vae pytorch代码实现

下面是一个使用PyTorch实现Variational Autoencoder (VAE)的简单代码示例：

import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
from torchvision import datasets, transforms

# 定义VAE模型
class VAE(nn.Module):
    def __init__(self):
        super(VAE, self).__init__()
        
        self.fc1 = nn.Linear(784, 400)
        self.fc21 = nn.Linear(400, 20)   # 均值
        self.fc22 = nn.Linear(400, 20)   # 方差
        self.fc3 = nn.Linear(20, 400)
        self.fc4 = nn.Linear(400, 784)

    def encode(self, x):
        h1 = F.relu(self.fc1(x))
        return self.fc21(h1), self.fc22(h1)

    def reparameterize(self, mu, logvar):
        std = torch.exp(0.5 * logvar)
        eps = torch.randn_like(std)
        return mu + eps * std

    def decode(self, z):
        h3 = F.relu(self.fc3(z))
        return torch.sigmoid(self.fc4(h3))

    def forward(self, x):
        mu, logvar = self.encode(x.view(-1, 784))
        z = self.reparameterize(mu, logvar)
        return self.decode(z), mu, logvar

# 计算VAE的损失函数
def loss_function(recon_x, x, mu, logvar):
    BCE = F.binary_cross_entropy(recon_x, x.view(-1, 784), reduction='sum')
    KLD = -0.5 * torch.sum(1 + logvar - mu.pow(2) - logvar.exp())
    return BCE + KLD

# 加载MNIST数据集
train_loader = torch.utils.data.DataLoader(
    datasets.MNIST('../data', train=True, download=True,
                   transform=transforms.ToTensor()),
    batch_size=128, shuffle=True)

# 初始化VAE模型和优化器
model = VAE()
optimizer = optim.Adam(model.parameters(), lr=1e-3)

# 训练VAE模型
def train(epoch):
    model.train()
    train_loss = 0
    for batch_idx, (data, _) in enumerate(train_loader):
        optimizer.zero_grad()
        recon_batch, mu, logvar = model(data)
        loss = loss_function(recon_batch, data, mu, logvar)
        loss.backward()
        train_loss += loss.item()
        optimizer.step()
        if batch_idx % 100 == 0:
            print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
                epoch, batch_idx * len(data), len(train_loader.dataset),
                100. * batch_idx / len(train_loader),
                loss.item() / len(data)))

    print('====> Epoch: {} Average loss: {:.4f}'.format(
          epoch, train_loss / len(train_loader.dataset)))

# 使用训练好的VAE生成一些样本
def generate_samples(num_samples):
    with torch.no_grad():
        sample = torch.randn(num_samples, 20)
        sample = model.decode(sample).cpu()
        return sample

# 开始训练和生成样本
num_epochs = 10
for epoch in range(1, num_epochs + 1):
    train(epoch)

samples = generate_samples(10)

这个代码示例实现了一个简单的VAE模型，使用MNIST数据集进行训练和生成样本。你可以根据实际情况进行修改和扩展。