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.