mnist手写数字识别pytorch的代码

下面是一个简单的 PyTorch 实现 MNIST 手写数字识别的代码：

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

# 定义超参数
batch_size = 64
learning_rate = 0.01
num_epochs = 10

# 下载和加载数据集
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)

# 创建数据加载器
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)

# 定义模型
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.pool = nn.MaxPool2d(2)
        self.fc = nn.Linear(320, 10)

    def forward(self, x):
        x = self.pool(nn.functional.relu(self.conv1(x)))
        x = self.pool(nn.functional.relu(self.conv2(x)))
        x = x.view(-1, 320)
        x = self.fc(x)
        return x

# 实例化模型和损失函数
model = Net()
criterion = nn.CrossEntropyLoss()

# 使用随机梯度下降优化器
optimizer = optim.SGD(model.parameters(), lr=learning_rate)

# 训练模型
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        # 将数据加载到 GPU 中
        images = images.cuda()
        labels = labels.cuda()

        # 前向传播和计算损失
        outputs = model(images)
        loss = criterion(outputs, labels)

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

        # 每 100 个批次输出一次日志信息
        if (i + 1) % 100 == 0:
            print('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'
                  .format(epoch + 1, num_epochs, i + 1, len(train_loader), loss.item()))

# 测试模型
model.eval()
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        # 将数据加载到 GPU 中
        images = images.cuda()
        labels = labels.cuda()

        # 计算输出并获取预测结果
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)

        # 统计正确预测的数量
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

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

这个代码使用了一个简单的卷积神经网络，包括两个卷积层、两个最大池化层和一个全连接层。训练过程中使用随机梯度下降优化器，测试过程中计算模型的准确率。