Indexing and slicing in PyTorch - ML Experiment: Train & Evaluate

Experiment - Indexing and slicing

Problem:You have a 3D tensor representing a batch of images with shape (batch_size, height, width). You want to extract specific parts of the images using indexing and slicing.

Current Metrics:N/A (This is a data manipulation task, not a model training task.)

Issue:You are unsure how to correctly use PyTorch indexing and slicing to extract sub-tensors without errors.

Your Task

Extract the center 2x2 patch from each image in the batch using PyTorch indexing and slicing.

Do not use any loops; use only tensor indexing and slicing.

The input tensor shape is (4, 5, 5) representing 4 images of 5x5 pixels.

Hint 1

Hint 2

Hint 3

Solution

PyTorch

import torch

# Create a batch of 4 images, each 5x5 pixels
images = torch.arange(4*5*5).reshape(4, 5, 5)

# Extract the center 2x2 patch from each image
# Center indices for 5x5 are rows 1 and 2 (0-based), columns 1 and 2
center_patch = images[:, 1:3, 1:3]

print('Original images shape:', images.shape)
print('Center patches shape:', center_patch.shape)
print('Center patches tensor:')
print(center_patch)

Used slicing to select rows 1 to 2 and columns 1 to 2 for all images in the batch.

Used ':' to select all images in the batch dimension.

Reshaped the tensor to simulate a batch of images.

Results Interpretation

Before slicing, the tensor shape was (4, 5, 5), representing 4 images of size 5x5.

After slicing, the tensor shape is (4, 2, 2), representing the center 2x2 patch of each image.

Indexing and slicing in PyTorch allow you to efficiently extract specific parts of tensors without loops, which is essential for data preprocessing and model input preparation.

Bonus Experiment

Try extracting the bottom-right 3x3 patch from each image using indexing and slicing.

💡 Hint

Use negative indices or calculate the start index as height - 3 and width - 3 to slice the last 3 rows and columns.

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