Pytorch将数据集划分为训练集、验证集和测试集

一起来玩

qq群：821429104

b站：宋老狗97

我们可以借助Pytorch从文件夹中读取数据集，十分方便，但是Pytorch中没有提供数据集划分的操作，需要手动将原始的数据集划分为训练集、验证集和测试集，废话不多说，这里我写了一个工具类，帮助大家将数据集自动划分为训练集、验证集和测试集，还可以指定比例，代码如下。

# 工具类
import os
import random
import shutil
from shutil import copy2


def data_set_split(src_data_folder, target_data_folder, train_scale=0.8, val_scale=0.1, test_scale=0.1):
    '''
    读取源数据文件夹，生成划分好的文件夹，分为trian、val、test三个文件夹进行
    :param src_data_folder: 源文件夹 E:/biye/gogogo/note_book/torch_note/data/utils_test/data_split/src_data
    :param target_data_folder: 目标文件夹 E:/biye/gogogo/note_book/torch_note/data/utils_test/data_split/target_data
    :param train_scale: 训练集比例
    :param val_scale: 验证集比例
    :param test_scale: 测试集比例
    :return:
    '''
    print("开始数据集划分")
    class_names = os.listdir(src_data_folder)
    # 在目标目录下创建文件夹
    split_names = ['train', 'val', 'test']
    for split_name in split_names:
        split_path = os.path.join(target_data_folder, split_name)
        if os.path.isdir(split_path):
            pass
        else:
            os.mkdir(split_path)
        # 然后在split_path的目录下创建类别文件夹
        for class_name in class_names:
            class_split_path = os.path.join(split_path, class_name)
            if os.path.isdir(class_split_path):
                pass
            else:
                os.mkdir(class_split_path)

    # 按照比例划分数据集，并进行数据图片的复制
    # 首先进行分类遍历
    for class_name in class_names:
        current_class_data_path = os.path.join(src_data_folder, class_name)
        current_all_data = os.listdir(current_class_data_path)
        current_data_length = len(current_all_data)
        current_data_index_list = list(range(current_data_length))
        random.shuffle(current_data_index_list)

        train_folder = os.path.join(os.path.join(target_data_folder, 'train'), class_name)
        val_folder = os.path.join(os.path.join(target_data_folder, 'val'), class_name)
        test_folder = os.path.join(os.path.join(target_data_folder, 'test'), class_name)
        train_stop_flag = current_data_length * train_scale
        val_stop_flag = current_data_length * (train_scale + val_scale)
        current_idx = 0
        train_num = 0
        val_num = 0
        test_num = 0
        for i in current_data_index_list:
            src_img_path = os.path.join(current_class_data_path, current_all_data[i])
            if current_idx <= train_stop_flag:
                copy2(src_img_path, train_folder)
                # print("{}复制到了{}".format(src_img_path, train_folder))
                train_num = train_num + 1
            elif (current_idx > train_stop_flag) and (current_idx <= val_stop_flag):
                copy2(src_img_path, val_folder)
                # print("{}复制到了{}".format(src_img_path, val_folder))
                val_num = val_num + 1
            else:
                copy2(src_img_path, test_folder)
                # print("{}复制到了{}".format(src_img_path, test_folder))
                test_num = test_num + 1

            current_idx = current_idx + 1

        print("*********************************{}*************************************".format(class_name))
        print(
            "{}类按照{}：{}：{}的比例划分完成，一共{}张图片".format(class_name, train_scale, val_scale, test_scale, current_data_length))
        print("训练集{}：{}张".format(train_folder, train_num))
        print("验证集{}：{}张".format(val_folder, val_num))
        print("测试集{}：{}张".format(test_folder, test_num))


if __name__ == '__main__':
    src_data_folder = "E:/biye/gogogo/note_book/torch_note/data/utils_test/data_split/src_data"
    target_data_folder = "E:/biye/gogogo/note_book/torch_note/data/utils_test/data_split/target_data"
    data_set_split(src_data_folder, target_data_folder)

** 注意 **

划分前你得文件夹结构应该是这样的

划分结果

tensorflow2.3 加载数据集的方式

from tensorflow.keras.preprocessing.image import ImageDataGenerator
import matplotlib.pyplot as plt
import tensorflow as tf
from tensorflow.keras import layers
from tensorflow.keras.models import Sequential


def load_data_from_folder(batch_size, target_img_height, target_img_width, data_dir="F:/datas/massmass/fer2013+/ccc/"):
    train_datagen = ImageDataGenerator(
        rescale=1. / 255,  # 重放缩因子，数值乘以1.0/255（归一化）
        shear_range=0.2,  # 剪切强度（逆时针方向的剪切变换角度）
        zoom_range=0.2,  # 随机缩放的幅度
        # 进行随机水平翻转
        horizontal_flip=True)
    val_datagen = ImageDataGenerator(
        rescale=1. / 255)

    train_generator = train_datagen.flow_from_directory(
        data_dir + '/train',  # dictory参数，该路径下的所有子文件夹的图片都会被生成器使用，无限产生batch数据
        target_size=(target_img_height, target_img_width),  # 图片将被resize成该尺寸
        color_mode='grayscale',  # 颜色模式，graycsale或rgb（默认rgb）
        batch_size=batch_size,  # batch数据的大小，默认为32
        class_mode='sparse')  # 返回的标签形式，默认为‘category’，返回2D的独热码标签
    val_generator = val_datagen.flow_from_directory(
        data_dir + '/val',  # 同上
        target_size=(target_img_height, target_img_width),
        color_mode='grayscale',
        batch_size=batch_size,
        class_mode='sparse')
    num_class = train_generator.num_classes
    return train_generator, val_generator, num_class

tensorflow2.0 加载数据集的方式

from tensorflow.keras.preprocessing.image import ImageDataGenerator
import matplotlib.pyplot as plt
import tensorflow as tf
from tensorflow.keras import layers
from tensorflow.keras.models import Sequential

def load_data_from_folder(batch_size, target_img_height, target_img_width, data_dir="data/"):
    emotion_classification_train_datagen = ImageDataGenerator(
        rescale=1. / 255,  # 重放缩因子，数值乘以1.0/255（归一化）
        shear_range=0.2,  # 剪切强度（逆时针方向的剪切变换角度）
        zoom_range=0.2,  # 随机缩放的幅度
        # 进行随机水平翻转
        horizontal_flip=True)
    emotion_classification_val_datagen = ImageDataGenerator(
        rescale=1. / 255)

    emotion_classification_train_generator = emotion_classification_train_datagen.flow_from_directory(
        data_dir + '/train',  # dictory参数，该路径下的所有子文件夹的图片都会被生成器使用，无限产生batch数据
        target_size=(target_img_height, target_img_width),  # 图片将被resize成该尺寸
        color_mode='grayscale',  # 颜色模式，graycsale或rgb（默认rgb）
        batch_size=batch_size,  # batch数据的大小，默认为32
        class_mode='sparse')  # 返回的标签形式，默认为‘category’，返回2D的独热码标签
    emotion_classification_val_generator = emotion_classification_val_datagen.flow_from_directory(
        data_dir + '/val',  # 同上
        target_size=(target_img_height, target_img_width),
        color_mode='grayscale',
        batch_size=batch_size,
        class_mode='sparse')
    num_class = emotion_classification_train_generator.num_classes
    return emotion_classification_train_generator, emotion_classification_val_generator, num_class

pytorch加载数据集的方式

import torch
import torch.nn as nn
import torch.optim as optim
from torch.optim import lr_scheduler
import numpy as np
import torchvision
from torchvision import datasets, models, transforms
import matplotlib.pyplot as plt
import time
import os
import copy

# Data augmentation and normalization for training
# Just normalization for validation
data_transforms = {
    'train': transforms.Compose([
        transforms.RandomResizedCrop(224),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
    'val': transforms.Compose([
        transforms.Resize(256),
        transforms.CenterCrop(224),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
}

data_dir = 'data/hymenoptera_data'
image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x),
                                          data_transforms[x])
                  for x in ['train', 'val']}
dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=4,
                                             shuffle=True, num_workers=4)
              for x in ['train', 'val']}
dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'val']}
class_names = image_datasets['train'].classes

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

最后附上github地址

https://github.com/cmFighting/mnist_demo_torch1.6

如果帮助到您的话可以请我喝杯咖啡嗷！谢谢！