举个栗子:
# 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])
输出
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]}]
保存:
torch.save(model.state_dict(), PATH)
加载:
model = TheModelClass(*args, **kwargs)
model.load_state_dict(torch.load(PATH))
model.eval()
假如我保存的时候是这样的
torch.save({
'model_state_dict': model.state_dict(),
'optimizer_state_dict': optimizer.state_dict(),
}, PATH)
那么加载的时候就是这样的
checkpoint = torch.load(PATH)
model.load_state_dict(checkpoint['model_state_dict'])
保存:
torch.save(model, PATH)
加载:
# Model class must be defined somewhere
model = torch.load(PATH)
model.eval()
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()
保存:
torch.save({
'modelA_state_dict': modelA.state_dict(),
'modelB_state_dict': modelB.state_dict(),
'optimizerA_state_dict': optimizerA.state_dict(),
'optimizerB_state_dict': optimizerB.state_dict(),
...
}, PATH)
加载:
modelA = TheModelAClass(*args, **kwargs)
modelB = TheModelBClass(*args, **kwargs)
optimizerA = TheOptimizerAClass(*args, **kwargs)
optimizerB = TheOptimizerBClass(*args, **kwargs)
checkpoint = torch.load(PATH)
modelA.load_state_dict(checkpoint['modelA_state_dict'])
modelB.load_state_dict(checkpoint['modelB_state_dict'])
optimizerA.load_state_dict(checkpoint['optimizerA_state_dict'])
optimizerB.load_state_dict(checkpoint['optimizerB_state_dict'])
modelA.eval()
modelB.eval()
# - or -
modelA.train()
modelB.train()
保存:
torch.save(modelA.state_dict(), PATH)
加载:
modelB = TheModelBClass(*args, **kwargs)
modelB.load_state_dict(torch.load(PATH), strict=False)
保存:
torch.save(model.state_dict(), PATH)
加载:
device = torch.device('cpu')
model = TheModelClass(*args, **kwargs)
model.load_state_dict(torch.load(PATH, map_location=device))
保存:
torch.save(model.state_dict(), PATH)
加载:
device = torch.device("cuda")
model = TheModelClass(*args, **kwargs)
model.load_state_dict(torch.load(PATH))
model.to(device)
# Make sure to call input = input.to(device) on any input tensors
# that you feed to the model
for state in optimizer.state.values():
for k, v in state.items():
if torch.is_tensor(v):
state[k] = v.cuda()
保存:
torch.save(model.state_dict(), PATH)
加载:
device = torch.device("cuda")
model = TheModelClass(*args, **kwargs)
model.load_state_dict(torch.load(PATH, map_location="cuda:0")) # Choose whatever GPU device number you want
model.to(device)
# Make sure to call input = input.to(device) on any input tensors that you feed to the model
保存:
torch.save(model.module.state_dict(), PATH)
加载:
Load to whatever device you want