pytorch保存和加载模型

来自官方教程链接,做个记录

什么是STATE_DICT?

在pytorch中，网络的可学习的参数可以通过model.parameters() 获得。一个state_dict 就是简单的python字典，将每一层的可学习参数保存起来，通常权重和优化器有一个这样的东西。
例子：

# Define model
class TheModelClass(nn.Module):
    def __init__(self):
        super(TheModelClass, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 16 * 5 * 5)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x
# Initialize model
model = TheModelClass()

#Initialize optimizer
optimizer = optim.SGD(model.parameters(), lr=0.001, momentum=0.9)

# Print model's state_dict
print("Model's state_dict:")
for param_tensor in model.state_dict():
    print(param_tensor, "\t", model.state_dict()[param_tensor].size())

# Print optimizer's state_dict
print("Optimizer's state_dict:")
for var_name in optimizer.state_dict():
    print(var_name, "\t", optimizer.state_dict()[var_name])

在上面我们定义了一个简单的CNN和优化器，打印他的状态字典可以得到：

Model's state_dict:
conv1.weight     torch.Size([6, 3, 5, 5])
conv1.bias   torch.Size([6])
conv2.weight     torch.Size([16, 6, 5, 5])
conv2.bias   torch.Size([16])
fc1.weight   torch.Size([120, 400])
fc1.bias     torch.Size([120])
fc2.weight   torch.Size([84, 120])
fc2.bias     torch.Size([84])
fc3.weight   torch.Size([10, 84])
fc3.bias     torch.Size([10])

Optimizer's state_dict:
state    {}
param_groups     [{'lr': 0.001, 'momentum': 0.9, 'dampening': 0, 'weight_decay': 0, 'nesterov': False, 'params': [4675713712, 4675713784, 4675714000, 4675714072, 4675714216, 4675714288, 4675714432, 4675714504, 4675714648, 4675714720]}]

可以看到state_dict的key就是参数的名字比如conv1.weight 和 conv1.bias 分别代表某一层的权重和偏置。value就是对应的值。

保存和加载模型

保存加载state_dict (推荐）

保存:
torch.save(model.state_dict(), PATH)
加载：

model = TheModelClass(*args, **kwargs)
model.load_state_dict(torch.load(PATH))
model.eval()

保存全部模型

保存:
torch.save(mode, PATH)
加载：

model = torch.load(PATH)
model.eval()

保存断点信息

保存

torch.save({
            'epoch': epoch,
            'model_state_dict': model.state_dict(),
            'optimizer_state_dict': optimizer.state_dict(),
            'loss': loss,
            ...
            }, PATH)

加载

model = TheModelClass(*args, **kwargs)
optimizer = TheOptimizerClass(*args, **kwargs)

checkpoint = torch.load(PATH)
model.load_state_dict(checkpoint['model_state_dict'])
optimizer.load_state_dict(checkpoint['optimizer_state_dict'])
epoch = checkpoint['epoch']
loss = checkpoint['loss']

model.eval()
# - or -
model.train()