Batch size and shuffling in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a DataLoader with batch size 32.

PyTorch

loader = DataLoader(dataset, batch_size=[1])

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

A64

B32

C16

D128

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing a batch size too small or too large for the example.

Confusing batch size with dataset size.

The batch_size parameter controls how many samples are loaded per batch. Here, 32 is the correct batch size.

2fill in blank

medium

Complete the code to enable shuffling of data in the DataLoader.

PyTorch

loader = DataLoader(dataset, batch_size=32, shuffle=[1])

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

A0

BFalse

CNone

DTrue

Attempts:

3 left

💡 Hint

Common Mistakes

Setting shuffle to False or None, which disables shuffling.

Using 0 instead of a boolean value.

Setting shuffle=True makes the DataLoader shuffle the data at every epoch, which helps training.

3fill in blank

hard

Fix the error in the DataLoader creation by choosing the correct batch size type.

PyTorch

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

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

A'32'

BNone

C32

DTrue

Attempts:

3 left

💡 Hint

Common Mistakes

Using a string like '32' instead of integer 32.

Passing None or True as batch size.

batch_size must be an integer, not a string or other type.

4fill in blank

hard

Fill both blanks to create a DataLoader with batch size 64 and shuffling enabled.

PyTorch

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

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

A64

BTrue

CFalse

D32

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up batch size and shuffle values.

Using False for shuffle when shuffling is needed.

Batch size 64 and shuffle=True correctly configure the DataLoader for training.

5fill in blank

hard

Fill all three blanks to create a DataLoader with batch size 16, shuffling enabled, and drop_last set to True.

PyTorch

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

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

A16

BTrue

CFalse

D32

Attempts:

3 left

💡 Hint

Common Mistakes

Setting drop_last to False when dropping last batch is needed.

Using wrong types for parameters.

batch_size=16, shuffle=True, and drop_last=True ensure batches are shuffled and incomplete last batch is dropped.