利用pytorch复现LeNet-5的MNIST手写数字分类

最近学习了pytorch的入门教程，https://github.com/yunjey/pytorch-tutorial，发现里面没有LeNet-5的复现，我就自己写了一个，发现其实和作者给的例子的结果差不多，都是98%多一点。做个记号，以免以后忘了。

#-*-coding:utf-8-*-
import torch
import torch.nn as nn
import torchvision
import  torchvision.transforms as transforms

device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')

num_epochs = 5
num_classes = 10
batch_size = 100
learning_rate = 0.001

# MNIST dataset
train_dataset = torchvision.datasets.MNIST(root='data/',
                                           train=True,
                                           transform=transforms.ToTensor(),
                                           download=True)

test_dataset = torchvision.datasets.MNIST(root='data/',
                                          train=False,
                                          transform=transforms.ToTensor())

# Data loader
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)

class LetNet5(nn.Module):
    def __init__(self, num_clases=10):
        super(LetNet5, self).__init__()

        self.c1 = nn.Sequential(
            nn.Conv2d(1, 6, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(6),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2)
        )

        self.c2 = nn.Sequential(
            nn.Conv2d(6, 16, kernel_size=5),
            nn.BatchNorm2d(16),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2)
        )

        self.c3 = nn.Sequential(
            nn.Conv2d(16, 120, kernel_size=5),
            nn.BatchNorm2d(120),
            nn.ReLU()
        )

        self.fc1 = nn.Sequential(
            nn.Linear(120, 84),
            nn.ReLU()
        )

        self.fc2 = nn.Sequential(
            nn.Linear(84, num_classes),
            nn.LogSoftmax()
        )

    def forward(self, x):
        out = self.c1(x)
        out = self.c2(out)
        out = self.c3(out)
        out = out.reshape(out.size(0), -1)
        out = self.fc1(out)
        out = self.fc2(out)
        return out


model = LetNet5(num_classes).to(device)

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

total_step = len(train_loader)
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        images = images.to(device)
        labels = labels.to(device)

        # Forward pass
        outputs = model(images)
        loss = criterion(outputs, labels)

        # Backward and optimize
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

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

# Test the model
model.eval()  # eval mode (batchnorm uses moving mean/variance instead of mini-batch mean/variance)
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.to(device)
        labels = labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

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

torch.save(model.state_dict(), 'LetNet-5.ckpt')

最后的结果

Test Accuracy of the model on the 10000 test images: 98.89 %

为什么我用谷歌的Colab训练达到了99% ？

Test Accuracy of the model on the 10000 test images: 99.1 %