1.将训练集、验证集、测试集按照7:2:1随机划分

1.项目准备

1.在项目下新建一个py文件，名字就叫做splitDataset1.py

2.将自己需要划分的原数据集就放在项目文件夹下面

以我的为例，我的原数据集名字叫做hatDataXml

里面的JPEGImages装的是图片

Annotations里面装的是xml标签

2.代码实现

python">
# 将标签为xml格式的数据集按照7:2:1的比例划分为训练集，验证集和测试集

import os, shutil, random
from tqdm import tqdm


def split_img(img_path, label_path, split_list):
    try:
        Data = 'DataSet'
        # Data是你要将要创建的文件夹路径（路径一定是相对于你当前的这个脚本而言的）
        os.mkdir(Data)

        train_img_dir = Data + '/images/train'
        val_img_dir = Data + '/images/val'
        test_img_dir = Data + '/images/test'

        train_label_dir = Data + '/labels/train'
        val_label_dir = Data + '/labels/val'
        test_label_dir = Data + '/labels/test'

        # 创建文件夹
        os.makedirs(train_img_dir)
        os.makedirs(train_label_dir)
        os.makedirs(val_img_dir)
        os.makedirs(val_label_dir)
        os.makedirs(test_img_dir)
        os.makedirs(test_label_dir)

    except:
        print('文件目录已存在')

    train, val, test = split_list
    all_img = os.listdir(img_path)
    all_img_path = [os.path.join(img_path, img) for img in all_img]
    # all_label = os.listdir(label_path)
    # all_label_path = [os.path.join(label_path, label) for label in all_label]
    train_img = random.sample(all_img_path, int(train * len(all_img_path)))
    train_img_copy = [os.path.join(train_img_dir, img.split('\\')[-1]) for img in train_img]
    train_label = [toLabelPath(img, label_path) for img in train_img]
    train_label_copy = [os.path.join(train_label_dir, label.split('\\')[-1]) for label in train_label]
    for i in tqdm(range(len(train_img)), desc='train ', ncols=80, unit='img'):
        _copy(train_img[i], train_img_dir)
        _copy(train_label[i], train_label_dir)
        all_img_path.remove(train_img[i])
    val_img = random.sample(all_img_path, int(val / (val + test) * len(all_img_path)))
    val_label = [toLabelPath(img, label_path) for img in val_img]
    for i in tqdm(range(len(val_img)), desc='val ', ncols=80, unit='img'):
        _copy(val_img[i], val_img_dir)
        _copy(val_label[i], val_label_dir)
        all_img_path.remove(val_img[i])
    test_img = all_img_path
    test_label = [toLabelPath(img, label_path) for img in test_img]
    for i in tqdm(range(len(test_img)), desc='test ', ncols=80, unit='img'):
        _copy(test_img[i], test_img_dir)
        _copy(test_label[i], test_label_dir)


def _copy(from_path, to_path):
    shutil.copy(from_path, to_path)


def toLabelPath(img_path, label_path):
    img = img_path.split('\\')[-1]
    label = img.split('.jpg')[0] + '.xml'  # 因为这个数据集的标签是xml格式，所以将这里改成xml,如果标签格式是txt格式，就将这里改成txt
    return os.path.join(label_path, label)


def main():
    # 需要修改的地方：装图片的文件夹以及装标签的文件夹
    img_path = 'hatDataXml/JPEGImages'
    label_path = 'hatDataXml/Annotations'
    split_list = [0.7, 0.2, 0.1]  # 数据集划分比例[train:val:test]
    split_img(img_path, label_path, split_list)


if __name__ == '__main__':
    main()

3.需要修改的地方

1.代码65行，如果你的标签格式是txt,就将这里的xml改成txt即可

2.代码71，72行，将原数据集的图片路径和标签路径填写在这里

4.直接运行splitDataset1.py,转换成功

2.将训练集、验证集按照8:2随机划分

在项目下新建一个py文件，名字叫做splitDataset2.py

1.代码实现

python">
# 将标签格式为xml的数据集按照8：2的比例划分为训练集和验证集

import os
import shutil
import random
from tqdm import tqdm


def split_img(img_path, label_path, split_list):
    try:  # 创建数据集文件夹
        Data = 'DataSet2parts'
        os.mkdir(Data)

        train_img_dir = Data + '/images/train'
        val_img_dir = Data + '/images/val'
        # test_img_dir = Data + '/images/test'

        train_label_dir = Data + '/labels/train'
        val_label_dir = Data + '/labels/val'
        # test_label_dir = Data + '/labels/test'

        # 创建文件夹
        os.makedirs(train_img_dir)
        os.makedirs(train_label_dir)
        os.makedirs(val_img_dir)
        os.makedirs(val_label_dir)
        # os.makedirs(test_img_dir)
        # os.makedirs(test_label_dir)

    except:
        print('文件目录已存在')

    train, val = split_list
    all_img = os.listdir(img_path)
    all_img_path = [os.path.join(img_path, img) for img in all_img]
    # all_label = os.listdir(label_path)
    # all_label_path = [os.path.join(label_path, label) for label in all_label]
    train_img = random.sample(all_img_path, int(train * len(all_img_path)))
    train_img_copy = [os.path.join(train_img_dir, img.split('\\')[-1]) for img in train_img]
    train_label = [toLabelPath(img, label_path) for img in train_img]
    train_label_copy = [os.path.join(train_label_dir, label.split('\\')[-1]) for label in train_label]
    for i in tqdm(range(len(train_img)), desc='train ', ncols=80, unit='img'):
        _copy(train_img[i], train_img_dir)
        _copy(train_label[i], train_label_dir)
        all_img_path.remove(train_img[i])
    val_img = all_img_path
    val_label = [toLabelPath(img, label_path) for img in val_img]
    for i in tqdm(range(len(val_img)), desc='val ', ncols=80, unit='img'):
        _copy(val_img[i], val_img_dir)
        _copy(val_label[i], val_label_dir)


def _copy(from_path, to_path):
    shutil.copy(from_path, to_path)


def toLabelPath(img_path, label_path):
    img = img_path.split('\\')[-1]
    label = img.split('.jpg')[0] + '.xml'
    return os.path.join(label_path, label)


def main():
    img_path = 'hatDataXml/JPEGImages'
    label_path = 'hatDataXml/Annotations'
    split_list = [0.8, 0.2]  # 数据集划分比例[train:val]
    split_img(img_path, label_path, split_list)


if __name__ == '__main__':
    main()