mnist pytorch

MNIST是一个手写数字识别数据集，其中包含60,000个训练样本和10,000个测试样本。在PyTorch中，可以使用torchvision库加载MNIST数据集。

以下是一个使用PyTorch训练MNIST的示例代码：

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

# 定义数据转换
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307,), (0.3081,))
])

# 加载数据集
trainset = torchvision.datasets.MNIST(root='./data', train=True,
                                      download=True, transform=transform)
testset = torchvision.datasets.MNIST(root='./data', train=False,
                                     download=True, transform=transform)

# 定义数据加载器
trainloader = torch.utils.data.DataLoader(trainset, batch_size=64,
                                          shuffle=True, num_workers=2)
testloader = torch.utils.data.DataLoader(testset, batch_size=64,
                                         shuffle=False, num_workers=2)

# 定义模型
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 32, kernel_size=3)
        self.conv2 = nn.Conv2d(32, 64, kernel_size=3)
        self.dropout1 = nn.Dropout2d(0.25)
        self.dropout2 = nn.Dropout2d(0.5)
        self.fc1 = nn.Linear(9216, 128)
        self.fc2 = nn.Linear(128, 10)

    def forward(self, x):
        x = self.conv1(x)
        x = nn.functional.relu(x)
        x = self.conv2(x)
        x = nn.functional.relu(x)
        x = nn.functional.max_pool2d(x, 2)
        x = self.dropout1(x)
        x = torch.flatten(x, 1)
        x = self.fc1(x)
        x = nn.functional.relu(x)
        x = self.dropout2(x)
        x = self.fc2(x)
        output = nn.functional.log_softmax(x, dim=1)
        return output

# 训练模型
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
net = Net().to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adadelta(net.parameters(), lr=0.1)

for epoch in range(10):
    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        inputs, labels = data[0].to(device), data[1].to(device)
        optimizer.zero_grad()
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        running_loss += loss.item()
        if i % 100 == 99:
            print('[%d, %5d] loss: %.3f' %
                  (epoch + 1, i + 1, running_loss / 100))
            running_loss = 0.0

# 测试模型
correct = 0
total = 0
with torch.no_grad():
    for data in testloader:
        inputs, labels = data[0].to(device), data[1].to(device)
        outputs = net(inputs)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

print('Accuracy of the network on the 10000 test images: %d %%' % (
    100 * correct / total))

在这个示例中，我们定义了一个包含两个卷积层和两个全连接层的神经网络模型，并使用Adadelta优化器训练模型。最后，我们在测试集上评估了模型的准确性。