使用Fashion MNIST 对LeNet进行训练和测试。优化算法采用 torchoptimSGD 或 torchoptimAdam。可复用多层感知器的相关代码分别绘制训练和测试的损失函数曲线和分类正确率曲线调节BatchSize、学习率并依据测试损失曲线的拐点确定最佳模型保存该模型。

首先，我们需要下载Fashion MNIST数据集并对其进行预处理。

import torch
import torchvision
import torchvision.transforms as transforms

# 数据预处理
transform = transforms.Compose(
    [transforms.ToTensor(),
     transforms.Normalize((0.5,), (0.5,))])

trainset = torchvision.datasets.FashionMNIST(root='./data', train=True,
                                        download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=4,
                                          shuffle=True, num_workers=2)

testset = torchvision.datasets.FashionMNIST(root='./data', train=False,
                                       download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=4,
                                         shuffle=False, num_workers=2)

classes = ('T-shirt/top', 'Trouser', 'Pullover', 'Dress',
           'Coat', 'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot')

接下来，我们定义LeNet模型。

import torch.nn as nn
import torch.nn.functional as F

class LeNet(nn.Module):
    def __init__(self):
        super(LeNet, self).__init__()
        self.conv1 = nn.Conv2d(1, 6, 5)
        self.pool1 = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.pool2 = nn.MaxPool2d(2, 2)
        self.fc1 = nn.Linear(16 * 4 * 4, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        x = self.pool1(F.relu(self.conv1(x)))
        x = self.pool2(F.relu(self.conv2(x)))
        x = x.view(-1, 16 * 4 * 4)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

net = LeNet()

接下来，我们定义优化器和损失函数。

import torch.optim as optim

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

现在，我们可以开始训练模型了。

import matplotlib.pyplot as plt

# 训练模型
def train(net, trainloader, optimizer, criterion, num_epochs):
    loss_list = []
    acc_list = []
    for epoch in range(num_epochs):
        running_loss = 0.0
        correct = 0
        total = 0
        for i, data in enumerate(trainloader, 0):
            inputs, labels = data
            optimizer.zero_grad()
            outputs = net(inputs)
            loss = criterion(outputs, labels)
            loss.backward()
            optimizer.step()
            
            running_loss += loss.item()
            _, predicted = torch.max(outputs.data, 1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
            
        loss_list.append(running_loss / len(trainloader))
        acc_list.append(correct / total)
        print('Epoch %d, Loss: %.3f, Accuracy: %.3f' % (epoch+1, running_loss / len(trainloader), correct / total))
        
    print('Finished Training')
    return loss_list, acc_list

num_epochs = 10
loss_list, acc_list = train(net, trainloader, optimizer, criterion, num_epochs)

# 绘制训练损失函数曲线
plt.plot(loss_list)
plt.title('Training Loss')
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.show()

# 绘制训练分类正确率曲线
plt.plot(acc_list)
plt.title('Training Accuracy')
plt.xlabel('Epoch')
plt.ylabel('Accuracy')
plt.show()

接下来，我们测试模型。

# 测试模型
def test(net, testloader, criterion):
    loss_list = []
    acc_list = []
    with torch.no_grad():
        running_loss = 0.0
        correct = 0
        total = 0
        for data in testloader:
            images, labels = data
            outputs = net(images)
            loss = criterion(outputs, labels)
            
            running_loss += loss.item()
            _, predicted = torch.max(outputs.data, 1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
            
        loss_list.append(running_loss / len(testloader))
        acc_list.append(correct / total)
        print('Test Loss: %.3f, Accuracy: %.3f' % (running_loss / len(testloader), correct / total))
    
    return loss_list, acc_list

loss_list, acc_list = test(net, testloader, criterion)

# 绘制测试损失函数曲线
plt.plot(loss_list)
plt.title('Test Loss')
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.show()

# 绘制测试分类正确率曲线
plt.plot(acc_list)
plt.title('Test Accuracy')
plt.xlabel('Epoch')
plt.ylabel('Accuracy')
plt.show()

最后，我们可以保存模型。

# 保存模型
torch.save(net.state_dict(), 'lenet.pth')

现在，我们已经完成了对Fashion MNIST数据集的LeNet模型的训练和测试，并保存了最佳模型。你可以调整BatchSize和学习率来看看不同的结果