Why TensorFlow is the industry deep learning framework - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import TensorFlow correctly.

TensorFlow

import [1] as tf

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

Atorch

Bkeras

Ctensorflow

Dnumpy

Attempts:

3 left

💡 Hint

Common Mistakes

Importing 'torch' instead of 'tensorflow'.

Using 'keras' directly without TensorFlow.

TensorFlow is imported using the name 'tensorflow'. This is the standard import for using TensorFlow in Python.

2fill in blank

medium

Complete the code to create a simple sequential model in TensorFlow.

TensorFlow

model = tf.keras.models.Sequential([tf.keras.layers.Dense([1], activation='relu')])

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

A10

B'relu'

CSequential

Dcompile

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the activation function name as the first argument.

Using 'compile' instead of number of units.

The Dense layer requires the number of units as an integer. Here, 10 units are specified.

3fill in blank

hard

Fix the error in compiling the model by filling the correct optimizer name.

TensorFlow

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

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

Atensorflow

Badam

Crelu

Dsoftmax

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'relu' or 'softmax' as optimizer.

Using 'tensorflow' as optimizer.

The optimizer name should be a valid TensorFlow optimizer string like 'adam'.

4fill in blank

hard

Fill both blanks to train the model with data and epochs.

TensorFlow

history = model.fit([1], [2], epochs=5)

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

Ax_train

By_train

Cx_test

Dy_test

Attempts:

3 left

💡 Hint

Common Mistakes

Using test data instead of training data for fitting.

Swapping inputs and labels.

The fit method requires training data inputs and labels, which are x_train and y_train respectively.

5fill in blank

hard

Fill all three blanks to evaluate the model and print accuracy.

TensorFlow

loss, [1] = model.evaluate([2], [3])
print(f'Accuracy: {accuracy:.2f}')

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

Aloss

Baccuracy

Cy_test

Dx_test

Attempts:

3 left

💡 Hint

Common Mistakes

Assigning loss twice.

Swapping test inputs and labels.

Printing variable not assigned.

The evaluate method returns loss and accuracy. The inputs are x_test and y_test. We assign accuracy to the second variable and print it.