Why CNNs dominate image classification in Computer Vision - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the main CNN layer used for image classification.

Computer Vision

from tensorflow.keras.layers import [1]

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

AConv2D

BDropout

CLSTM

DDense

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing Dense instead of Conv2D because Dense is for fully connected layers.

Selecting LSTM which is for sequence data, not images.

The Conv2D layer is the core building block of CNNs for image data.

2fill in blank

medium

Complete the code to add a convolutional layer with 32 filters and a 3x3 kernel.

Computer Vision

model.add(Conv2D([1], kernel_size=(3, 3), activation='relu'))

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

A128

B32

C64

D16

Attempts:

3 left

💡 Hint

Common Mistakes

Using 16 filters which might be too few for good feature extraction.

Choosing 128 filters which is usually for deeper layers.

32 filters is a common choice for the first convolutional layer.

3fill in blank

hard

Fix the error in the code to correctly flatten the output before the dense layer.

Computer Vision

model.add([1]())

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

AMaxPooling2D

BConv2D

CFlatten

DDropout

Attempts:

3 left

💡 Hint

Common Mistakes

Using Conv2D again which expects 2D input.

Using MaxPooling2D which reduces spatial size but does not flatten.

Flatten converts the 2D feature maps into a 1D vector for the dense layer.

4fill in blank

hard

Fill both blanks to compile the CNN model with Adam optimizer and categorical crossentropy loss.

Computer Vision

model.compile(optimizer=[1], loss=[2], metrics=['accuracy'])

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

A'adam'

B'sgd'

C'categorical_crossentropy'

D'mean_squared_error'

Attempts:

3 left

💡 Hint

Common Mistakes

Using SGD optimizer which can work but is less common for beginners.

Using mean squared error loss which is for regression, not classification.

Adam optimizer and categorical crossentropy loss are standard for multi-class image classification.

5fill in blank

hard

Fill all three blanks to create a dictionary comprehension that maps image labels to their counts if count is greater than 10.

Computer Vision

label_counts = { [1]: [2] for [3] in labels if labels[[3]] > 10 }

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

Alabel

Blabels[label]

Dcount

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'count' as loop variable which is undefined.

Swapping keys and values in the dictionary comprehension.

This comprehension creates a dictionary with labels as keys and their counts as values, filtering counts greater than 10.