:
           image_id = image_id[3:]
        list_file.write('%s/trainImage/%s\n'%(wd,image_id)) #为图像所在文件夹
        print(image_id)
        convert_annotation(image_id,0,savepath)
    list_file.close()