Data augmentation as regularization in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to apply random horizontal flip to images for data augmentation.

TensorFlow

data_augmentation = tf.keras.Sequential([
    tf.keras.layers.RandomFlip([1])
])

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

A'horizontal_and_vertical'

B'horizontal'

C'vertical'

D'none'

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'vertical' flips images up and down, which is less common for some datasets.

The RandomFlip layer with 'horizontal' flips images left to right, which is a common augmentation.

2fill in blank

medium

Complete the code to add random rotation of 20% to the data augmentation pipeline.

TensorFlow

data_augmentation = tf.keras.Sequential([
    tf.keras.layers.RandomRotation([1])
])

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

A0.2

B20

C2

D0.02

Attempts:

3 left

💡 Hint

Common Mistakes

Using 20 instead of 0.2 causes an error because the value must be between 0 and 1.

The RandomRotation layer expects a float between 0 and 1 representing fraction of 2π radians. 0.2 means 20% rotation.

3fill in blank

hard

Fix the error in the code to correctly apply random zoom augmentation.

TensorFlow

data_augmentation = tf.keras.Sequential([
    tf.keras.layers.RandomZoom(height_factor=[1])
])

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

A-0.1

B10

C0.1

D'0.1'

Attempts:

3 left

💡 Hint

Common Mistakes

Using a string instead of a float causes a type error.

Negative values are invalid for zoom factor.

The height_factor must be a float between 0 and 1 representing zoom range. 0.1 means zoom in/out by 10%.

4fill in blank

hard

Fill both blanks to create a data augmentation pipeline with random flip and rotation.

TensorFlow

data_augmentation = tf.keras.Sequential([
    tf.keras.layers.RandomFlip([1]),
    tf.keras.layers.RandomRotation([2])
])

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

A'horizontal'

B0.3

C0.2

D'vertical'

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'vertical' flip instead of 'horizontal'.

Using 0.3 instead of 0.2 for rotation.

Use 'horizontal' for flipping and 0.2 for 20% rotation.

5fill in blank

hard

Fill all three blanks to build a data augmentation pipeline with flip, rotation, and zoom.

TensorFlow

data_augmentation = tf.keras.Sequential([
    tf.keras.layers.RandomFlip([1]),
    tf.keras.layers.RandomRotation([2]),
    tf.keras.layers.RandomZoom(height_factor=[3])
])

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

A'horizontal'

B0.1

C0.2

D'vertical'

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up zoom and rotation values.

Using 'vertical' flip instead of 'horizontal'.

The pipeline flips images horizontally, rotates by 20%, and zooms by 10%.