Broadcasting in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to add a tensor and a scalar using broadcasting.

PyTorch

import torch

a = torch.tensor([1, 2, 3])
b = 5
result = a [1] b
print(result)

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

A/

B-

C*

D+

Attempts:

3 left

💡 Hint

Common Mistakes

Using subtraction or multiplication instead of addition.

Trying to add without an operator.

Adding a tensor and a scalar uses broadcasting, so + correctly adds 5 to each element.

2fill in blank

medium

Complete the code to multiply a 2D tensor by a 1D tensor using broadcasting.

PyTorch

import torch

a = torch.tensor([[1, 2, 3], [4, 5, 6]])
b = torch.tensor([1, 0, 1])
result = a [1] b
print(result)

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

A*

B+

C-

D/

Attempts:

3 left

💡 Hint

Common Mistakes

Using addition instead of multiplication.

Trying to multiply tensors with incompatible shapes without broadcasting.

Multiplying a 2D tensor by a 1D tensor broadcasts the 1D tensor across rows, so * is the correct operator.

3fill in blank

hard

Fix the error in the code by completing the broadcasting operation correctly.

PyTorch

import torch

a = torch.tensor([[1, 2, 3], [4, 5, 6]])
b = torch.tensor([1, 2])
result = a [1] b
print(result)

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

A+

B*

C-

D/

Attempts:

3 left

💡 Hint

Common Mistakes

Using multiplication which causes shape mismatch.

Trying to add tensors with incompatible shapes without broadcasting.

Adding a (2,3) tensor and a (2,) tensor broadcasts the smaller tensor across columns, so + works correctly.

4fill in blank

hard

Fill both blanks to create a tensor of shape (3, 4) by broadcasting a (3, 1) tensor with a (1, 4) tensor.

PyTorch

import torch

a = torch.tensor([[1], [2], [3]])  # shape (3, 1)
b = torch.tensor([[4, 5, 6, 7]])  # shape (1, 4)
result = a [1] b
print(result.shape)  # should print torch.Size([2])

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

A*

B+

C(3, 4)

D(4, 3)

Attempts:

3 left

💡 Hint

Common Mistakes

Using addition instead of multiplication.

Confusing the output shape dimensions.

Multiplying tensors with shapes (3,1) and (1,4) broadcasts to (3,4). The shape printed is (3, 4).

5fill in blank

hard

Fill all three blanks to create a dictionary comprehension that maps each word to its length if the length is greater than 3.

PyTorch

words = ['apple', 'bat', 'carrot', 'dog']
lengths = { [1]: [2] for word in words if len(word) [3] 3 }
print(lengths)

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

Aword

Blen(word)

C>

D<

Attempts:

3 left

💡 Hint

Common Mistakes

Using the wrong comparison operator.

Swapping key and value in the dictionary comprehension.

The dictionary comprehension maps each word to its len(word) only if the length is greater than 3.