Small dataset strategies in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load images from a directory using a common computer vision library.

Computer Vision

from tensorflow.keras.preprocessing.image import ImageDataGenerator

datagen = ImageDataGenerator(rescale=1./255)
data = datagen.flow_from_directory('[1]', target_size=(150, 150), batch_size=32, class_mode='binary')

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

Adataset/train

Bimages

Cdata

Dfolder

Attempts:

3 left

💡 Hint

Common Mistakes

Using a generic folder name that does not exist.

Not specifying the correct path to the image directory.

The directory path where training images are stored is usually specified. Here, 'dataset/train' is the correct folder path.

2fill in blank

medium

Complete the code to apply data augmentation to images to help with small datasets.

Computer Vision

datagen = ImageDataGenerator(rescale=1./255, rotation_range=[1], horizontal_flip=True)

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

A10

B180

C90

D40

Attempts:

3 left

💡 Hint

Common Mistakes

Using 90 or 180 degrees which may distort images too much.

Using too small rotation like 10 degrees which may not augment enough.

Rotation range of 40 degrees is a common augmentation to help models generalize better on small datasets.

3fill in blank

hard

Fix the error in the code to freeze the base model layers for transfer learning.

Computer Vision

base_model = tf.keras.applications.MobileNetV2(input_shape=(224, 224, 3), include_top=False, weights='imagenet')
for layer in base_model.[1]:
    layer.trainable = False

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

Alayer

Blayers

Ctrainable

Dtrain

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'layer' which is a single layer, not iterable.

Using 'trainable' or 'train' which are not iterable attributes.

The base model's layers are accessed via the 'layers' attribute to freeze them.

4fill in blank

hard

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

Computer Vision

augmented_images = {filename: next(datagen.[1](image[None], batch_size=1))[0] for filename, image in images.items() if image.shape [2] (224, 224, 3)}

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

Aflow

Bshape

C==

Dresize

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'resize' which is not a method of ImageDataGenerator.

Using 'shape' as a method instead of an attribute.

'flow' generates augmented images from the original image, and '==' checks if the image shape matches the target size.

5fill in blank

hard

Fill all three blanks to create a dictionary comprehension that filters images by size and applies augmentation.

Computer Vision

filtered_augmented = {filename: next(datagen.[1](image[None], batch_size=1))[0] for filename, image in images.items() if image.[2][0] [3] 224}

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

Aflow

Bshape

C>=

D<

Attempts:

3 left

💡 Hint

Common Mistakes

Using '<' instead of '>=' which filters out larger images.

Using 'resize' instead of 'flow' for augmentation.

'flow' generates augmented images, 'shape' accesses the image dimensions, and '>=' filters images with width at least 224 pixels.