PyTorch 手写数字识别代码示例

以下是 PyTorch 手写数字识别代码的示例：

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

# 定义神经网络模型
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 32, kernel_size=5)
        self.conv2 = nn.Conv2d(32, 64, kernel_size=5)
        self.fc1 = nn.Linear(1024, 256)
        self.fc2 = nn.Linear(256, 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, 1024)
        x = nn.functional.relu(self.fc1(x))
        x = self.fc2(x)
        return nn.functional.log_softmax(x, dim=1)

# 定义训练函数
def train(model, device, train_loader, optimizer, 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 = nn.functional.nll_loss(output, 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()))

# 定义测试函数
def test(model, device, test_loader):
    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 += nn.functional.nll_loss(output, target, reduction='sum').item() # sum up batch loss
            pred = output.argmax(dim=1, keepdim=True) # get the index of the max log-probability
            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)))

# 设置训练参数
batch_size = 64
learning_rate = 0.01
epochs = 5
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# 加载MNIST数据集并进行预处理
train_dataset = datasets.MNIST(root='./data', train=True, transform=transforms.ToTensor(), download=True)
test_dataset = datasets.MNIST(root='./data', train=False, transform=transforms.ToTensor(), download=True)
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=batch_size, shuffle=True)

# 创建模型和优化器
model = Net().to(device)
optimizer = optim.SGD(model.parameters(), lr=learning_rate)

# 训练和测试模型
for epoch in range(1, epochs + 1):
    train(model, device, train_loader, optimizer, epoch)
    test(model, device, test_loader)

此代码使用 PyTorch 中的卷积神经网络（CNN）模型对 MNIST 数据集进行手写数字识别。具体步骤如下：

定义一个包含两个卷积层和两个全连接层的 CNN 模型。其中，卷积层使用 ReLU 函数作为激活函数，全连接层使用 Log Softmax 函数作为激活函数。
定义训练函数和测试函数，用于训练和测试 CNN 模型。训练函数使用随机梯度下降（SGD）算法进行优化，测试函数用于评估模型的性能。
加载 MNIST 数据集并进行预处理，包括将图像转换为张量、将像素值归一化等。
创建 CNN 模型和优化器。
在训练集上训练模型，然后在测试集上测试模型。

该模型在 5 个 epoch 的训练后，可以在测试集上达到超过 99% 的准确率。