下载数据集(yolov3格式)并转化为VOC的xml文件

下载数据集(yolov3格式)并转化为VOC的xml文件

寻找数据集

https://blog.csdn.net/sinat_35907936/article/details/88911770
这个博客讲的非常清楚,叫你如何下载yolov3格式的数据集。
下载完后每个.txt文件格式为 <x_center> <y_center>

对数据集中的lables转换为xml格式

from xml.dom.minidom import Document
import os
import os.path
from PIL import Image

ann_path = "D:\\DS\\person_head\\labels\\" #yolov3标注.txt文件夹
img_path = "D:\\DS\\person_head\\Human_head+Hat\\" #图片文件夹
xml_path = "D:\\DS\\Person_head\\annotations\\" #  .xml文件存放地址

if not os.path.exists(xml_path):
    os.mkdir(xml_path)


def writeXml(tmp, imgname, w, h, objbud, wxml):
    doc = Document()
    # owner
    annotation = doc.createElement('annotation')
    doc.appendChild(annotation)
    # owner
    folder = doc.createElement('folder')
    annotation.appendChild(folder)
    folder_txt = doc.createTextNode("VOC2005")
    folder.appendChild(folder_txt)

    filename = doc.createElement('filename')
    annotation.appendChild(filename)
    filename_txt = doc.createTextNode(imgname)
    filename.appendChild(filename_txt)
    # ones#
    source = doc.createElement('source')
    annotation.appendChild(source)

    database = doc.createElement('database')
    source.appendChild(database)
    database_txt = doc.createTextNode("The VOC2005 Database")
    database.appendChild(database_txt)

    annotation_new = doc.createElement('annotation')
    source.appendChild(annotation_new)
    annotation_new_txt = doc.createTextNode("PASCAL VOC2005")
    annotation_new.appendChild(annotation_new_txt)

    image = doc.createElement('image')
    source.appendChild(image)
    image_txt = doc.createTextNode("flickr")
    image.appendChild(image_txt)
    # onee#
    # twos#
    size = doc.createElement('size')
    annotation.appendChild(size)

    width = doc.createElement('width')
    size.appendChild(width)
    width_txt = doc.createTextNode(str(w))
    width.appendChild(width_txt)

    height = doc.createElement('height')
    size.appendChild(height)
    height_txt = doc.createTextNode(str(h))
    height.appendChild(height_txt)

    depth = doc.createElement('depth')
    size.appendChild(depth)
    depth_txt = doc.createTextNode("3")
    depth.appendChild(depth_txt)
    # twoe#
    segmented = doc.createElement('segmented')
    annotation.appendChild(segmented)
    segmented_txt = doc.createTextNode("0")
    segmented.appendChild(segmented_txt)

    for i in range(0, int(len(objbud))):
        objbuds=objbud[i].split(' ')
        #print(objbuds)
        # threes#
        object_new = doc.createElement("object")
        annotation.appendChild(object_new)

        name = doc.createElement('name')
        object_new.appendChild(name)
        name_txt = doc.createTextNode(objbuds[0])
        name.appendChild(name_txt)

        pose = doc.createElement('pose')
        object_new.appendChild(pose)
        pose_txt = doc.createTextNode("Unspecified")
        pose.appendChild(pose_txt)

        truncated = doc.createElement('truncated')
        object_new.appendChild(truncated)
        truncated_txt = doc.createTextNode("0")
        truncated.appendChild(truncated_txt)

        difficult = doc.createElement('difficult')
        object_new.appendChild(difficult)
        difficult_txt = doc.createTextNode("0")
        difficult.appendChild(difficult_txt)
        # threes-1#
        bndbox = doc.createElement('bndbox')
        object_new.appendChild(bndbox)

        xmin = doc.createElement('xmin')
        bndbox.appendChild(xmin)
        xmin_txt = doc.createTextNode(str(int((float(objbuds[1])*w - float(objbuds[3])*w/2.0))))
        xmin.appendChild(xmin_txt)

        ymin = doc.createElement('ymin')
        bndbox.appendChild(ymin)
        ymin_txt = doc.createTextNode(str(int(float(objbuds[2])*h - float(objbuds[4])*h/2.0)))
        ymin.appendChild(ymin_txt)

        xmax = doc.createElement('xmax')
        bndbox.appendChild(xmax)
        xmax_txt = doc.createTextNode(str(int(float(objbuds[1])*w + float(objbuds[3])*w/2.0)))
        xmax.appendChild(xmax_txt)

        ymax = doc.createElement('ymax')
        bndbox.appendChild(ymax)
        ymax_txt = doc.createTextNode(str(int(float(objbuds[2])*h + float(objbuds[4])*h/2)))
        ymax.appendChild(ymax_txt)
        # threee-1#
        # threee#

    tempfile = tmp + "test.xml"
    with open(tempfile, "w") as f:
        f.write(doc.toprettyxml(indent='\t'))

    rewrite = open(tempfile, "r")
    lines = rewrite.read().split('\n')
    newlines = lines[1:len(lines) - 1]

    fw = open(wxml, "w")
    for i in range(0, len(newlines)):
        fw.write(newlines[i] + '\n')

    fw.close()
    rewrite.close()
    os.remove(tempfile)
    return


for files in os.walk(ann_path):
    temp = "C:\\temp\\"
    if not os.path.exists(temp):
        os.mkdir(temp)
    for file in files[2]:
        print (file + "-->start!")
        img_name = os.path.splitext(file)[0] + '.jpg'
        fileimgpath = img_path + img_name
        im = Image.open(fileimgpath)
        width = int(im.size[0])
        height = int(im.size[1])

        filelabel = open(ann_path + file, "r")
        lines = filelabel.read().split('\n')
        obj = lines[:len(lines)-1]
        #print(obj)

        filename = xml_path + os.path.splitext(file)[0] + '.xml'
        writeXml(temp, img_name, width, height, obj, filename)
    os.rmdir(temp)
评论 4
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值