【PyTorch】保存/加载模型参数

1 操作步骤

• 保存模型
  使用torch.save(model, 'model.ckpt')保存模型参数

• 加载模型
  使用model.load_state_dict(torch.load('model.ckpt'))加载模型，不过在这之前模型的网络结构也需要进行定义。加载之后，要进行测试，则需要使用model.eval()来固定模型参数（BatchNorm不再起作用），并去除Dropout操作；要继续进行训练，则正常放置训练模块即可。

2 代码实例

• 保存模型

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
learning_rate = 0.001
batch_size = 100

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()
)
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 ConvNet(nn.Module):
    def __init__(self, num_classes = 10):
        super(ConvNet, self).__init__()
        self.layer1 = nn.Sequential(
            nn.Conv2d(in_channels=1, out_channels=16, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(16),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2)
        )
        self.layer2 = nn.Sequential(
            nn.Conv2d(in_channels=16, out_channels=32, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(32),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2)
        )
        self.fc = nn.Linear(32*7*7, num_classes)
    def forward(self, x):
        out = self.layer1(x)
        out = self.layer2(out)
        out = out.reshape(out.size(0), -1)
        out = self.fc(out)
        return out

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

model.train()

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)
        outputs = model(images)
        loss = criterion(outputs, labels)
        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()))

model.eval()
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: {:.4f} %'.format(100 * correct / total))

torch.save(model.state_dict, 'model.ckpt') # 保存模型参数

• 加载模型

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
learning_rate = 0.001
batch_size = 100

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()
)
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 ConvNet(nn.Module):
    def __init__(self, num_classes = 10):
        super(ConvNet, self).__init__()
        self.layer1 = nn.Sequential(
            nn.Conv2d(in_channels=1, out_channels=16, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(16),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2)
        )
        self.layer2 = nn.Sequential(
            nn.Conv2d(in_channels=16, out_channels=32, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(32),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2)
        )
        self.fc = nn.Linear(32*7*7, num_classes)
    def forward(self, x):
        out = self.layer1(x)
        out = self.layer2(out)
        out = out.reshape(out.size(0), -1)
        out = self.fc(out)
        return out

model = ConvNet(num_classes).to(device)

model.load_state_dict(torch.load('model.ckpt')) # 加载模型参数
model.eval()

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: {:.4f} %'.format(100 * correct / total))