Indexing and slicing in PyTorch - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output of slicing a 2D tensor

What is the output of the following PyTorch code snippet?

PyTorch

import torch
x = torch.tensor([[1, 2, 3], [4, 5, 6], [7, 8, 9]])
result = x[1:, :2]
print(result)

A tensor([[4, 5], [7, 8]])

B tensor([[5, 6], [8, 9]])

C tensor([[1, 2], [4, 5]])

D tensor([[2, 3], [5, 6]])

💡 Hint

Remember that x[1:, :2] means rows from index 1 to end, columns from index 0 up to but not including 2.

The slice x[1:, :2] selects rows starting from index 1 (second row) to the end, and columns from index 0 up to 2 (first two columns). So it picks rows [[4,5,6],[7,8,9]] and columns [0,1], resulting in [[4,5],[7,8]].

❓ Model Choice

intermediate

Choosing correct indexing for batch selection

You have a tensor `data` of shape (10, 3, 28, 28) representing 10 images with 3 color channels and 28x28 pixels. Which indexing expression correctly selects the first 5 images?

A data[5:]

B data[:5]

C data[:, :5]

D data[0:5, 1]

💡 Hint

The first dimension is the batch size (number of images).

The first dimension indexes images. data[:5] selects images from index 0 up to 5 (first 5 images). data[5:] selects images from index 5 to end. data[:, :5] selects all images but only first 5 channels (which is invalid since channels=3). data[0:5, 1] selects first 5 images but only channel 1, not the full image.

❓ Metrics

advanced

Effect of slicing on tensor shape

Given a tensor `t` of shape (8, 16, 32), what is the shape of `t[:, 4:10, 5:15]`?

A (8, 6, 10)

B (8, 6, 9)

C (8, 5, 10)

D (8, 7, 10)

💡 Hint

Subtract start index from end index for each sliced dimension.

For dimension 1: 4 to 10 means indices 4,5,6,7,8,9 → 6 elements. For dimension 2: 5 to 15 means indices 5 through 14 → 10 elements. The first dimension remains 8. So shape is (8, 6, 10).

🔧 Debug

advanced

Identify the error in tensor indexing

What error does the following PyTorch code raise?

PyTorch

import torch
t = torch.randn(4, 5)
result = t[1:3, 5]

A No error, returns a tensor

B TypeError: only integers, slices (`:`), ellipsis (`...`), None and long or byte Variables are valid indices

C ValueError: too many indices for tensor of dimension 2

D IndexError: index 5 is out of bounds for dimension 1 with size 5

💡 Hint

Check the size of dimension 1 and the index used.

The tensor t has shape (4,5), so valid indices for dimension 1 are 0 to 4. Index 5 is out of bounds, causing IndexError.

🧠 Conceptual

expert

Understanding advanced slicing with steps

Given a tensor `x` of shape (12,), what is the output of `x[10:2:-3]`?

PyTorch

import torch
x = torch.arange(12)
result = x[10:2:-3]
print(result)

A tensor([10, 7, 1])

B tensor([10, 8, 5])

C tensor([10, 7, 4])

D tensor([10, 7, 3])

💡 Hint

Remember slicing with negative step goes backward, start index included, stop index excluded.

x is [0,1,2,...,11]. Slicing x[10:2:-3] starts at index 10 (value 10), moves backward by 3 steps: indices 10,7,4. Values are 10,7,4.

Practice

1. What does the expression tensor[2] do in PyTorch when tensor is a 1D tensor?

easy

A. Selects every second element starting at index 2

B. Selects elements from index 0 to 2

C. Selects the element at index 2

D. Raises an error because indexing starts at 1

Solution

1. Step 1: Understand 1D tensor indexing

   In PyTorch, indexing a 1D tensor with [2] picks the element at position 2 (0-based index).

2. Step 2: Confirm indexing behavior

   Since indexing starts at 0, tensor[2] returns the third element.

3. Final Answer:

   Selects the element at index 2 -> Option C

4. Quick Check:

   Indexing with a single integer picks one element [OK]

Hint: Single index picks one element by position [OK]

Common Mistakes:

• Thinking indexing starts at 1
• Confusing slicing with indexing
• Expecting a range instead of one element

2. Which of the following is the correct syntax to slice a 1D tensor t to get elements from index 1 to 4 (excluding 4)?

easy

A. t(1:4)

B. t[1:4]

C. t[1-4]

D. t[1,4]

Solution

1. Step 1: Recall slicing syntax

   Slicing uses start:stop inside square brackets to select elements from start index up to but not including stop index.

2. Step 2: Check each option

   t[1:4] uses correct slicing syntax t[1:4]. Options A, B, and C use invalid syntax for slicing.

3. Final Answer:

   t[1:4] -> Option B

4. Quick Check:

   Slicing uses colon inside brackets [OK]

Hint: Use colon inside brackets for slicing [OK]

Common Mistakes:

• Using comma instead of colon for slicing
• Using parentheses instead of brackets
• Using minus sign instead of colon

3. Given the tensor t = torch.tensor([[1, 2, 3], [4, 5, 6], [7, 8, 9]]), what is the output of t[1:, :2]?

medium

A. [[5, 6], [8, 9]]

B. [[2, 3], [5, 6]]

C. [[1, 2], [4, 5]]

D. [[4, 5], [7, 8]]

Solution

1. Step 1: Understand slicing t[1:, :2]

   1: means rows from index 1 to end (rows 1 and 2). :2 means columns from start to index 2 (columns 0 and 1).

2. Step 2: Extract the sliced elements

   Rows 1 and 2 are [[4,5,6],[7,8,9]]. Taking columns 0 and 1 gives [[4,5],[7,8]].

3. Final Answer:

   [[4, 5], [7, 8]] -> Option D

4. Quick Check:

   Row slice 1: and col slice :2 gives [[4,5],[7,8]] [OK]

Hint: Rows after 1, columns before 2 slice tensor [OK]

Common Mistakes:

• Mixing row and column indices
• Including column index 2 mistakenly
• Confusing slicing ranges

4. What is wrong with this code snippet?

import torch
t = torch.tensor([1, 2, 3, 4, 5])
print(t[::2, 1])

medium

A. Trying to index 2D on a 1D tensor

B. Slicing syntax is incorrect

C. Tensor is not created properly

D. Print statement missing parentheses

Solution

1. Step 1: Analyze tensor shape

   The tensor t is 1D with shape (5,). It has only one dimension.

2. Step 2: Check indexing used

   The code uses t[::2, 1] which tries to index two dimensions (rows and columns). This causes an error because t is 1D.

3. Final Answer:

   Trying to index 2D on a 1D tensor -> Option A

4. Quick Check:

   1D tensor cannot be indexed with two indices [OK]

Hint: Match number of indices to tensor dimensions [OK]

Common Mistakes:

• Assuming 1D tensor can be indexed like 2D
• Confusing slicing syntax with indexing
• Ignoring tensor shape before indexing

5. You have a 3D tensor t with shape (4, 5, 6). Which indexing expression extracts all elements from the second dimension at index 3, across all batches and features?

hard

A. t[:, 3, :]

B. t[3, :, :]

C. t[:, :, 3]

D. t[3, 3, :]

Solution

1. Step 1: Understand tensor dimensions

   Tensor shape is (4, 5, 6): first dim = batches, second dim = 5 elements, third dim = 6 features.

2. Step 2: Select all batches, index 3 in second dim, all features

   Use : to select all in first and third dims, and 3 to select index 3 in second dim, so t[:, 3, :].

3. Final Answer:

   t[:, 3, :] -> Option A

4. Quick Check:

   Colon means all, index 3 picks second dim element [OK]

Hint: Use colon for all dims, index for specific dim [OK]

Common Mistakes:

• Mixing dimension order
• Using wrong index for dimension
• Using single index for multiple dims