yolov5/v8转txt及划分数据集验证集代码

转txt

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


def convert(size, box):
    x_center = (box[0] + box[1]) / 2.0
    y_center = (box[2] + box[3]) / 2.0
    x = x_center / size[0]
    y = y_center / size[1]
    w = (box[1] - box[0]) / size[0]
    h = (box[3] - box[2]) / size[1]
    return (x, y, w, h)


def convert_annotation(xml_files_path, save_txt_files_path, classes):
    xml_files = os.listdir(xml_files_path)
    print(xml_files)
    for xml_name in xml_files:
        print(xml_name)
        xml_file = os.path.join(xml_files_path, xml_name)
        out_txt_path = os.path.join(save_txt_files_path, xml_name.split('.')[0] + '.txt')
        out_txt_f = open(out_txt_path, 'w')
        tree = ET.parse(xml_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))
            # b=(xmin, xmax, ymin, ymax)
            print(w, h, b)
            bb = convert((w, h), b)
            out_txt_f.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')


if __name__ == "__main__":
    # 需要转换的类别，需要一一对应
    classes1 = ['flower', 'Great wall', 'nurse', 'Tang Monk', 'Green tree', 'volcano', 'mirror', 'hospital']
    # 2、voc格式的xml标签文件路径
    xml_files1 = r'D:\pyjb\VOCdevkit\VOC2007\Annotations'
    # 3、转化为yolo格式的txt标签文件存储路径
    save_txt_files1 = r'D:\pyjb\VOCdevkit\VOC2007\label'

    convert_annotation(xml_files1, save_txt_files1, classes1)

划分代码

import os, random, shutil


def moveimg(fileDir, tarDir):
    pathDir = os.listdir(fileDir)  # 取图片的原始路径
    filenumber = len(pathDir)
    rate = 0.1 #自定义抽取图片的比例，比方说100张抽10张，那就是0.1
    picknumber = int(filenumber * rate)  # 按照rate比例从文件夹中取一定数量图片
    sample = random.sample(pathDir, picknumber)  # 随机选取picknumber数量的样本图片
    print(sample)
    for name in sample:
        shutil.move(fileDir + name, tarDir + "\\" + name)
    return


def movelabel(file_list, file_label_train, file_label_val):
    for i in file_list:
        if i.endswith('.jpg'):
            # filename = file_label_train + "\\" + i[:-4] + '.xml'  # 可以改成xml文件将’.txt‘改成'.xml'就可以了
            filename = file_label_train + "\\" + i[:-4] + '.txt'  # 可以改成xml文件将’.txt‘改成'.xml'就可以了
            if os.path.exists(filename):
                shutil.move(filename, file_label_val)
                print(i + "处理成功！")


if __name__ == '__main__':
    fileDir = r"D:\pyjb\VOCdevkit\images\train" + "\\"  # 源图片文件夹路径
    tarDir = r'D:\pyjb\VOCdevkit\images\val'  # 图片移动到新的文件夹路径
    moveimg(fileDir, tarDir)
    file_list = os.listdir(tarDir)
    file_label_train = r"D:\pyjb\VOCdevkit\labels\train"  # 源图片标签路径
    file_label_val = r"D:\pyjb\VOCdevkit\labels\val"  # 标签
    # 移动到新的文件路径
    movelabel(file_list, file_label_train, file_label_val)