如何简化Pytorch中自动编码器的DataLoader

import torch
from torch.utils.data import DataLoader, TensorDataset
import torch.nn as nn
import torch.optim as optim

# 假设我们有一个数据集 X
X = torch.randn(1000, 784)  # 1000个样本，每个样本784维

# 创建TensorDataset
dataset = TensorDataset(X)

# 创建DataLoader
dataloader = DataLoader(dataset, batch_size=64, shuffle=True, num_workers=4)

# 定义自动编码器
class Autoencoder(nn.Module):
    def __init__(self):
        super(Autoencoder, self).__init__()
        self.encoder = nn.Linear(784, 32)
        self.decoder = nn.Linear(32, 784)

    def forward(self, x):
        x = self.encoder(x)
        x = torch.relu(x)
        x = self.decoder(x)
        return x

# 实例化模型、损失函数和优化器
model = Autoencoder()
criterion = nn.MSELoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

# 训练模型
for epoch in range(10):  # 假设训练10个周期
    for data in dataloader:
        inputs = data[0]
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, inputs)
        loss.backward()
        optimizer.step()
    print(f'Epoch {epoch+1}, Loss: {loss.item()}')