Checkpoint with optimizer state in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to save the model checkpoint including the optimizer state.

PyTorch

torch.save({'model_state_dict': model.state_dict(), 'optimizer_state_dict': [1], 'checkpoint.pth')

Drag options to blanks, or click blank then click option'

Aoptimizer.state_dict()

Bmodel.state_dict()

Coptimizer.save()

Dmodel.save()

Attempts:

3 left

💡 Hint

Common Mistakes

Using model.state_dict() instead of optimizer.state_dict() for optimizer state

Calling save() method on optimizer which does not exist

To save the optimizer state, use optimizer.state_dict() inside the checkpoint dictionary.

2fill in blank

medium

Complete the code to load the optimizer state from the checkpoint.

PyTorch

checkpoint = torch.load('checkpoint.pth')
optimizer.[1](checkpoint['optimizer_state_dict'])

Drag options to blanks, or click blank then click option'

Astate_dict

Bload

Cload_optimizer

Dload_state_dict

Attempts:

3 left

💡 Hint

Common Mistakes

Using load() instead of load_state_dict()

Trying to assign the state dict directly without using the method

To restore the optimizer state, use optimizer.load_state_dict() with the saved state dictionary.

3fill in blank

hard

Fix the error in the code to correctly save the checkpoint with model and optimizer states.

PyTorch

torch.save({'model': model.state_dict(), 'optimizer': [1], 'checkpoint.pth')

Drag options to blanks, or click blank then click option'

Aoptimizer.state_dict()

Boptimizer.load_state_dict()

Coptimizer.save()

Dmodel.state_dict()

Attempts:

3 left

💡 Hint

Common Mistakes

Using load_state_dict() instead of state_dict() when saving

Calling save() on optimizer which is not a valid method

The checkpoint dictionary keys can be any string, but the value for optimizer must be optimizer.state_dict() to save its state.

4fill in blank

hard

Fill both blanks to correctly load the model and optimizer states from the checkpoint.

PyTorch

checkpoint = torch.load('checkpoint.pth')
model.[1](checkpoint['model'])
optimizer.[2](checkpoint['optimizer'])

Drag options to blanks, or click blank then click option'

Aload_state_dict

Bload

Cstate_dict

Dsave

Attempts:

3 left

💡 Hint

Common Mistakes

Using load() instead of load_state_dict()

Using state_dict property instead of method to load

Both model and optimizer use load_state_dict() to restore their saved states from the checkpoint.

5fill in blank

hard

Fill all three blanks to save a checkpoint with model state, optimizer state, and current epoch.

PyTorch

torch.save({'model_state_dict': model.[1](), 'optimizer_state_dict': optimizer.[2](), 'epoch': [3], 'checkpoint.pth')

Drag options to blanks, or click blank then click option'

Astate_dict

Bstate_dict()

Ccurrent_epoch

Depoch

Attempts:

3 left

💡 Hint

Common Mistakes

Using state_dict without parentheses which is a property, not a method call

Saving epoch as a string instead of a variable

Use state_dict() method to get model and optimizer states. The epoch number is saved as a variable, here named 'epoch'.