Albumentations library in Computer Vision - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is the Albumentations library used for in computer vision?

Albumentations is a Python library used to easily apply fast and flexible image augmentations to improve the diversity of training data in computer vision tasks.

beginner

Name three common image augmentations provided by Albumentations.

Common augmentations include flipping images horizontally or vertically, rotating images by some degrees, and changing brightness or contrast.

intermediate

How does Albumentations help improve machine learning model performance?

By creating varied versions of images through augmentation, Albumentations helps models learn to recognize objects under different conditions, reducing overfitting and improving generalization.

intermediate

What is the typical way to apply multiple augmentations using Albumentations?

You create a Compose object that chains multiple augmentations together, then apply it to images during training.

intermediate

Why is Albumentations preferred over some other augmentation libraries?

Albumentations is fast, easy to use, supports many augmentations, works well with bounding boxes and masks, and integrates smoothly with deep learning frameworks.

What does Albumentations primarily help with in computer vision?

A Image augmentation to increase training data variety

B Building neural network architectures

C Evaluating model accuracy

D Collecting image datasets

Albumentations is designed to apply image augmentations to increase data variety for training.

Which Albumentations function is used to combine multiple augmentations?

A Chain()

B Compose()

C Merge()

D Concat()

Compose() is used to chain multiple augmentations in Albumentations.

Which of these is NOT a typical augmentation in Albumentations?

A TrainTestSplit

B Rotate

C HorizontalFlip

D BrightnessContrast

TrainTestSplit is a data splitting method, not an augmentation.

Albumentations supports augmentations for which of these data types?

A Images only

B Audio data

C Text data

D Images and bounding boxes

Albumentations supports images and related annotations like bounding boxes and masks.

Why is image augmentation important in training computer vision models?

A To reduce dataset size

B To make models faster

C To increase data diversity and reduce overfitting

D To label images automatically

Augmentation increases data diversity, helping models generalize better and avoid overfitting.

Explain how Albumentations improves the training of computer vision models.

Think about how changing images helps models learn.

Describe the process of applying multiple augmentations using Albumentations.

How do you combine several changes to images in one step?

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