models.py

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

# Cấu hình
BATCH_SIZE = 128
DEVICE = torch.device('cpu')

class Net(nn.Module):
    """Mạng CNN cho phân loại MNIST"""
    def __init__(self):
        super(Net, self).__init__()

        self.conv_layers = nn.Sequential(
            nn.Conv2d(1, 10, kernel_size=5),
            nn.MaxPool2d(2),
            nn.ReLU(),
            nn.Conv2d(10, 20, kernel_size=5),
            nn.Dropout(),
            nn.MaxPool2d(2),
            nn.ReLU(),
        )
        self.fc_layers = nn.Sequential(
            nn.Linear(320, 50),
            nn.ReLU(),
            nn.Dropout(),
            nn.Linear(50, 10),
            nn.Softmax(dim=1)
        )

    def forward(self, x):
        x = self.conv_layers(x)
        x = x.view(-1, 320)
        x = self.fc_layers(x)
        return x

def train(model, device, train_loader, optimizer, epoch):
    """Hàm train model cho 1 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.log(), target)
        loss.backward()
        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()))

def test(model, device, test_loader):
    """Hàm test model"""
    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.log(), target).item()
            pred = output.max(1, keepdim=True)[1]
            correct += pred.eq(target.view_as(pred)).sum().item()

    test_loss /= len(test_loader.dataset)
    print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
        test_loss, correct, len(test_loader.dataset),
        100. * correct / len(test_loader.dataset)))

# Tạo data loaders
train_loader = torch.utils.data.DataLoader(
    datasets.MNIST('mnist_data', train=True, download=True,
                   transform=transforms.Compose([
                       transforms.ToTensor()
                   ])),
    batch_size=BATCH_SIZE, shuffle=True)

test_loader = torch.utils.data.DataLoader(
    datasets.MNIST('mnist_data', train=False, transform=transforms.Compose([
                       transforms.ToTensor()
                   ])),
    batch_size=BATCH_SIZE, shuffle=True)

def train_model(model, num_epochs):
    """Hàm train model với số epochs chỉ định"""
    optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)
    
    for epoch in range(1, num_epochs + 1):
        train(model, DEVICE, train_loader, optimizer, epoch)
        test(model, DEVICE, test_loader)