mnist_cnn.py

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

class ConvNet(nn.Module):
    def __init__(self):
        super(ConvNet, self).__init__()
        # 畳み込み層
        self.conv1 = nn.Conv2d(1, 32, 3, padding=1)
        self.conv2 = nn.Conv2d(32, 64, 3, padding=1)
        
        # 全結合層
        self.fc1 = nn.Linear(64 * 7 * 7, 100)
        self.fc2 = nn.Linear(100, 200)
        self.fc3 = nn.Linear(200, 10)
        
        # ドロップアウト
        self.dropout = nn.Dropout(0.5)
        
    def forward(self, x):
        # 畳み込み層1
        x = self.conv1(x)
        x = F.relu(x)
        x = F.max_pool2d(x, 2)
        
        # 畳み込み層2
        x = self.conv2(x)
        x = F.relu(x)
        x = F.max_pool2d(x, 2)
        
        # 全結合層への変換
        x = x.view(-1, 64 * 7 * 7)
        
        # 全結合層1
        x = self.fc1(x)
        x = F.relu(x)
        x = self.dropout(x)
        
        # 全結合層2
        x = self.fc2(x)
        x = F.relu(x)
        x = self.dropout(x)
        
        # 出力層
        x = self.fc3(x)
        return F.log_softmax(x, dim=1)

def train(model, device, train_loader, optimizer, epoch):
    model.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        data, target = data.to(device), target.to(device)
        optimizer.zero_grad()
        output = model(data)
        loss = F.nll_loss(output, target)
        loss.backward()
        optimizer.step()
        
        if batch_idx % 100 == 0:
            print(f'Train Epoch {epoch} [{batch_idx * len(data)}/{len(train_loader.dataset)} '
                  f'({100. * batch_idx / len(train_loader):.0f}%)]\tLoss {loss.item():.6f}')

def test(model, device, test_loader):
    model.eval()
    test_loss = 0
    correct = 0
    with torch.no_grad():
        for data, target in test_loader:
            data, target = data.to(device), target.to(device)
            output = model(data)
            test_loss += F.nll_loss(output, target, reduction='sum').item()
            pred = output.argmax(dim=1, keepdim=True)
            correct += pred.eq(target.view_as(pred)).sum().item()
    
    test_loss /= len(test_loader.dataset)
    print(f'\nTest set: Average loss {test_loss:.4f}, '
          f'Accuracy {correct}/{len(test_loader.dataset)} '
          f'({100. * correct / len(test_loader.dataset):.2f}%)\n')

def main():
    # デバイスの設定
    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
    
    # データローダーの設定
    train_loader = torch.utils.data.DataLoader(
        datasets.MNIST('./data', train=True, download=True,
                      transform=transforms.Compose([
                          transforms.ToTensor(),
                          transforms.Normalize((0.1307,), (0.3081,))
                      ])),
        batch_size=100, shuffle=True)
    
    test_loader = torch.utils.data.DataLoader(
        datasets.MNIST('./data', train=False, 
                      transform=transforms.Compose([
                          transforms.ToTensor(),
                          transforms.Normalize((0.1307,), (0.3081,))
                      ])),
        batch_size=100, shuffle=True)
    
    # モデルの設定
    model = ConvNet().to(device)
    
    # オプティマイザの設定（モメンタム付きSGD）
    optimizer = torch.optim.SGD(model.parameters(), lr=0.01, momentum=0.9)
    
    # 学習の実行
    for epoch in range(10):
        train(model, device, train_loader, optimizer, epoch)
        test(model, device, test_loader)

if __name__ == '__main__':
    main()