Model Saving and Loading in PyTorch

state_dict

In PyTorch, the learnable parameters (i.e. weights and biases) of an torch.nn.Module model are contained in the model’s parameters (accessed with model.parameters()). A state_dict is simply a Python dictionary object that maps each layer to its parameter tensor. Note that only layers with learnable parameters (convolutional layers, linear layers, etc.) and registered buffers (batchnorm’s running_mean) have entries in the model’s state_dict. Optimizer objects (torch.optim) also have a state_dict, which contains information about the optimizer’s state, as well as the hyperparameters used.

Because state_dict objects are Python dictionaries, they can be easily saved, updated, altered, and restored, adding a great deal of modularity to PyTorch models and optimizers.

import torch
import torch.nn as nn
import torch.optim as optim
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 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])

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': [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]}]

Saving and Loading Model

torch.save(model.state_dict(), "./model.pth")

# model = TheModelClass(*args, **kwargs)
model.load_state_dict(torch.load("./model.pth"))
model.eval()

TheModelClass(
  (conv1): Conv2d(3, 6, kernel_size=(5, 5), stride=(1, 1))
  (pool): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (conv2): Conv2d(6, 16, kernel_size=(5, 5), stride=(1, 1))
  (fc1): Linear(in_features=400, out_features=120, bias=True)
  (fc2): Linear(in_features=120, out_features=84, bias=True)
  (fc3): Linear(in_features=84, out_features=10, bias=True)
)

Save load entire model

torch.save(model, 'entire_model.pth')

entire_model = torch.load('entire_model.pth')
entire_model.eval()

TheModelClass(
  (conv1): Conv2d(3, 6, kernel_size=(5, 5), stride=(1, 1))
  (pool): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (conv2): Conv2d(6, 16, kernel_size=(5, 5), stride=(1, 1))
  (fc1): Linear(in_features=400, out_features=120, bias=True)
  (fc2): Linear(in_features=120, out_features=84, bias=True)
  (fc3): Linear(in_features=84, out_features=10, bias=True)
)

Saving & Loading a General Checkpoint for Inference and/or Resuming Training

epoch = 5
loss = nn.CrossEntropyLoss()

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

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

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

model.eval()

TheModelClass(
  (conv1): Conv2d(3, 6, kernel_size=(5, 5), stride=(1, 1))
  (pool): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (conv2): Conv2d(6, 16, kernel_size=(5, 5), stride=(1, 1))
  (fc1): Linear(in_features=400, out_features=120, bias=True)
  (fc2): Linear(in_features=120, out_features=84, bias=True)
  (fc3): Linear(in_features=84, out_features=10, bias=True)
)

References

• https://pytorch.org/tutorials/beginner/saving_loading_models.html