Reshaping (view, reshape, squeeze, unsqueeze) in PyTorch - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

What is the shape of tensor after view operation?

Given the following PyTorch code, what will be the shape of tensor `b` after the `view` operation?

PyTorch

import torch
a = torch.randn(2, 3, 4)
b = a.view(3, 8)

A torch.Size([4, 6])

B torch.Size([6, 4])

C torch.Size([2, 12])

D torch.Size([3, 8])

💡 Hint

Remember that view reshapes the tensor without changing the total number of elements.

The original tensor has shape (2, 3, 4), total elements = 2*3*4 = 24. The view reshapes it to (3, 8), which also has 24 elements.

❓ Predict Output

intermediate

What is the output shape after squeeze operation?

What will be the shape of tensor `b` after applying `squeeze` on tensor `a`?

PyTorch

import torch
a = torch.randn(1, 5, 1, 3)
b = a.squeeze()

A torch.Size([5, 3])

B torch.Size([1, 5, 3])

C torch.Size([5, 1, 3])

D torch.Size([1, 5, 1, 3])

💡 Hint

Squeeze removes all dimensions of size 1.

The original shape is (1, 5, 1, 3). Squeeze removes dimensions with size 1, so the shape becomes (5, 3).

❓ Model Choice

advanced

Which operation correctly adds a new dimension at position 2?

You have a tensor `a` with shape (4, 5). Which PyTorch operation will add a new dimension at position 2 (0-based index), resulting in shape (4, 5, 1)?

PyTorch

import torch
a = torch.randn(4, 5)

A a.unsqueeze(1)

B a.unsqueeze(2)

C a.unsqueeze(0)

D a.unsqueeze(-2)

💡 Hint

Remember that unsqueeze adds a dimension at the specified index.

The tensor `a` has shape (4, 5). Adding a dimension at position 2 means after the second dimension, so shape becomes (4, 5, 1). `a.unsqueeze(2)` does this. `a.unsqueeze(-2)` inserts at position 1, giving (4, 1, 5).

❓ Hyperparameter

advanced

Choosing correct reshape parameters for a tensor

You have a tensor `a` with shape (2, 3, 4). You want to reshape it to a 2D tensor with 6 rows. Which of the following reshape calls achieves this without raising an error?

PyTorch

import torch
a = torch.randn(2, 3, 4)

A a.reshape(3, 8)

B a.reshape(4, 6)

C a.reshape(6, -1)

D a.reshape(6, 5)

💡 Hint

The total number of elements must remain the same after reshape. Use -1 to infer a dimension.

Tensor `a` has 24 elements. A: (3,8) has 6 rows? No. B: (6,-1) infers 4, (6,4)=24, good. C: (6,5)=30 mismatch, error. D: (4,6)=24 but 4 rows.

🔧 Debug

expert

Why does this reshape code raise an error?

Consider the following code snippet. Why does it raise an error?

PyTorch

import torch
a = torch.randn(2, 3, 4)
b = a.view(4, 3, 3)

A The total number of elements does not match between original and new shape.

B view cannot change the order of dimensions, only reshape.

C The new shape must have a dimension of size 1.

D view requires the tensor to be contiguous, and this tensor is not.

💡 Hint

Check the total number of elements in both shapes.

Original tensor has 2*3*4=24 elements. New shape (4,3,3) has 4*3*3=36 elements. Total number of elements does not match.