Best model saving pattern in PyTorch - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

What does this PyTorch model saving code output?

Consider this PyTorch training loop snippet that saves the best model based on validation loss. What will be the content of the saved file 'best_model.pth' after training?

PyTorch

import torch
import torch.nn as nn

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

model = SimpleModel()
optimizer = torch.optim.SGD(model.parameters(), lr=0.1)

best_loss = float('inf')
for epoch in range(3):
    val_loss = 1.0 / (epoch + 1)  # simulated validation loss: 1.0, 0.5, 0.333...
    if val_loss < best_loss:
        best_loss = val_loss
        torch.save(model.state_dict(), 'best_model.pth')

loaded_state = torch.load('best_model.pth')
print(type(loaded_state))

A <class 'collections.OrderedDict'>

B FileNotFoundError

C <class 'dict'>

D <class 'torch.nn.Module'>

💡 Hint

torch.save(model.state_dict()) saves the model parameters as an OrderedDict.

torch.save(model.state_dict()) saves the model's parameters as an OrderedDict. Loading it with torch.load returns this OrderedDict, not the full model object.

❓ Model Choice

intermediate

Which PyTorch saving pattern ensures you can resume training with optimizer state?

You want to save your PyTorch model and optimizer states to resume training later exactly where you left off. Which saving pattern is best?

A torch.save({'model': model.state_dict(), 'optimizer': optimizer.state_dict()}, 'checkpoint.pth')

B torch.save(optimizer.state_dict(), 'optimizer.pth')

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

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

💡 Hint

You need both model and optimizer states in one file.

Saving a dictionary with both model and optimizer state_dicts allows resuming training with exact states.

❓ Hyperparameter

advanced

What is the best practice for saving model checkpoints during training?

During training, you want to save checkpoints to avoid losing progress. Which practice is best?

A Save checkpoint only when training loss decreases

B Save checkpoint every epoch regardless of performance

C Save checkpoint only at the end of training

D Save checkpoint only when validation accuracy improves

💡 Hint

Validation accuracy reflects generalization better than training loss.

Saving checkpoints when validation accuracy improves ensures you keep the best model generalizing to new data.

🔧 Debug

advanced

Why does loading a saved PyTorch model with torch.load('model.pth') fail?

You saved your model using torch.save(model, 'model.pth') but loading it with torch.load('model.pth') raises an error. What is the likely cause?

A Model was saved with state_dict, not full model

B File path is incorrect

C Model class definition is missing or different when loading

D torch.load only works with CPU models

💡 Hint

Full model saving requires the class code to be available when loading.

Saving the full model requires the exact model class code to be present when loading, otherwise torch.load fails.

🧠 Conceptual

expert

Why is saving only the model's state_dict preferred over saving the entire model in PyTorch?

Select the best reason why saving only the model's state_dict is recommended instead of saving the entire model object.

A Saving entire model is faster and more reliable

B State_dict files are smaller and more portable across PyTorch versions

C State_dict includes optimizer state automatically

D Entire model saving does not require model class definition when loading

💡 Hint

Think about portability and dependency on code.

Saving state_dict is smaller, more portable, and does not require the exact model class code when loading, unlike saving the entire model.

Practice

1. What is the best practice for saving a PyTorch model during training?

easy

A. Save the model only at the start of training.

B. Save the model only when it improves on validation data.

C. Save the model after every training batch.

D. Save the model only if the training loss increases.

Solution

1. Step 1: Understand model saving timing

   Saving the model only when validation improves ensures you keep the best version, avoiding unnecessary saves.

2. Step 2: Compare other options

   Saving every batch wastes space; saving at start or on loss increase is not useful for best model.

3. Final Answer:

   Save the model only when it improves on validation data. -> Option B

4. Quick Check:

   Save best validation model = C [OK]

Hint: Save model only on validation improvement to keep best [OK]

Common Mistakes:

• Saving model too frequently wastes storage
• Saving only at start misses improvements
• Saving on training loss increase is wrong

2. Which of the following is the correct PyTorch code to save only the model weights?

easy

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

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

C. model.save('model.pth')

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

Solution

1. Step 1: Identify correct saving method

   PyTorch saves weights using torch.save(model.state_dict(), filename).

2. Step 2: Check other options

   Saving the whole model (torch.save(model, 'model.pth')) is possible but less flexible; options C and D are invalid syntax.

3. Final Answer:

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

4. Quick Check:

   Save weights with state_dict() = A [OK]

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

Common Mistakes:

• Trying to save model directly without state_dict
• Using non-existent save methods on model
• Confusing saving weights vs full model

3. Given this code snippet, what will be printed?

import torch
import torch.nn as nn

model = nn.Linear(2, 1)
torch.save(model.state_dict(), 'best.pth')
new_model = nn.Linear(2, 1)
new_model.load_state_dict(torch.load('best.pth'))
print(new_model.weight.shape)

medium

A. torch.Size([1, 2])

B. torch.Size([2, 1])

C. torch.Size([1, 1])

D. Error: shape mismatch

Solution

1. Step 1: Understand model architecture

   nn.Linear(2,1) creates weights of shape [1, 2] (output features, input features).

2. Step 2: Loading weights into new model

   Loading saved weights into identical model keeps weight shape same.

3. Final Answer:

   torch.Size([1, 2]) -> Option A

4. Quick Check:

   Linear(2,1) weight shape = [1, 2] [OK]

Hint: Linear layer weights shape = (out_features, in_features) [OK]

Common Mistakes:

• Confusing input/output dimensions order
• Expecting error when loading identical model
• Misreading weight shape as (2,1)

4. What is wrong with this code snippet for saving the best model?

if val_loss < best_loss:
    best_loss = val_loss
    torch.save(model, 'best_model.pth')

medium

A. There is no condition to check validation loss.

B. It should save model.state_dict() instead of model.

C. It does not update best_loss correctly.

D. It saves the entire model, which is less flexible than saving state_dict.

Solution

1. Step 1: Analyze saving method

   Saving entire model works but is less flexible and may cause issues when loading on different devices or PyTorch versions.

2. Step 2: Compare with best practice

   Best practice is saving model.state_dict() for portability and smaller files.

3. Final Answer:

   It saves the entire model, which is less flexible than saving state_dict. -> Option D

4. Quick Check:

   Save state_dict() preferred over full model [OK]

Hint: Save state_dict() for flexibility, not full model [OK]

Common Mistakes:

• Saving full model without state_dict
• Ignoring portability issues
• Assuming full model save is always best

5. You want to save the best model during training based on validation accuracy. Which code snippet correctly implements this pattern?

best_acc = 0.0
for epoch in range(epochs):
    train()
    val_acc = validate()
    # Save best model here
    ???

hard

A. if val_acc < best_acc:
best_acc = val_acc
torch.save(model.state_dict(), 'best_model.pth')

B. if val_acc == best_acc:
torch.save(model.state_dict(), 'best_model.pth')

C. if val_acc > best_acc:
best_acc = val_acc
torch.save(model.state_dict(), 'best_model.pth')

D. torch.save(model.state_dict(), 'best_model.pth') # save every epoch

Solution

1. Step 1: Identify saving condition

   We save model only if validation accuracy improves (val_acc > best_acc).

2. Step 2: Update best accuracy and save weights

   Update best_acc and save model.state_dict() to keep best weights.

3. Final Answer:

   if val_acc > best_acc: best_acc = val_acc torch.save(model.state_dict(), 'best_model.pth') -> Option C

4. Quick Check:

   Save on val_acc improvement = B [OK]

Hint: Save model only if validation accuracy improves [OK]

Common Mistakes:

• Saving when accuracy decreases
• Saving every epoch wastes space
• Not updating best accuracy variable