YOLO divides the data set (training set, verification set, test set)

Preface

This blog is based on the mutual conversion of VOC format and YOLO format in my other blog . You can refer to it if necessary.

$$The\; following\; code\; can\; be\; directly\; copied\; and\; run\; for\; personal\; testing\; (change\; all\; the\; following\; paths\; to\; your\; own\; corresponding\; paths)$$

Training set, validation set (8:2)

split82.pyThe content is as follows:

import os
import shutil
import random
from tqdm import tqdm

"""
标注文件是yolo格式（txt文件）
训练集：验证集 （8：2） 
"""


def split_img(img_path, label_path, split_list):
    try:  # 创建数据集文件夹
        Data = './VOCdevkit/VOC2007/ImageSets'
        # 这里我的文件夹./VOCdevkit/VOC2007/ImageSets提前创建好了，所以注释了下一行，否则会抛异常
        # 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] + '.txt'
    return os.path.join(label_path, label)


if __name__ == '__main__':
    img_path = './VOCdevkit/VOC2007/JPEGImages'
    label_path = './YoloLabels'
    split_list = [0.8, 0.2]  # 数据集划分比例[train:val]
    split_img(img_path, label_path, split_list)

Training set, validation set, test set (7:2:1)

split721.pyThe content is as follows:

import os, shutil, random
from tqdm import tqdm

"""
标注文件是yolo格式（txt文件）
训练集：验证集：测试集 （7：2：1） 
"""


def split_img(img_path, label_path, split_list):
    try:
        Data = './VOCdevkit/VOC2007/ImageSets'
        # 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] + '.txt'
    return os.path.join(label_path, label)


if __name__ == '__main__':
    img_path = './VOCdevkit/VOC2007/JPEGImages'  # 你的图片存放的路径（路径一定是相对于你当前的这个脚本文件而言的）
    label_path = './YoloLabels'  # 你的txt文件存放的路径（路径一定是相对于你当前的这个脚本文件而言的）
    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)

After completing the mutual conversion between the VOC format and YOLO format of my other blog and the YOLO partitioning of the data set (training set, verification set, test set) in this article , my entire project structure is as shown below: