ディープラーニング yolo | データセットの準備

yolo2xml.py は、yolo 形式の txt タグを xml タグに変換します

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': "ball1",
           '1': "ball2",
           '2': "0degree",  # 创建字典用来对类型进行转换
           '3': "6degree",  # 此处的字典要与自己的classes.txt文件中的类对应，且顺序要一致
           '4': "12degree",'5': "18degree",'6': "24degree",'7': "30degree",'8': "36degree",'9': "42degree",'10': "48degree",'11': "54degree",'12': "60degree",'13': "66degree",'14': "72degree",'15': "78degree",'16': "84degree",'17': "90degree",'18': "96degree",'19': "102degree",'20': "108degree",'21': "114degree",'22': "120degree",'23': "126degree",'24': "132degree",
           '25': "138degree",'26': "144degree",'27': "150degree",'28': "156degree",'29': "162degree",'30': "168degree",'31': "174degree",'32': "180degree",
           }
    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"G:\make_1.2M_6D_VOCdevkit\VOC2007\JPEGImages"  # 图片所在文件夹路径，后面的/一定要带上
    txtPath = r"G:\make_1.2M_6D_VOCdevkit\VOC2007\YOLOTXT"  # yolo txt所在文件夹路径，后面的/一定要带上
    xmlPath = r"G:\make_1.2M_6D_VOCdevkit\VOC2007\Annotations"  # xml文件保存路径，后面的/一定要带上
    makexml(picPath, txtPath, xmlPath)

Bath_txt.py は txt タグをバッチで生成します。

#批量生成txt标签
#一个文件夹里有一个txt文档和608张JPG图像，复制608个txt，将txt文档里的内容分别写入608个txt,txt文档name为对应的JPG的name
import glob
import os
import shutil

Path=r"G:\1.2M_6D_data"
for root,dirs,filename in os.walk(Path):
    for i in range(len(filename)):
        if filename[i].endswith('.mat'):
            os.remove(root+"\\"+filename[i])
        with open(root+"\\"+filename[1],'r') as f:
            content=f.read()
            print(content)
        if filename[i].endswith('jpg'):
            name = filename[i].split('.')[0]
            print(name)
            new_txt=root+"\\"+name+'.txt' #创建txt文件
            with open(new_txt,'w') as ff:
             ff.write(content)

class2list.py は、classes.txt 内のクラス名をリスト形式で出力するために使用されます。

result = []
with open(r'C:\Users\YUXIAOYANG\Desktop\1.2M_6D_data\classes.txt' ,'r') as f:
    for line in f:
     result.append(line.strip().split(',')[0])  #a.append(b)：是将b原封不动的追加到a的末尾上，会改变a的值
        #strip()用于移除字符串头尾指定的字符（默认为空格或者换行符）或字符序列
    print(result)
print(result[0])

———————————————————————————————————————————
データセットの形式を示します下の図にあります。

注釈: xml タグ
ImageSets: 4 つのテキスト ドキュメント
JPEGImages: 画像
ラベル: yolo 形式の txt タグ

makeTxt.pyは以下の通りです。ImageSet の生成に使用されるテキスト ドキュメント。

import os
import random
trainval_percent = 0.1
train_percent = 0.9
xmlfilepath = 'VOC2007/Annotations'
txtsavepath = 'VOC2007/ImageSets'
total_xml = os.listdir(xmlfilepath)
num = len(total_xml)
list = range(num)
tv = int(num * trainval_percent)
tr = int(tv * train_percent)
trainval = random.sample(list, tv)
train = random.sample(trainval, tr)
ftrainval = open('VOC2007/ImageSets/trainval.txt', 'w')
ftest = open('VOC2007/ImageSets/test.txt', 'w')
ftrain = open('VOC2007/ImageSets/train.txt', 'w')
fval = open('VOC2007/ImageSets/val.txt', 'w')
for i in list:
    name = total_xml[i][:-4] + '\n'
    if i in trainval:
        ftrainval.write(name)
        if i in train:
            ftest.write(name)
        else:
            fval.write(name)
    else:
        ftrain.write(name)
ftrainval.close()
ftrain.close()
fval.close()
ftest.close()

voc_label.pyは以下の通りです。voc2007 と同じディレクトリに 3 つのテキスト ファイルを生成するために使用されます。

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

sets = ['train', 'test', 'val']

classes = ['ball1', 'ball2', '0degree', '6degree', '12degree', '18degree', '24degree', '30degree', '36degree', '42degree', '48degree', '54degree', '60degree', '66degree', '72degree', '78degree', '84degree', '90degree', '96degree', '102degree', '108degree', '114degree', '120degree', '126degree', '132degree', '138degree', '144degree', '150degree', '156degree', '162degree', '168degree', '174degree', '180degree']  #改成自己的类别


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):
    in_file = open('VOC2007/Annotations/%s.xml' % (image_id))
    out_file = open('VOC2007/labels/%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
        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()
print(wd)
for image_set in sets:
    if not os.path.exists('VOC2007/labels/'):
        os.makedirs('VOC2007/labels/')
    image_ids = open('VOC2007/ImageSets/%s.txt' % (image_set)).read().strip().split()
    list_file = open('VOC2007/%s.txt' % (image_set), 'w')
    for image_id in image_ids:
        list_file.write('VOC2007/JPEGImages/%s.jpg\n' % (image_id))
        convert_annotation(image_id)
    list_file.close()