optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)

optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)

optimizer = torch.optim.Adagrad(model.parameters(), lr=learning_rate)

optimizer = torch.optim.RMSprop(model.parameters(), lr=learning_rate)

optimizer = torch.optim.Adadelta(model.parameters(), lr=learning_rate)

import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import datasets, transforms
from torch.utils.data import DataLoader
import matplotlib.pyplot as plt

# 設(shè)置隨機(jī)種子
torch.manual_seed(42)

# 定義數(shù)據(jù)轉(zhuǎn)換
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (0.5,))])

# 下載和加載MNIST數(shù)據(jù)集
train_dataset = datasets.MNIST(root='./data', train=True, download=True, transform=transform)
test_dataset = datasets.MNIST(root='./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)

# 定義簡(jiǎn)單的卷積神經(jīng)網(wǎng)絡(luò)模型
class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1 = nn.Conv2d(1, 32, kernel_size=3, stride=1, padding=1)
        self.relu = nn.ReLU()
        self.pool = nn.MaxPool2d(kernel_size=2, stride=2)
        self.conv2 = nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1)
        self.fc1 = nn.Linear(64 * 7 * 7, 128)
        self.fc2 = nn.Linear(128, 10)

    def forward(self, x):
        x = self.conv1(x)
        x = self.relu(x)
        x = self.pool(x)
        x = self.conv2(x)
        x = self.relu(x)
        x = self.pool(x)
        x = x.view(-1, 64 * 7 * 7)
        x = self.fc1(x)
        x = self.relu(x)
        x = self.fc2(x)
        return x

# 創(chuàng)建模型、損失函數(shù)和優(yōu)化器
model = CNN()
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

# 訓(xùn)練模型
num_epochs = 5
train_losses = []
train_accuracies = []

for epoch in range(num_epochs):
    model.train()
    total_loss = 0.0
    correct = 0
    total = 0

    for inputs, labels in train_loader:
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        total_loss += loss.item()
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

    accuracy = correct / total
    train_losses.append(total_loss / len(train_loader))
    train_accuracies.append(accuracy)
    print(f"Epoch {epoch+1}/{num_epochs}, Loss: {train_losses[-1]:.4f}, Accuracy: {accuracy:.4f}")

# 繪制損失曲線和準(zhǔn)確率曲線
plt.figure(figsize=(10, 5))
plt.subplot(1, 2, 1)
plt.plot(train_losses, label='Training Loss')
plt.title('Training Loss')
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.legend()

plt.subplot(1, 2, 2)
plt.plot(train_accuracies, label='Training Accuracy')
plt.title('Training Accuracy')
plt.xlabel('Epoch')
plt.ylabel('Accuracy')
plt.legend()

plt.tight_layout()
plt.show()

# 在測(cè)試集上評(píng)估模型
model.eval()
correct = 0
total = 0

with torch.no_grad():
    for inputs, labels in test_loader:
        outputs = model(inputs)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

accuracy = correct / total
print(f"Accuracy on test set: {accuracy * 100:.2f}%")