簡単な画像生成AI python

import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import datasets, transforms
from torch.utils.data import DataLoader
from torchvision.utils import save_image  # 画像保存のための関数
import os  # ファイルの保存先を指定するためのライブラリ

# VAEのエンコーダーとデコーダー
class VAE(nn.Module):
    def __init__(self, input_dim=784, hidden_dim=400, latent_dim=20):
        super(VAE, self).__init__()
        self.fc1 = nn.Linear(input_dim, hidden_dim)
        self.fc21 = nn.Linear(hidden_dim, latent_dim)
        self.fc22 = nn.Linear(hidden_dim, latent_dim)
        self.fc3 = nn.Linear(latent_dim, hidden_dim)
        self.fc4 = nn.Linear(hidden_dim, input_dim)

    def encode(self, x):
        h1 = torch.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 = torch.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

# VAEの損失関数
def loss_function(recon_x, x, mu, logvar):
    BCE = nn.functional.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

# モデルの定義とデータローダーの準備
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
vae = VAE().to(device)
optimizer = optim.Adam(vae.parameters(), lr=1e-3)

transform = transforms.ToTensor()
train_dataset = datasets.MNIST('.', train=True, download=True, transform=transform)
train_loader = DataLoader(train_dataset, batch_size=128, shuffle=True)

# トレーニングループ
vae.train()
for epoch in range(10):  # 10エポックで学習
    train_loss = 0
    for batch_idx, (data, _) in enumerate(train_loader):
        data = data.to(device)
        optimizer.zero_grad()
        recon_batch, mu, logvar = vae(data)
        loss = loss_function(recon_batch, data, mu, logvar)
        loss.backward()
        train_loss += loss.item()
        optimizer.step()
    
    print(f'Epoch {epoch + 1}, Loss: {train_loss / len(train_loader.dataset)}')

# 学習したモデルで画像生成
vae.eval()
with torch.no_grad():
    z = torch.randn(64, 20).to(device)
    sample = vae.decode(z).cpu()
    sample = sample.view(64, 1, 28, 28)  # 28x28の画像サイズに変換 (MNISTデータのフォーマット)
    
    # 保存先ディレクトリを指定
    os.makedirs('generated_images', exist_ok=True)
    save_image(sample, 'generated_images/sample.png')

    print("画像生成完了: 'generated_images/sample.png' に保存されました")