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.

Practice

1. What does the torch.squeeze() function do to a tensor?

easy

A. Adds a new dimension of size 1 at a specified position

B. Removes all dimensions of size 1 from the tensor

C. Changes the tensor's data without changing its shape

D. Flattens the tensor into a 1D vector

Solution

1. Step 1: Understand the purpose of squeeze

   torch.squeeze() removes dimensions that have size 1, effectively reducing unnecessary dimensions.

2. Step 2: Differentiate from other reshape functions

   Unlike unsqueeze which adds size 1 dims, squeeze removes them without changing data.

3. Final Answer:

   Removes all dimensions of size 1 from the tensor -> Option B

4. Quick Check:

   squeeze removes size 1 dims = B [OK]

Hint: Squeeze removes dims with size 1, like cleaning empty boxes [OK]

Common Mistakes:

• Confusing squeeze with unsqueeze
• Thinking squeeze changes data values
• Assuming squeeze flattens the tensor

2. Which of the following is the correct syntax to add a new dimension at position 0 using PyTorch?

easy

A. tensor.unsqueeze(0)

B. tensor.unsqueeze(1)

C. tensor.squeeze(0)

D. tensor.reshape(0)

Solution

1. Step 1: Recall unsqueeze syntax

   unsqueeze(dim) adds a dimension of size 1 at the specified dim index.

2. Step 2: Identify correct dimension index

   To add at position 0 (the front), use unsqueeze(0). tensor.unsqueeze(1) adds at position 1, C squeezes, D is invalid.

3. Final Answer:

   tensor.unsqueeze(0) -> Option A

4. Quick Check:

   unsqueeze(0) adds dim at front = A [OK]

Hint: unsqueeze(dim) adds size 1 dim at dim index [OK]

Common Mistakes:

• Using squeeze instead of unsqueeze
• Passing wrong dimension index
• Using reshape with a single integer argument

3. Given the tensor t = torch.randn(2, 1, 3), what is the shape after t.view(2, 3)?

medium

A. (2, 3)

B. (2, 1, 3)

C. (1, 6)

D. RuntimeError due to incompatible shape

Solution

1. Step 1: Understand original tensor shape

   Tensor t has shape (2, 1, 3), total elements = 2*1*3 = 6.

2. Step 2: Check if view(2, 3) is compatible

   New shape (2, 3) also has 6 elements, so view can reshape without error.

3. Final Answer:

   (2, 3) -> Option A

4. Quick Check:

   view reshapes without changing total elements = A [OK]

Hint: view reshapes if total elements match exactly [OK]

Common Mistakes:

• Confusing view with squeeze or unsqueeze
• Assuming view changes data order
• Trying incompatible shapes causing runtime error

4. What is wrong with this code snippet?

import torch
t = torch.randn(3, 1, 4)
t = t.view(3, 3, 1, 1)

medium

A. The new shape has more elements than original tensor

B. view cannot add new dimensions, only reshape existing ones

C. view requires contiguous tensor, but t is not contiguous

D. The new shape is incompatible with the total number of elements

Solution

1. Step 1: Calculate original tensor elements

   Original shape (3,1,4) has 3*1*4 = 12 elements.

2. Step 2: Calculate new shape elements

   New shape (3,3,1,1) has 3*3*1*1 = 9 elements, which does not match.

3. Final Answer:

   The new shape is incompatible with the total number of elements -> Option D

4. Quick Check:

   view fails if total elements don't match = C [OK]

Hint: Check total elements before view; must match exactly [OK]

Common Mistakes:

• Assuming view cannot add dimensions
• Confusing contiguous memory errors
• Miscounting total elements

5. You have a tensor x of shape (4, 1, 28, 28). You want to prepare it for a fully connected layer that expects input shape (4, 784). Which sequence of PyTorch operations correctly reshapes x without changing data order?

hard

A. x = x.view(4, 28, 28)

B. x = x.unsqueeze(1).view(4, 1, 784)

C. x = x.squeeze(1).view(4, 784)

D. x = x.reshape(4, 1, 784)

Solution

1. Step 1: Understand original tensor shape

   x has shape (4, 1, 28, 28). The middle dimension is size 1, which is unnecessary for flattening.

2. Step 2: Remove the size 1 dimension

   Use squeeze(1) to remove the dimension of size 1 at index 1, resulting in shape (4, 28, 28).

3. Step 3: Flatten the last two dimensions

   Use view(4, 784) to reshape (4, 28, 28) into (4, 784) without changing data order.

4. Final Answer:

   x = x.squeeze(1).view(4, 784) -> Option C

5. Quick Check:

   Remove size 1 dim then flatten = D [OK]

Hint: Squeeze first to remove size 1 dims, then view to flatten [OK]

Common Mistakes:

• Trying to view directly without squeezing
• Using unsqueeze unnecessarily
• Confusing reshape and view effects