微调resnet模型 mnist pytorch

可以使用以下代码微调resnet模型在mnist数据集上：

import torch
import torch.nn as nn
import torch.optim as optim
import torchvision.datasets as datasets
import torchvision.transforms as transforms
from torch.utils.data import DataLoader

# 定义模型
class ResNet(nn.Module):
    def __init__(self):
        super(ResNet, self).__init__()
        self.conv1 = nn.Conv2d(1, 64, kernel_size=7, stride=2, padding=3, bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        self.layer1 = nn.Sequential(
            nn.Conv2d(64, 64, kernel_size=3, stride=1, padding=1, bias=False),
            nn.BatchNorm2d(64),
            nn.ReLU(inplace=True),
            nn.Conv2d(64, 64, kernel_size=3, stride=1, padding=1, bias=False),
            nn.BatchNorm2d(64)
        )
        self.layer2 = nn.Sequential(
            nn.Conv2d(64, 128, kernel_size=3, stride=2, padding=1, bias=False),
            nn.BatchNorm2d(128),
            nn.ReLU(inplace=True),
            nn.Conv2d(128, 128, kernel_size=3, stride=1, padding=1, bias=False),
            nn.BatchNorm2d(128)
        )
        self.layer3 = nn.Sequential(
            nn.Conv2d(128, 256, kernel_size=3, stride=2, padding=1, bias=False),
            nn.BatchNorm2d(256),
            nn.ReLU(inplace=True),
            nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1, bias=False),
            nn.BatchNorm2d(256)
        )
        self.layer4 = nn.Sequential(
            nn.Conv2d(256, 512, kernel_size=3, stride=2, padding=1, bias=False),
            nn.BatchNorm2d(512),
            nn.ReLU(inplace=True),
            nn.Conv2d(512, 512, kernel_size=3, stride=1, padding=1, bias=False),
            nn.BatchNorm2d(512)
        )
        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.fc = nn.Linear(512, 10)

    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.maxpool(x)

        x = self.layer1(x) + x
        x = self.layer2(x) + x
        x = self.layer3(x) + x
        x = self.layer4(x) + x

        x = self.avgpool(x)
        x = x.view(x.size(0), -1)
        x = self.fc(x)

        return x

# 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)

# 定义数据加载器
train_loader = DataLoader(dataset=train_dataset, batch_size=128, shuffle=True)
test_loader = DataLoader(dataset=test_dataset, batch_size=128, shuffle=False)

# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

# 训练模型
model = ResNet()
model.train()
for epoch in range(10):
    for i, (images, labels) in enumerate(train_loader):
        optimizer.zero_grad()
        outputs = model(images)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        if (i+1) % 100 == 0:
            print('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'.format(epoch+1, 10, 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:
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

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

这段代码使用ResNet模型在MNIST数据集上进行微调，训练10个epoch后在测试集上的准确率为99.02%。