Num workers for parallel loading in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to set the number of workers for parallel data loading in PyTorch.

PyTorch

train_loader = DataLoader(dataset, batch_size=32, shuffle=True, num_workers=[1])

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

A0

B4

C-1

DNone

Attempts:

3 left

💡 Hint

Common Mistakes

Using negative numbers for num_workers causes errors.

Setting num_workers to None is invalid.

Setting num_workers=0 means data loading happens in the main process without parallel workers.

2fill in blank

medium

Complete the code to enable parallel data loading with 2 workers in PyTorch.

PyTorch

train_loader = DataLoader(dataset, batch_size=64, shuffle=True, num_workers=[1])

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

A0

B1

C8

D2

Attempts:

3 left

💡 Hint

Common Mistakes

Setting num_workers to 0 disables parallel loading.

Using too many workers can slow down the system.

Setting num_workers=2 uses two subprocesses to load data in parallel, speeding up training.

3fill in blank

hard

Fix the error in the code by choosing the correct num_workers value for DataLoader.

PyTorch

loader = DataLoader(dataset, batch_size=16, shuffle=False, num_workers=[1])

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

A0

BNone

C3

D-2

Attempts:

3 left

💡 Hint

Common Mistakes

Using negative numbers like -2 causes errors.

Passing None is not accepted.

Negative values other than zero are invalid for num_workers. Zero disables parallel loading safely.

4fill in blank

hard

Fill both blanks to create a DataLoader with batch size 128 and 6 parallel workers.

PyTorch

loader = DataLoader(dataset, batch_size=[1], shuffle=True, num_workers=[2])

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

A128

B64

C6

D4

Attempts:

3 left

💡 Hint

Common Mistakes

Confusing batch size with num_workers values.

Using too many workers causing slowdowns.

Batch size is set to 128 and num_workers to 6 for parallel loading.

5fill in blank

hard

Fill all three blanks to create a DataLoader with batch size 256, shuffle disabled, and 8 workers.

PyTorch

loader = DataLoader(dataset, batch_size=[1], shuffle=[2], num_workers=[3])

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

ATrue

BFalse

C8

D256

Attempts:

3 left

💡 Hint

Common Mistakes

Setting shuffle to True when it should be False.

Using invalid types for batch size or num_workers.

Batch size is 256, shuffle is False to disable shuffling, and num_workers is 8 for parallel loading.