AlexNet模型手写数字识别pycharm

### 使用 AlexNet 实现手写数字识别 为了在 PyCharm 中使用 AlexNet 模型完成手写数字识别任务，可以按照以下方法构建完整的解决方案。以下是详细的说明： #### 1. 数据准备 手写数字识别通常使用的数据集是 MNIST 或 Fashion-MNIST。这些数据集可以直接通过 `torchvision.datasets` 加载[^2]。 加载数据的代码如下： ```python import torch from torchvision import datasets, transforms transform = transforms.Compose([ transforms.Resize((224, 224)), # 调整图像大小以适应 AlexNet 输入 (224x224) transforms.ToTensor(), # 将 PIL 图像转换为 Tensor transforms.Normalize([0.5], [0.5]) # 归一化处理 ]) 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 = torch.utils.data.DataLoader(dataset=train_dataset, batch_size=64, shuffle=True) test_loader = torch.utils.data.DataLoader(dataset=test_dataset, batch_size=64, shuffle=False) ``` #### 2. 定义 AlexNet 模型 AlexNet 是一种经典的卷积神经网络结构，适用于分类任务。由于 MNIST 的类别数为 10（代表 0 到 9），因此需要调整最后一层全连接层的输出维度为 10[^1]。 定义模型的代码如下： ```python import torch.nn as nn import torch.nn.functional as F class AlexNet(nn.Module): def __init__(self, num_classes=10): super(AlexNet, self).__init__() self.features = nn.Sequential( nn.Conv2d(1, 64, kernel_size=11, stride=4, padding=2), # 修改输入通道数为 1 nn.ReLU(inplace=True), nn.MaxPool2d(kernel_size=3, stride=2), nn.Conv2d(64, 192, kernel_size=5, padding=2), nn.ReLU(inplace=True), nn.MaxPool2d(kernel_size=3, stride=2), nn.Conv2d(192, 384, kernel_size=3, padding=1), nn.ReLU(inplace=True), nn.Conv2d(384, 256, kernel_size=3, padding=1), nn.ReLU(inplace=True), nn.Conv2d(256, 256, kernel_size=3, padding=1), nn.ReLU(inplace=True), nn.MaxPool2d(kernel_size=3, stride=2), ) self.avgpool = nn.AdaptiveAvgPool2d((6, 6)) self.classifier = nn.Sequential( nn.Dropout(), nn.Linear(256 * 6 * 6, 4096), nn.ReLU(inplace=True), nn.Dropout(), nn.Linear(4096, 4096), nn.ReLU(inplace=True), nn.Linear(4096, num_classes), ) def forward(self, x): x = self.features(x) x = self.avgpool(x) x = torch.flatten(x, 1) x = self.classifier(x) return x ``` #### 3. 训练过程 训练过程中需要设置损失函数、优化器以及评估指标。常用的交叉熵损失函数适合多分类问题。 训练代码如下： ```python device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') model = AlexNet(num_classes=10).to(device) criterion = nn.CrossEntropyLoss() optimizer = torch.optim.Adam(model.parameters(), lr=0.001) def train_model(model, criterion, optimizer, dataloader, epochs=10): model.train() for epoch in range(epochs): running_loss = 0.0 correct_predictions = 0 total_samples = 0 for inputs, labels in dataloader: inputs, labels = inputs.to(device), labels.to(device) optimizer.zero_grad() outputs = model(inputs) loss = criterion(outputs, labels) loss.backward() optimizer.step() _, preds = torch.max(outputs, 1) running_loss += loss.item() * inputs.size(0) correct_predictions += torch.sum(preds == labels.data) total_samples += labels.size(0) epoch_loss = running_loss / total_samples accuracy = correct_predictions.double() / total_samples print(f'Epoch {epoch+1}/{epochs}, Loss: {epoch_loss:.4f}, Accuracy: {accuracy:.4f}') train_model(model, criterion, optimizer, train_loader) ``` #### 4. 测试与验证 测试阶段用于评估模型性能。计算准确率或其他评价指标可以帮助了解模型的表现。 测试代码如下： ```python def test_model(model, dataloader): model.eval() correct_predictions = 0 total_samples = 0 with torch.no_grad(): for inputs, labels in dataloader: inputs, labels = inputs.to(device), labels.to(device) outputs = model(inputs) _, preds = torch.max(outputs, 1) correct_predictions += torch.sum(preds == labels.data) total_samples += labels.size(0) accuracy = correct_predictions.double() / total_samples print(f'Test Accuracy: {accuracy:.4f}') test_model(model, test_loader) ``` --- ### 注意事项 动态图机制可能增加调试难度，尤其是对于不熟悉张量形状变化的新手来说。建议逐步检查每一部分代码的功能和输出，确保其正确无误。 ---