Albumentations library in Computer Vision

Introduction

Albumentations helps you easily change images to make your AI models better at understanding different pictures.

When you want to teach a model to recognize objects in photos taken in different lighting.

When you have few images and want to create more by changing them slightly.

When you want to make your model strong against small changes like rotation or color shifts.

When you need to prepare images for training by resizing or cropping.

When you want to add random effects like blur or noise to make your model more robust.

Syntax

Computer Vision

import albumentations as A

transform = A.Compose([
    A.HorizontalFlip(p=0.5),
    A.RandomBrightnessContrast(p=0.2),
    A.Rotate(limit=40, p=0.5),
])

augmented = transform(image=image)
augmented_image = augmented['image']

Use A.Compose to combine many image changes together.

Each change has a probability p to decide if it happens or not.

Examples

This will flip the image upside down sometimes and always crop a 256x256 part.

Computer Vision

transform = A.Compose([
    A.VerticalFlip(p=0.3),
    A.RandomCrop(width=256, height=256, p=1.0),
])

This adds blur or changes colors randomly to make images look different.

Computer Vision

transform = A.Compose([
    A.Blur(blur_limit=3, p=0.4),
    A.HueSaturationValue(p=0.5),
])

Sample Model

This code loads a sample image, applies flipping, brightness/contrast change, and rotation, then shows both images. It prints a message when done.

Computer Vision

import albumentations as A
import cv2

# Load an example image
image = cv2.imread(cv2.samples.findFile('lena.jpg'))

# Define transformations
transform = A.Compose([
    A.HorizontalFlip(p=1.0),
    A.RandomBrightnessContrast(p=1.0),
    A.Rotate(limit=30, p=1.0),
])

# Apply transformations
augmented = transform(image=image)
augmented_image = augmented['image']

# Show original and augmented images
cv2.imshow('Original', image)
cv2.imshow('Augmented', augmented_image)
cv2.waitKey(0)
cv2.destroyAllWindows()

# Print confirmation
print('Transformation applied successfully')

Important Notes

Albumentations works with images as numpy arrays, usually loaded by OpenCV.

Always check the probability p to control how often a change happens.

You can combine many transformations to make your dataset more varied.

Summary

Albumentations makes image changes easy and fast for training AI models.

Use Compose to group multiple changes with set chances.

Transforms help models learn better by seeing many versions of images.

Practice

1. What is the main purpose of the Albumentations library in computer vision?

easy

A. To apply image transformations that help AI models learn better

B. To train deep learning models directly

C. To label images for datasets

D. To evaluate model accuracy

Solution

1. Step 1: Understand Albumentations role

   Albumentations is designed to change images by applying transformations like flips, crops, or color changes.

2. Step 2: Connect transformations to model training

   These changes create many versions of images, helping AI models learn better by seeing varied data.

3. Final Answer:

   To apply image transformations that help AI models learn better -> Option A

4. Quick Check:

   Albumentations = Image transformations for training [OK]

Hint: Albumentations = image changes to improve training [OK]

Common Mistakes:

• Thinking Albumentations trains models directly
• Confusing it with labeling tools
• Assuming it measures accuracy

2. Which of the following is the correct way to import the Compose function from Albumentations?

easy

A. from albumentations import Compose

B. import albumentations.Compose

C. from albumentations.Compose import *

D. import Compose from albumentations

Solution

1. Step 1: Recall Python import syntax

   To import a function from a module, use 'from module import function'.

2. Step 2: Match with Albumentations usage

   Albumentations provides Compose as a function inside the albumentations module, so 'from albumentations import Compose' is correct.

3. Final Answer:

   from albumentations import Compose -> Option A

4. Quick Check:

   Correct import syntax = from albumentations import Compose [OK]

Hint: Use 'from module import function' for imports [OK]

Common Mistakes:

• Using dot notation in import incorrectly
• Trying to import with 'import Compose from ...'
• Using wildcard import from Compose

3. What will be the output shape of the image after applying this Albumentations transform?

import albumentations as A
transform = A.Compose([A.Resize(128, 128)])
augmented = transform(image=image)
result = augmented['image'].shape

medium

A. (256, 256, 3)

B. (128, 128)

C. (3, 128, 128)

D. (128, 128, 3)

Solution

1. Step 1: Understand Resize transform

   The Resize transform changes the image size to the given height and width, here 128x128 pixels.

2. Step 2: Check image shape format

   Albumentations uses height, width, and channels format (H, W, C). Assuming input image has 3 color channels, output shape is (128, 128, 3).

3. Final Answer:

   (128, 128, 3) -> Option D

4. Quick Check:

   Resize to 128x128 with 3 channels = (128,128,3) [OK]

Hint: Resize sets height and width; channels stay same [OK]

Common Mistakes:

• Confusing channel order with PyTorch (C,H,W)
• Ignoring color channels in output shape
• Assuming Resize doubles size

4. Identify the error in this Albumentations code snippet:

import albumentations as A
transform = A.Compose([
    A.HorizontalFlip(p=0.5),
    A.RandomBrightnessContrast(p=1.2)
])
augmented = transform(image=image)

medium

A. Compose cannot take a list of transforms

B. HorizontalFlip does not accept probability parameter

C. Probability p=1.2 is invalid; must be between 0 and 1

D. Missing import for RandomBrightnessContrast

Solution

1. Step 1: Check probability parameters

   Albumentations expects probability values (p) between 0 and 1 for transforms.

2. Step 2: Identify invalid p value

   RandomBrightnessContrast has p=1.2, which is invalid and will cause an error.

3. Final Answer:

   Probability p=1.2 is invalid; must be between 0 and 1 -> Option C

4. Quick Check:

   Probability p must be ≤ 1 [OK]

Hint: Probabilities must be between 0 and 1 [OK]

Common Mistakes:

• Setting p > 1 by mistake
• Thinking HorizontalFlip lacks p parameter
• Assuming Compose needs special import

5. You want to create a training pipeline that randomly flips images horizontally 50% of the time and then applies either a random brightness or contrast change (but not both) with equal chance. Which Albumentations Compose setup achieves this?

hard

A. A.Compose([A.OneOf([A.HorizontalFlip(p=0.5), A.RandomBrightness(p=1), A.RandomContrast(p=1)], p=1)])

B. A.Compose([A.HorizontalFlip(p=0.5), A.OneOf([A.RandomBrightness(p=1), A.RandomContrast(p=1)], p=1)])

C. A.Compose([A.HorizontalFlip(p=0.5), A.RandomBrightness(p=0.5), A.RandomContrast(p=0.5)])

D. A.Compose([A.HorizontalFlip(p=1), A.RandomBrightness(p=0.5), A.RandomContrast(p=0.5)])

Solution

1. Step 1: Understand HorizontalFlip probability

   We want horizontal flip with 50% chance, so use A.HorizontalFlip(p=0.5).

2. Step 2: Apply either brightness or contrast randomly

   Use A.OneOf with two transforms inside, each with p=1, and OneOf's p=1 to ensure exactly one is applied.

3. Step 3: Check options

   A.Compose([A.HorizontalFlip(p=0.5), A.OneOf([A.RandomBrightness(p=1), A.RandomContrast(p=1)], p=1)]) matches this logic exactly. Others either apply both brightness and contrast or misuse probabilities.

4. Final Answer:

   A.Compose([A.HorizontalFlip(p=0.5), A.OneOf([A.RandomBrightness(p=1), A.RandomContrast(p=1)], p=1)]) -> Option B

5. Quick Check:

   Use OneOf for exclusive choice [OK]

Hint: Use OneOf to pick one transform randomly [OK]

Common Mistakes:

• Applying brightness and contrast together
• Setting wrong probabilities in OneOf
• Using OneOf to include HorizontalFlip