头歌第4关：使用pytorch搭建卷积神经网络识别手写数字

好的，让我们来一步步完成这个任务吧！

首先，我们需要导入一些必要的库：

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

接着，我们需要定义一些超参数：

batch_size = 64
learning_rate = 0.01
num_epochs = 10

然后，我们需要加载MNIST数据集：

transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307,), (0.3081,))
])

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

接下来，我们需要定义卷积神经网络的结构：

class ConvNet(nn.Module):
    def __init__(self):
        super(ConvNet, self).__init__()

        self.conv1 = nn.Conv2d(1, 32, kernel_size=5, padding=2)
        self.conv2 = nn.Conv2d(32, 64, kernel_size=5, padding=2)
        self.pool = nn.MaxPool2d(2)
        self.fc1 = nn.Linear(64 * 7 * 7, 512)
        self.fc2 = nn.Linear(512, 10)

    def forward(self, x):
        x = self.pool(torch.relu(self.conv1(x)))
        x = self.pool(torch.relu(self.conv2(x)))
        x = x.view(-1, 64 * 7 * 7)
        x = torch.relu(self.fc1(x))
        x = self.fc2(x)
        return x

最后，我们需要定义损失函数和优化器，并开始训练：

model = ConvNet()

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=learning_rate)

for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        optimizer.zero_grad()
        outputs = model(images)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        if (i+1) % 100 == 0:
            print('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'.format(epoch+1, num_epochs, i+1, len(train_loader), loss.item()))

model.eval()

correct = 0
total = 0
with torch.no_grad():
    for images, labels in test_loader:
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

print('Accuracy of the model on the 10000 test images: {} %'.format(100 * correct / total))

这就是使用PyTorch搭建卷积神经网络识别手写数字的完整代码。