基于PyTorch利用CNN实现MNIST的手写数字识别

---

GitHub地址：
https://github.com/gao7025/pytorch_cnn_mnist.git

1.定义模型、损失函数、优化器

• 定义一个卷积神经网络的网络结构，并设置一个优化器（optimizer）和一个损失准则（losscriterion）。创建一个随机梯度下降（stochasticgradientdescent）优化器

# 仅定义模型
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 16, kernel_size=4)
        self.conv2 = nn.Conv2d(16, 32, kernel_size=4)
        self.fc1 = nn.Linear(32 * 4 * 4, 32)
        self.fc2 = nn.Linear(32, 10)

    def forward(self, x):
        x = f.relu(self.conv1(x))
        x = f.max_pool2d(x, 2)
        x = f.relu(self.conv2(x))
        x = f.max_pool2d(x, 2)
        x = x.view(-1, 32 * 4 * 4)
        x = f.relu(self.fc1(x))
        x = self.fc2(x)
        return x

# 定义模型、损失函数、优化器
from model_class import Net
model = Net()
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=0.01)

2.加载已有或下载mnist数据集

# 数据加载与预处理
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307,), (0.3081,))  # MNIST数据集的均值和标准差
])

train_dataset = datasets.MNIST(root='mnist_data', train=True, download=False, transform=transform)
test_dataset = datasets.MNIST(root='mnist_data', train=False, download=False, transform=transform)

train_loader = DataLoader(train_dataset, batch_size=512, shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=512)

3.模型训练

# 模型训练
def train(model, train_loader, criterion, optimizer, epoch, train_losses):
    model.train()
    train_loss = 0
    for batch_idx, (data, target) in enumerate(train_loader):
        optimizer.zero_grad()
        output = model(data)
        loss = criterion(output, target)
        loss.backward()
        optimizer.step()

        train_loss += loss.item()
        if batch_idx % 100 == 0:
            print(f'Epoch: {epoch + 1}, Batch: {batch_idx}, Loss: {loss.item():.4f}')

    avg_train_loss = train_loss / len(train_loader)
    train_losses.append(avg_train_loss)
    return avg_train_loss

4.模型的验证与测试

# 模型验证
def evaluate(model, test_loader, criterion, test_losses, accuracies):
    model.eval()
    test_loss = 0
    correct = 0
    # 禁用梯度计算区域
    with torch.no_grad():
        for data, target in test_loader:
            output = model(data)
            test_loss += criterion(output, target).item()
            pred = output.argmax(dim=1, keepdim=True)
            correct += pred.eq(target.view_as(pred)).sum().item()

    avg_test_loss = test_loss / len(test_loader)
    accuracy = 100. * correct / len(test_loader.dataset)

    test_losses.append(avg_test_loss)
    accuracies.append(accuracy)

    print(
        f'\nTest set: Average loss: {avg_test_loss:.4f}, '
        f'Accuracy: {correct}/{len(test_loader.dataset)} ({accuracy:.2f}%)\n')
    return avg_test_loss, accuracy

5.绘制训练与测试的loss曲线和acc曲线并调优

def plot_loss_acc(train_losses, test_losses, accuracies):
    """
        针对训练过程绘制loss曲线和acc曲线

    Parameters
    ----------
    train_losses : list_like
        train loss list。
    test_losses : list_like
        test loss list。
    accuracies : list_like
        accuracies list。
    """
    plt.figure(figsize=(10, 4))

    plt.subplot(1, 2, 1)
    plt.plot(train_losses, 'o-', label='Training Loss')
    plt.plot(test_losses, 's-', label='Test Loss')
    plt.xlabel('Epoch')
    plt.ylabel('Loss')
    plt.title('Training and Test Loss')
    plt.legend()
    # plt.grid(True)

    plt.subplot(1, 2, 2)
    plt.plot(accuracies, 'd-', color='green')
    plt.xlabel('Epoch')
    plt.ylabel('Accuracy (%)')
    plt.title('Test Accuracy')
    # plt.grid(True)

    plt.tight_layout()
    timestamp = str(dt.now().strftime("%y%m%d%H%M%S"))
    plt.savefig('./results/training_metrics_{time}.png'.format(time=timestamp))
    plt.show()

6.模型预测与结果可视化

1. 加载训练好的模型和参数，并将模型设置为评估模式

from model_class import Net
model = Net()
model.load_state_dict(torch.load('mnist_cnn_model_params.pth'))
model.eval()

2. 加载测试集数据

# 测试集数据加载
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307,), (0.3081,))  # MNIST数据集的均值和标准差
])
test_dataset = datasets.MNIST(root='mnist_data', train=False, download=False, transform=transform)
test_loader = DataLoader(test_dataset, batch_size=512)

3. 预测结果，并将部分结果可视化展示

# 预测函数
def predict_random_samples(model, test_dataset, num_samples=9, max_show_num=16):
    """随机选择样本进行预测并可视化结果"""
    model.eval()
    indices = np.random.choice(len(test_dataset), num_samples, replace=False)

    # 计算子图网格的行数和列数
    cols = int(np.ceil(np.sqrt(min(num_samples, max_show_num))))  # 向上取整
    rows = int(np.ceil(min(num_samples, max_show_num) / cols))

    # 创建相应大小的子图网格
    fig, axes = plt.subplots(rows, cols, figsize=(cols * 2, rows * 2))

    # 如果只有一个子图，axes会是一个单独的对象，需要将其转为数组
    if num_samples == 1:
        axes = np.array([axes])
    else:
        # 将多维数组展平为一维数组
        axes = axes.flatten()

    # fig, axes = plt.subplots(3, 3, figsize=(10, 6))
    # axes = axes.flatten()
    correct = 0
    with torch.no_grad():
        for i, idx in enumerate(indices):
            image, true_label = test_dataset[idx]
            output = model(image.unsqueeze(0))
            pred = output.argmax(dim=1)
            correct += pred.eq(true_label).sum().item()

            # 反标准化以便正确显示图像
            img = image.squeeze().numpy() * 0.3081 + 0.1307

            # 只处理有效的子图索引
            if i < len(axes) and i <= max_show_num:
                axes[i].imshow(img, cmap='gray')
                axes[i].set_title(f'Pred: {pred}, True: {true_label}',
                                  color=('green' if pred == true_label else 'red'))
                axes[i].axis('off')
        # 隐藏多余的子图
        for i in range(num_samples, len(axes)):
            axes[i].axis('off')

    accuracy = 100. * correct / num_samples

    print(
        f'Accuracy: {correct}/{num_samples} ({accuracy:.2f}%)\n')

    plt.tight_layout()
    timestamp = str(dt.now().strftime("%y%m%d%H%M%S"))
    plt.savefig('./results/prediction_samples_{time}.png'.format(time=timestamp))
    plt.show()
    print(f"预测样本已保存为 'prediction_samples_{timestamp}.png'")

可视化结果