Albumentations library in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the Albumentations library.

Computer Vision

import [1] as A

Drag options to blanks, or click blank then click option'

Anumpy

Bcv2

Calbumentations

Dtorch

Attempts:

3 left

💡 Hint

Common Mistakes

Importing 'cv2' instead of 'albumentations'.

Using 'torch' which is for deep learning, not augmentations.

The Albumentations library is imported using 'import albumentations as A'.

2fill in blank

medium

Complete the code to create a horizontal flip augmentation with a 50% chance.

Computer Vision

transform = A.[1](p=0.5)

Drag options to blanks, or click blank then click option'

AHorizontalFlip

BVerticalFlip

CRandomBrightnessContrast

DRotate

Attempts:

3 left

💡 Hint

Common Mistakes

Using VerticalFlip which flips images top to bottom.

Using Rotate which rotates images instead of flipping.

HorizontalFlip is the correct augmentation to flip images horizontally with probability p=0.5.

3fill in blank

hard

Fix the error in the code to apply a random brightness and contrast adjustment.

Computer Vision

transform = A.[1](brightness_limit=0.2, contrast_limit=0.2, p=0.5)

Drag options to blanks, or click blank then click option'

ABrightnessContrast

BRandomContrast

CRandomBrightness

DRandomBrightnessContrast

Attempts:

3 left

💡 Hint

Common Mistakes

Using RandomBrightness or RandomContrast alone which only adjust one property.

Using a non-existent class 'BrightnessContrast'.

RandomBrightnessContrast is the correct class to adjust brightness and contrast randomly.

4fill in blank

hard

Fill both blanks to create a Compose pipeline with horizontal flip and random rotate.

Computer Vision

transform = A.Compose([
    A.[1](p=0.5),
    A.[2](limit=40, p=0.7)
])

Drag options to blanks, or click blank then click option'

AHorizontalFlip

BVerticalFlip

CRotate

DRandomRotate90

Attempts:

3 left

💡 Hint

Common Mistakes

Using VerticalFlip instead of HorizontalFlip for horizontal flipping.

Using RandomRotate90 which rotates only by 90 degrees multiples.

HorizontalFlip and Rotate are used to flip images horizontally and rotate them randomly within a limit.

5fill in blank

hard

Fill all three blanks to create a Compose pipeline with normalization, horizontal flip, and random brightness/contrast.

Computer Vision

transform = A.Compose([
    A.[1](mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)),
    A.[2](p=0.5),
    A.[3](brightness_limit=0.2, contrast_limit=0.2, p=0.3)
])

Drag options to blanks, or click blank then click option'

ANormalize

BHorizontalFlip

CRandomBrightnessContrast

DResize

Attempts:

3 left

💡 Hint

Common Mistakes

Using Resize instead of Normalize for normalization.

Mixing up the order of augmentations.

Normalize standardizes image colors, HorizontalFlip flips images, and RandomBrightnessContrast adjusts brightness and contrast randomly.