pytorch cv自带预训练模型再微调

参考：
https://pytorch.org/docs/0.4.1/torchvision/models.html
https://zhuanlan.zhihu.com/p/436574436
https://blog.csdn.net/u014297502/article/details/125884141

Network	Top-1 error	Top-5 error
AlexNet	43.45	20.91
VGG-11	30.98	11.37
VGG-13	30.07	10.75
VGG-16	28.41	9.62
VGG-19	27.62	9.12
VGG-11 with batch normalization	29.62	10.19
VGG-13 with batch normalization	28.45	9.63
VGG-16 with batch normalization	26.63	8.50
VGG-19 with batch normalization	25.76	8.15
ResNet-18	30.24	10.92
ResNet-34	26.70	8.58
ResNet-50	23.85	7.13
ResNet-101	22.63	6.44
ResNet-152	21.69	5.94
SqueezeNet 1.0	41.90	19.58
SqueezeNet 1.1	41.81	19.38
Densenet-121	25.35	7.83
Densenet-169	24.00	7.00
Densenet-201	22.80	6.43
Densenet-161	22.35	6.20
Inception v3	22.55	6.44

自带预训练模型对手写数字微调

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

# 定义数据转换和加载 MNIST 数据集
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.5,), (0.5,))
])

trainset = torchvision.datasets.MNIST(root='./data', train=True, download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=64, shuffle=True)

testset = torchvision.datasets.MNIST(root='./data', train=False, download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=64, shuffle=False)

# 加载 torchvision 中的预训练模型
model = torchvision.models.resnet18(pretrained=True)

#下面两行冻结模型的所有参数；不加这两行就是全量训练
for param in model.parameters():
    param.requires_grad = False
    

model.conv1 = nn.Conv2d(1, 64, kernel_size=7, stride=2, padding=3, bias=False)  # 修改输入通道数为1  （因为resnet18输入图像维度3，MNIST图片维度是1）

#修改模型的最后一层/分类器，用于适应特定任务的类别数量
num_features = model.fc.in_features
model.fc = nn.Linear(num_features, 10)

# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.001, momentum=0.9)

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)

##训练
epochs = 10
for epoch in range(epochs):
    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        inputs, labels = data
        # print(inputs.shape)
        inputs, labels = inputs.to(device), labels.to(device)

        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        running_loss += loss.item()
        if i % 200 == 199:
            print('[%d, %5d] loss: %.3f' % (epoch + 1, i + 1, running_loss / 200))
            running_loss = 0.0

### 验证
correct = 0
total = 0
with torch.no_grad():
    for data in testloader:
        images, labels = data
        images, labels = images.to(device), labels.to(device)
        outputs = model(images)
        _, 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: %.2f %%' % (100 * correct / total))