Data augmentation importance in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the library used for image data augmentation in Keras.

Computer Vision

from tensorflow.keras.preprocessing.image import [1]

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

AImageTransformer

BImageAugmentor

CImageDataGenerator

DImageLoader

Attempts:

3 left

💡 Hint

Common Mistakes

Using a non-existent class like ImageAugmentor.

Confusing with image loading classes.

The ImageDataGenerator class in Keras is used to perform image data augmentation.

2fill in blank

medium

Complete the code to create an ImageDataGenerator that applies horizontal flips to images.

Computer Vision

datagen = ImageDataGenerator([1]=True)

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

Ahorizontal_flip

Bvertical_flip

Crotation_range

Dzoom_range

Attempts:

3 left

💡 Hint

Common Mistakes

Using vertical_flip instead of horizontal_flip.

Confusing with rotation or zoom parameters.

The horizontal_flip parameter enables random horizontal flipping of images during augmentation.

3fill in blank

hard

Fix the error in the code to correctly apply data augmentation to the training images.

Computer Vision

train_generator = datagen.flow_from_directory(
    'train_data',
    target_size=(150, 150),
    batch_size=32,
    class_mode=[1]
)

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

Anone

Bsparse

Cbinary

Dcategorical

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'binary' for multi-class problems.

Using 'none' which disables labels.

For multi-class classification, categorical is the correct class_mode to get one-hot encoded labels.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps image filenames to their augmented versions using the datagen.

Computer Vision

augmented_images = {img: datagen.[1](img) for img in images if img.[2]('.jpg')}

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

Aflow

Bendswith

Cstartswith

Dfit

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'fit' instead of 'flow' to generate images.

Using 'startswith' instead of 'endswith' for file extension check.

The flow method generates augmented images from input images, and endswith checks if the filename ends with '.jpg'.

5fill in blank

hard

Fill all three blanks to complete the code that applies rotation and zoom augmentation, then fits the generator to training images.

Computer Vision

datagen = ImageDataGenerator(
    rotation_range=[1],
    zoom_range=[2]
)
datagen.[3](train_images)

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

A20

B0.15

Cfit

Dflow

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'flow' instead of 'fit' to prepare the generator.

Confusing rotation_range with zoom_range values.

rotation_range=20 means images can rotate up to 20 degrees, zoom_range=0.15 means zooming up to 15%, and fit prepares the generator with the training images.