1、Dataset和DataLoader

1）Dataset类，构建数据，需要重写__len__和__getitem__这两个函数
2）DataLoader，迭代器，加载Dataset数据把分batch用作模型输入

import torch
import torch.utils.data.dataset as Dataset
#引入DataLoader：
import torch.utils.data.dataloader as DataLoader
import numpy as np
 
Data = np.asarray([[1, 2], [3, 4],[5, 6], [7, 8]])
Label = np.asarray([[0], [1], [0], [2]])
#创建子类
class subDataset(Dataset.Dataset):
    #初始化，定义数据内容和标签
    def __init__(self, Data, Label):
        self.Data = Data
        self.Label = Label
    #返回数据集大小
    def __len__(self):
        return len(self.Data)
    #得到数据内容和标签
    def __getitem__(self, index):
        data = torch.Tensor(self.Data[index])
        label = torch.IntTensor(self.Label[index])
        return data, label
 
if __name__ == '__main__':
    dataset = subDataset(Data, Label)
    print(dataset)
    print('dataset大小为：', dataset.__len__())
    print(dataset.__getitem__(0))
    print(dataset[0])
 
    #创建DataLoader迭代器
    #创建DataLoader，batch_size设置为2，shuffle=False不打乱数据顺序，num_workers= 4使用4个子进程：
    dataloader = DataLoader.DataLoader(dataset,batch_size= 2, shuffle = False, num_workers= 0)
    #使用enumerate访问可遍历的数组对象：
    for i, item in enumerate(dataloader):
        print('i:', i)
        data, label = item
        print('data:', data)
        print('label:', label)

batch_size= 2

2、pytorch-lightning

参考：https://github.com/PyTorchLightning/pytorch-lightning

pytorch的高层封装，更容易编写；类似于keras之于tensorflow

import os
import torch
from torch import nn
import torch.nn.functional as F
from torchvision.datasets import MNIST
from torch.utils.data import DataLoader, random_split
from torchvision import transforms
import pytorch_lightning as pl


class LitAutoEncoder(pl.LightningModule):
    def __init__(self):
        super().__init__()
        self.encoder = nn.Sequential(nn.Linear(28 * 28, 128), nn.ReLU(), nn.Linear(128, 3))
        self.decoder = nn.Sequential(nn.Linear(3, 128), nn.ReLU(), nn.Linear(128, 28 * 28))

    def forward(self, x):
        # in lightning, forward defines the prediction/inference actions
        embedding = self.encoder(x)
        return embedding

    def training_step(self, batch, batch_idx):
        # training_step defines the train loop. It is independent of forward
        x, y = batch
        x = x.view(x.size(0), -1)
        z = self.encoder(x)
        x_hat = self.decoder(z)
        loss = F.mse_loss(x_hat, x)
        self.log("train_loss", loss)
        return loss

    def configure_optimizers(self):
        optimizer = torch.optim.Adam(self.parameters(), lr=1e-3)
        return optimizer

    
dataset = MNIST(os.getcwd(), download=True, transform=transforms.ToTensor())
train, val = random_split(dataset, [55000, 5000])

autoencoder = LitAutoEncoder()
trainer = pl.Trainer()
trainer.fit(autoencoder, DataLoader(train), DataLoader(val))