用pytorch实现简单的手写数字识别

好的，下面是使用 PyTorch 实现手写数字识别的基本步骤：

1. 导入必要的库：

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

2. 准备数据集：

手写数字数据集可以通过 `torchvision.datasets` 库中的 `MNIST` 类来获取。我们需要对数据进行预处理，将像素值归一化到 0 到 1 之间，并将其转换为 PyTorch 张量。代码如下：

transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.5,), (0.5,))
])

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

3. 定义模型：

我们将使用一个简单的卷积神经网络来识别手写数字。代码如下：

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
        self.fc1 = nn.Linear(320, 50)
        self.fc2 = nn.Linear(50, 10)

    def forward(self, x):
        x = nn.functional.relu(nn.functional.max_pool2d(self.conv1(x), 2))
        x = nn.functional.relu(nn.functional.max_pool2d(self.conv2(x), 2))
        x = x.view(-1, 320)
        x = nn.functional.relu(self.fc1(x))
        x = self.fc2(x)
        return nn.functional.log_softmax(x, dim=1)

net = Net()

4. 训练模型：

我们将使用交叉熵损失函数和随机梯度下降优化器来训练模型。代码如下：

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.01, momentum=0.5)

def train(epoch):
    net.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        optimizer.zero_grad()
        output = net(data)
        loss = criterion(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()))

for epoch in range(1, 11):
    train(epoch)

5. 测试模型：

我们将使用测试集来评估模型的性能。代码如下：

def test():
    net.eval()
    test_loss = 0
    correct = 0
    with torch.no_grad():
        for data, target in test_loader:
            output = net(data)
            test_loss += criterion(output, target).item()
            pred = output.argmax(dim=1, keepdim=True)
            correct += pred.eq(target.view_as(pred)).sum().item()

    test_loss /= len(test_loader.dataset)

    print('Test set: