Reshaping (view, reshape, squeeze, unsqueeze) in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to reshape a tensor of shape (4, 3) into (2, 6) using PyTorch.

PyTorch

import torch
x = torch.randn(4, 3)
y = x.[1](2, 6)
print(y.shape)

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

Aview

Breshape

Csqueeze

Dunsqueeze

Attempts:

3 left

💡 Hint

Common Mistakes

Using squeeze or unsqueeze which add or remove dimensions instead of reshaping.

Using reshape without understanding the difference with view.

The view method reshapes the tensor without copying data if possible. Here, view(2, 6) changes the shape from (4, 3) to (2, 6).

2fill in blank

medium

Complete the code to add a new dimension at position 1 to a tensor of shape (3, 4).

PyTorch

import torch
x = torch.randn(3, 4)
y = x.[1](1)
print(y.shape)

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

Aview

Bsqueeze

Cunsqueeze

Dreshape

Attempts:

3 left

💡 Hint

Common Mistakes

Using squeeze which removes dimensions instead of adding.

Using view or reshape which change shape but do not add singleton dimensions.

The unsqueeze method adds a dimension of size 1 at the specified position. Here, unsqueeze(1) changes shape from (3, 4) to (3, 1, 4).

3fill in blank

hard

Fix the error in the code to remove all dimensions of size 1 from the tensor.

PyTorch

import torch
x = torch.randn(1, 3, 1, 5)
y = x.[1]()
print(y.shape)

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

Areshape

Bsqueeze

Cview

Dunsqueeze

Attempts:

3 left

💡 Hint

Common Mistakes

Using unsqueeze which adds dimensions instead of removing.

Using view or reshape which do not remove singleton dimensions automatically.

The squeeze method removes all dimensions of size 1. Here, it changes shape from (1, 3, 1, 5) to (3, 5).

4fill in blank

hard

Fill both blanks to reshape a tensor and then add a new dimension at the end.

PyTorch

import torch
x = torch.randn(6, 4)
y = x.[1](3, 8).[2](-1)
print(y.shape)

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

Areshape

Bunsqueeze

Csqueeze

Dview

Attempts:

3 left

💡 Hint

Common Mistakes

Using squeeze instead of unsqueeze to add a dimension.

Using view instead of reshape which may fail if tensor is not contiguous.

First, reshape(3, 8) changes the shape from (6, 4) to (3, 8). Then, unsqueeze(-1) adds a new dimension at the end, resulting in shape (3, 8, 1).

5fill in blank

hard

Fill all three blanks to create a dictionary with keys as the tensor's dimension sizes and values as the dimension indices, but only for dimensions larger than 1.

PyTorch

import torch
x = torch.randn(1, 5, 1, 7)
result = {x.shape[[1]]: [2] for [3] in range(len(x.shape)) if x.shape[[1]] > 1}
print(result)

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

Ai

Dj

Attempts:

3 left

💡 Hint

Common Mistakes

Using different variables for indexing and looping causing errors.

Using a variable not defined in the loop.

We use i as the loop variable and index to access each dimension size. The dictionary comprehension maps dimension sizes greater than 1 to their indices.