Saving model state_dict in PyTorch

Introduction

Saving the model's state_dict lets you keep the learned settings so you can use or improve the model later without starting over.

You want to pause training and continue later without losing progress.

You finished training and want to save the model to make predictions later.

You want to share your trained model with others.

You want to keep different versions of your model during experiments.

Syntax

PyTorch

torch.save(model.state_dict(), 'filename.pth')

The state_dict is a dictionary that holds all the model's parameters (weights and biases).

The filename usually ends with '.pth' or '.pt' to indicate a PyTorch model file.

Examples

Save the model's parameters to a file named 'model_weights.pth'.

PyTorch

torch.save(model.state_dict(), 'model_weights.pth')

Save the model's parameters to a variable path for flexibility.

PyTorch

PATH = 'checkpoint.pth'
torch.save(model.state_dict(), PATH)

Sample Model

This code creates a simple model, prints its initial weights, saves the weights to a file, then loads them into a new model and prints the loaded weights to confirm they match.

PyTorch

import torch
import torch.nn as nn

# Define a simple model
class SimpleModel(nn.Module):
    def __init__(self):
        super(SimpleModel, self).__init__()
        self.linear = nn.Linear(2, 1)
    def forward(self, x):
        return self.linear(x)

# Create model instance
model = SimpleModel()

# Print initial weights
print('Initial weights:', model.linear.weight)

# Save the model's state_dict
torch.save(model.state_dict(), 'simple_model.pth')

# Load the state_dict into a new model to check
new_model = SimpleModel()
new_model.load_state_dict(torch.load('simple_model.pth'))

# Print loaded weights
print('Loaded weights:', new_model.linear.weight)

Important Notes

Always save the state_dict, not the whole model object, for better flexibility and compatibility.

When loading, create the model architecture first, then load the saved state_dict.

Use consistent file paths and names to avoid confusion.

Summary

Saving model state_dict stores only the model's learned parameters.

Use torch.save(model.state_dict(), 'file.pth') to save.

Load saved weights into the same model architecture with load_state_dict.

Practice

1. What does model.state_dict() in PyTorch contain?

easy

A. Only the optimizer settings

B. The learned parameters (weights and biases) of the model

C. The entire model architecture and code

D. The training dataset

Solution

1. Step 1: Understand what state_dict holds

   The state_dict stores all the learned parameters like weights and biases of the model layers.

2. Step 2: Differentiate from other components

   It does not include the model architecture code or optimizer settings, only the parameters.

3. Final Answer:

   The learned parameters (weights and biases) of the model -> Option B

4. Quick Check:

   state_dict = learned parameters [OK]

Hint: state_dict always means model weights only [OK]

Common Mistakes:

• Thinking state_dict saves the whole model code
• Confusing optimizer state with model state
• Assuming it saves the training data

2. Which of the following is the correct syntax to save a PyTorch model's state_dict to a file named 'model.pth'?

easy

A. torch.save(model.state_dict(), 'model.pth')

B. model.state_dict().save('model.pth')

C. model.save_state('model.pth')

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

Solution

1. Step 1: Recall the saving function

   In PyTorch, torch.save() is used to save objects to a file.

2. Step 2: Save only the state_dict

   To save the model parameters, you pass model.state_dict() to torch.save() along with the filename.

3. Final Answer:

   torch.save(model.state_dict(), 'model.pth') -> Option A

4. Quick Check:

   Use torch.save with state_dict [OK]

Hint: Use torch.save(model.state_dict(), filename) to save weights [OK]

Common Mistakes:

• Saving the whole model instead of state_dict
• Using non-existent save_state method
• Calling save on state_dict directly

3. Given the code below, what will be printed?

import torch
import torch.nn as nn

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(2, 1)

model = SimpleModel()
torch.save(model.state_dict(), 'weights.pth')
loaded_state = torch.load('weights.pth')
print(type(loaded_state))

medium

A.

B.

C.

D.

Solution

1. Step 1: Understand what torch.save stores

   Saving model.state_dict() stores an OrderedDict of parameter tensors.

2. Step 2: Loading with torch.load returns the same type

   When loaded, it returns an OrderedDict, not a Module or plain dict.

3. Final Answer:

   <class 'collections.OrderedDict'> -> Option C

4. Quick Check:

   state_dict loads as OrderedDict [OK]

Hint: state_dict loads as OrderedDict, not model or tensor [OK]

Common Mistakes:

• Expecting loaded_state to be a model instance
• Thinking it returns a plain dict
• Confusing with tensor type

4. You saved a model's state_dict with torch.save(model.state_dict(), 'model.pth'). Later, you try to load it with model.load_state_dict(torch.load('model.pth')) but get a runtime error about missing keys. What is the most likely cause?

medium

A. The model architecture does not match the saved state_dict

B. The file 'model.pth' is corrupted

C. You forgot to call model.eval() before loading

D. You used torch.save(model, 'model.pth') instead

Solution

1. Step 1: Understand load_state_dict requirements

   Loading weights requires the model architecture to match the saved parameters exactly.

2. Step 2: Identify cause of missing keys error

   If keys are missing, it usually means the model layers differ from those saved in the state_dict.

3. Final Answer:

   The model architecture does not match the saved state_dict -> Option A

4. Quick Check:

   Mismatch architecture causes missing keys error [OK]

Hint: Check model matches saved weights architecture [OK]

Common Mistakes:

• Assuming file corruption without checking
• Thinking eval mode affects loading
• Confusing saving whole model vs state_dict

5. You want to save a PyTorch model's state_dict after training and later load it to continue training on a different machine. Which sequence of steps is correct?

hard

A. Save model.state_dict() and optimizer.state_dict() together in one file, then load both on new machine

B. Save with torch.save(model, 'file.pth'), then load with model = torch.load('file.pth') without defining architecture

C. Save optimizer state only, then recreate model and optimizer on new machine

D. Save with torch.save(model.state_dict(), 'file.pth'), then on new machine create same model architecture and load with model.load_state_dict(torch.load('file.pth'))

Solution

1. Step 1: Save only model parameters

   Use torch.save(model.state_dict(), 'file.pth') to save learned weights.

2. Step 2: Recreate model architecture on new machine

   Define the same model class and create an instance before loading weights.

3. Step 3: Load saved weights into model

   Use model.load_state_dict(torch.load('file.pth')) to load parameters.

4. Final Answer:

   Save state_dict, recreate model, then load state_dict -> Option D

5. Quick Check:

   Save weights, recreate model, load weights [OK]

Hint: Always recreate model before loading state_dict [OK]

Common Mistakes:

• Trying to load weights without model definition
• Saving whole model causing compatibility issues
• Ignoring optimizer state when continuing training