当前位置：首页 > article >正文

PyTorch实战-手写数字识别-CNN模型

article 2024/11/5 13:45:32

1 需求

2 接口

3 示例

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

# 定义超参数
batch_size = 128
learning_rate = 0.001
num_epochs = 10

# 数据预处理
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307,), (0.3081,))
])

# 加载 MNIST 数据集
train_dataset = datasets.MNIST(root='./data', train=True, transform=transform, download=True)
test_dataset = datasets.MNIST(root='./data', train=False, transform=transform)

train_loader = torch.utils.data.DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=True)
test_loader = torch.utils.data.DataLoader(dataset=test_dataset, batch_size=batch_size, shuffle=False)

# 定义 CNN 模型
class CNNModel(nn.Module):
    def __init__(self):
        super(CNNModel, self).__init__()
        self.conv1 = nn.Conv2d(1, 32, kernel_size=5)
        self.conv2 = nn.Conv2d(32, 64, kernel_size=5)
        self.fc1 = nn.Linear(64 * 4 * 4, 1024)
        self.fc2 = nn.Linear(1024, 10)

    def forward(self, x):
        x = nn.functional.relu(self.conv1(x))
        x = nn.functional.max_pool2d(x, 2)
        x = nn.functional.relu(self.conv2(x))
        x = nn.functional.max_pool2d(x, 2)
        x = x.view(-1, 64 * 4 * 4)
        x = nn.functional.relu(self.fc1(x))
        x = self.fc2(x)
        return nn.functional.log_softmax(x, dim=1)

# 实例化模型
model = CNNModel()

# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=learning_rate)

# 训练模型
for epoch in range(num_epochs):
    for batch_idx, (data, targets) in enumerate(train_loader):
        # 前向传播
        outputs = model(data)
        loss = criterion(outputs, targets)

        # 反向传播和优化
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if batch_idx % 100 == 0:
            print(f'Epoch [{epoch + 1}/{num_epochs}], Step [{batch_idx + 1}/{len(train_loader)}], Loss: {loss.item()}')

# 在测试集上评估模型
model.eval()
with torch.no_grad():
    correct = 0
    total = 0
    for data, targets in test_loader:
        outputs = model(data)
        _, predicted = torch.max(outputs.data, 1)
        total += targets.size(0)
        correct += (predicted == targets).sum().item()

    accuracy = correct / total
    print(f'Test Accuracy: {accuracy * 100:.2f}%')