torch.nn.Module.load_state_dict:
torch.nn.Module
是所有NN模块的基类，我们的模型都是其子类。
STATE_DICT
与.cpu()/.cuda()/.add_module()同样是模型的一个对象
是torch.nn.Module的可学习参数(即权重和偏差)，模块模型包含在model’s参数中(通过model.parameters()访问)。
state_dict是个简单的Python dictionary对象，它将每个层映射到它的参数张量。
ex
import torch
import torch.nn as nn
import torch.nn.functional as F
# 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 farward(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=torch.optim.SGD(model.parameters(),lr=1e-4,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])
out
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': 0.0001, 'momentum': 0.9, 'dampening': 0, 'weight_decay': 0, 'nesterov': False, 'params': [1310469552240, 1310469552384, 1310469552456, 1310469552528, 1310469552600, 1310469552672, 1310469552744, 1310469552816, 1310469552888, 1310469552960]}]
ref
https://www.jianshu.com/p/4905bf8e06e5
https://pytorch.org/tutorials/beginner/saving_loading_models.html#