给我基于pytorch的DCGAN代码

以下是基于pytorch的DCGAN代码：

import torch
import torch.nn as nn
import torch.optim as optim
import torchvision.utils as vutils
import torchvision.datasets as dset
import torchvision.transforms as transforms
from torch.utils.data import DataLoader

# Set random seed for reproducibility
manual_seed = 999
torch.manual_seed(manual_seed)

# Set device to GPU if available, otherwise CPU
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

# Define hyperparameters
batch_size = 128
image_size = 64
num_epochs = 100
latent_size = 100
ngf = 64
ndf = 64
lr = 0.0002
beta1 = 0.5

# Load dataset
dataset = dset.CIFAR10(root='./data', download=True,
                       transform=transforms.Compose([
                           transforms.Resize(image_size),
                           transforms.CenterCrop(image_size),
                           transforms.ToTensor(),
                           transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)),
                       ]))
dataloader = DataLoader(dataset, batch_size=batch_size, shuffle=True, num_workers=2)

# Define generator network
class Generator(nn.Module):
    def __init__(self):
        super(Generator, self).__init__()
        self.main = nn.Sequential(
            nn.ConvTranspose2d(latent_size, ngf * 8, 4, 1, 0, bias=False),
            nn.BatchNorm2d(ngf * 8),
            nn.ReLU(True),
            nn.ConvTranspose2d(ngf * 8, ngf * 4, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ngf * 4),
            nn.ReLU(True),
            nn.ConvTranspose2d(ngf * 4, ngf * 2, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ngf * 2),
            nn.ReLU(True),
            nn.ConvTranspose2d(ngf * 2, ngf, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ngf),
            nn.ReLU(True),
            nn.ConvTranspose2d(ngf, 3, 4, 2, 1, bias=False),
            nn.Tanh()
        )

    def forward(self, input):
        output = self.main(input)
        return output

# Define discriminator network
class Discriminator(nn.Module):
    def __init__(self):
        super(Discriminator, self).__init__()
        self.main = nn.Sequential(
            nn.Conv2d(3, ndf, 4, 2, 1, bias=False),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Conv2d(ndf, ndf * 2, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ndf * 2),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Conv2d(ndf * 2, ndf * 4, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ndf * 4),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Conv2d(ndf * 4, ndf * 8, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ndf * 8),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Conv2d(ndf * 8, 1, 4, 1, 0, bias=False),
            nn.Sigmoid()
        )

    def forward(self, input):
        output = self.main(input)
        return output.view(-1, 1).squeeze(1)

# Initialize generator and discriminator networks
netG = Generator().to(device)
netD = Discriminator().to(device)

# Initialize generator weights
netG.apply(weights_init)

# Print generator and discriminator architectures
print(netG)
print(netD)

# Define loss function and optimizer
criterion = nn.BCELoss()
optimizerG = optim.Adam(netG.parameters(), lr=lr, betas=(beta1, 0.999))
optimizerD = optim.Adam(netD.parameters(), lr=lr, betas=(beta1, 0.999))

# Define fixed noise for visualization
fixed_noise = torch.randn(64, latent_size, 1, 1, device=device)

# Training loop
for epoch in range(num_epochs):
    for i, data in enumerate(dataloader, 0):
        # Update discriminator network
        netD.zero_grad()
        real = data[0].to(device)
        batch_size = real.size(0)
        label = torch.full((batch_size,), 1, device=device)
        output = netD(real)
        errD_real = criterion(output, label)
        errD_real.backward()
        D_x = output.mean().item()

        noise = torch.randn(batch_size, latent_size, 1, 1, device=device)
        fake = netG(noise)
        label.fill_(0)
        output = netD(fake.detach())
        errD_fake = criterion(output, label)
        errD_fake.backward()
        D_G_z1 = output.mean().item()
        errD = errD_real + errD_fake
        optimizerD.step()

        # Update generator network
        netG.zero_grad()
        label.fill_(1)
        output = netD(fake)
        errG = criterion(output, label)
        errG.backward()
        D_G_z2 = output.mean().item()
        optimizerG.step()

        # Print training statistics
        if i % 50 == 0:
            print('[%d/%d][%d/%d]\tLoss_D: %.4f\tLoss_G: %.4f\tD(x): %.4f\tD(G(z)): %.4f / %.4f'
                  % (epoch, num_epochs, i, len(dataloader),
                     errD.item(), errG.item(), D_x, D_G_z1, D_G_z2))

        # Save generated images for visualization
        if (epoch == 0) and (i == 0):
            vutils.save_image(real, '%s/real_samples.png' % "./results", normalize=True)
        if i % 100 == 0:
            with torch.no_grad():
                fake = netG(fixed_noise)
                vutils.save_image(fake.detach(), '%s/fake_samples_epoch_%03d.png' % ("./results", epoch), normalize=True)

# Save final generator network
torch.save(netG.state_dict(), './generator.pth')