jupyter训练mnist数据集

以下是使用Jupyter Notebook训练MNIST数据集的步骤：

1. 导入所需的库和模块：

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

2. 定义数据预处理和加载器：

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

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

train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=64, shuffle=True)
test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=64, shuffle=False)

3. 定义模型结构：

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)

model = Net()

4. 定义损失函数和优化器：

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

5. 训练模型：

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

6. 在测试集上评估模型：

def test():
    model.eval()
    test_loss = 0
    correct = 0
    with torch.no_grad():
        for data, target in test_loader:
            output = model(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)
    accuracy = 100. * correct / len(test_loader.dataset)
    print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.2f}%)\n'.format(
        test_loss, correct, len(test_loader.dataset), accuracy))

test()