Why CNNs understand visual patterns in TensorFlow - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the TensorFlow library.

TensorFlow

import [1] as tf

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

Atensorflow

Btorch

Cnumpy

Dsklearn

Attempts:

3 left

💡 Hint

Common Mistakes

Importing PyTorch or NumPy instead of TensorFlow.

TensorFlow is imported as tf to build and train CNN models.

2fill in blank

medium

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

TensorFlow

model = tf.keras.Sequential([
    tf.keras.layers.Conv2D([1], kernel_size=3, activation='relu', input_shape=(28, 28, 1))
])

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

A64

B32

C16

D128

Attempts:

3 left

💡 Hint

Common Mistakes

Using too few or too many filters like 16 or 128.

The convolutional layer uses 32 filters to detect visual patterns.

3fill in blank

hard

Fix the error in the code to compile the CNN model with Adam optimizer.

TensorFlow

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

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

Aadagrad

Bsgd

Crmsprop

Dadam

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'Adam' with uppercase A or other optimizers causing slower training.

Adam optimizer is commonly used for training CNNs efficiently.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps each image to its label if the label is 0.

TensorFlow

filtered_data = {img: label for img, label in dataset.items() if label [1] [2]

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

A==

B!=

C0

D1

Attempts:

3 left

💡 Hint

Common Mistakes

Using '!=' instead of '==' or wrong label number.

The comprehension keeps images where the label equals 0, filtering for a specific class.

5fill in blank

hard

Fill all three blanks to create a dictionary of image sizes for images with width greater than 28.

TensorFlow

image_sizes = {img: (width, height) for img, (width, height) in images.items() if width [1] [2] and height [3] 28}

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

A>

B28

C>=

D<

Attempts:

3 left

💡 Hint

Common Mistakes

Using '>=' instead of '>' or wrong comparison operators.

This filters images with width greater than 28 and height less than 28.