MNIST (PyTorch)

MNIST（エムニスト）は28×28ピクセルの手書き画像で，ピクセル値は0から255までの整数である。

ここではPyTorchを使う。Tensorflow版と同じ処理であるが、PyTorchのほうが複雑になるので、ChatGPTのGPT-4とOpenAI APIのgpt-4-turbo-previewに書いてもらって、つぎはぎした。ちなみにMacならPyTorchに似たMLXを使った例 mlx-examples/mnist が速そう。

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
from torch.utils.data import DataLoader
from sklearn.metrics import confusion_matrix

# Step 1: Load and preprocess the MNIST dataset
# カレントディレクトリにdataというサブディレクトリを作ってそこにデータを取得
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.5,), (0.5,))
])
train_dataset = datasets.MNIST('./data', train=True, download=True, transform=transform)
test_dataset = datasets.MNIST('./data', train=False, download=True, transform=transform)

train_loader = DataLoader(train_dataset, batch_size=64, shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=1000, shuffle=False)

# Step 2: Define the neural network model
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.flatten = nn.Flatten()
        self.fc1 = nn.Linear(28*28, 128)
        self.dropout = nn.Dropout(0.2)
        self.fc2 = nn.Linear(128, 10)

    def forward(self, x):
        x = self.flatten(x)
        x = F.relu(self.fc1(x))
        x = self.dropout(x)
        x = self.fc2(x)
        return x

model = Net()

# Step 3: Set up the loss function and the optimizer
loss_fn = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters())

# Step 4: Train the model
def train(model, train_loader, optimizer, loss_fn, epoch):
    model.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        optimizer.zero_grad()
        output = model(data)
        loss = loss_fn(output, target)
        loss.backward()
        optimizer.step()
    print(f"Epoch {epoch}, Loss: {loss.item()}")

for epoch in range(1, 6):
    train(model, train_loader, optimizer, loss_fn, epoch)

# Step 5: Evaluate the model and calculate the confusion matrix
def test(model, test_loader):
    model.eval()
    test_loss = 0
    correct = 0
    all_preds = []
    all_targets = []
    with torch.no_grad():
        for data, target in test_loader:
            output = model(data)
            test_loss += loss_fn(output, target).item()
            pred = output.argmax(dim=1, keepdim=True)
            correct += pred.eq(target.view_as(pred)).sum().item()
            all_preds.extend(pred.view(-1).tolist())
            all_targets.extend(target.view(-1).tolist())

    test_loss /= len(test_loader.dataset)
    accuracy = 100. * correct / len(test_loader.dataset)
    print(f"Test set: Average loss: {test_loss:.4f}, Accuracy: {correct}/{len(test_loader.dataset)} ({accuracy:.0f}%)")
    return all_targets, all_preds

targets, predictions = test(model, test_loader)
print(confusion_matrix(targets, predictions))

Last modified: