Albumentations library in Computer Vision - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

What is the output shape after applying this Albumentations transform?

Given the following Albumentations pipeline applied to a 256x256 RGB image, what will be the shape of the output image?

Computer Vision

import albumentations as A
import numpy as np

transform = A.Compose([
    A.RandomCrop(width=224, height=224),
    A.HorizontalFlip(p=1.0),
])

image = np.zeros((256, 256, 3), dtype=np.uint8)
augmented = transform(image=image)
output = augmented['image'].shape

A (256, 256, 3)

B (224, 224)

C (224, 224, 3)

D (256, 256)

💡 Hint

RandomCrop changes the image size, HorizontalFlip does not change shape.

RandomCrop crops the image to 224x224 pixels, keeping 3 color channels. HorizontalFlip only flips horizontally without changing shape.

❓ Model Choice

intermediate

Which Albumentations transform is best to increase brightness randomly?

You want to randomly increase or decrease the brightness of images during training. Which Albumentations transform should you use?

A A.RandomBrightnessContrast(brightness_limit=0.2, contrast_limit=0, p=1.0)

B A.HorizontalFlip(p=1.0)

C A.RandomCrop(width=224, height=224)

D A.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225))

💡 Hint

Brightness changes pixel intensity, contrast changes difference between light and dark.

RandomBrightnessContrast with brightness_limit changes brightness randomly. Other options do not affect brightness.

❓ Hyperparameter

advanced

What is the effect of setting p=0.5 in an Albumentations transform?

In Albumentations, what does setting the parameter p=0.5 for a transform do during augmentation?

A The transform is applied twice to each image.

B The transform is applied to all images but with half intensity.

C The transform is applied only if the image size is greater than 50%.

D The transform is applied to 50% of the images randomly.

💡 Hint

p controls the probability of applying the transform.

p=0.5 means the transform is applied randomly to half of the images, otherwise skipped.

🔧 Debug

advanced

Why does this Albumentations pipeline raise an error?

Consider this Albumentations pipeline: transform = A.Compose([ A.RandomCrop(width=300, height=300), A.HorizontalFlip(p=0.5), ]) image = np.zeros((256, 256, 3), dtype=np.uint8) augmented = transform(image=image) Why does this code raise an error?

A RandomCrop size is larger than the input image size, causing an error.

B HorizontalFlip requires p=1.0 to work correctly.

C Compose requires at least three transforms.

D The image array must be float32, not uint8.

💡 Hint

RandomCrop cannot crop bigger than the image.

RandomCrop cannot crop a 300x300 area from a 256x256 image, so it raises an error.

🧠 Conceptual

expert

Which Albumentations transform is best for simulating motion blur in images?

You want to simulate motion blur effects on images to make your model robust to camera movement. Which Albumentations transform should you use?

A A.GaussianBlur(blur_limit=7, p=1.0)

B A.MotionBlur(blur_limit=7, p=1.0)

C A.RandomBrightnessContrast(p=1.0)

D A.HorizontalFlip(p=1.0)

💡 Hint

Motion blur simulates streaks caused by movement.

MotionBlur simulates directional blur caused by motion, unlike GaussianBlur which is uniform blur.