Why Keras simplifies model building in TensorFlow - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import Keras from TensorFlow.

TensorFlow

from tensorflow import [1]

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

Akeras

Bnumpy

Cpandas

Dmatplotlib

Attempts:

3 left

💡 Hint

Common Mistakes

Importing unrelated libraries like numpy or pandas instead of keras.

Trying to import keras separately without tensorflow.

Keras is a high-level API in TensorFlow used for building and training models easily.

2fill in blank

medium

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

TensorFlow

model = keras.models.[1]()

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

APipeline

BGraph

CModel

DSequential

Attempts:

3 left

💡 Hint

Common Mistakes

Using Model instead of Sequential for simple linear stacks.

Using non-existent classes like Graph or Pipeline.

The Sequential class in Keras allows you to build models layer by layer simply.

3fill in blank

hard

Fix the error in adding a dense layer with 10 units and ReLU activation.

TensorFlow

model.add(keras.layers.Dense([1], activation='relu'))

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

A'ten'

B10

Cunits=10

Dactivation='relu'

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the number of units as a string like 'ten'.

Trying to pass keyword arguments inside the first parameter.

The number of units must be an integer, not a string or keyword argument inside the first parameter.

4fill in blank

hard

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

TensorFlow

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

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

A'adam'

B'mse'

C'categorical_crossentropy'

D'binary_crossentropy'

Attempts:

3 left

💡 Hint

Common Mistakes

Using mean squared error (mse) loss for classification.

Using binary crossentropy for multi-class problems.

Adam optimizer is popular for training, and categorical crossentropy is used for multi-class classification.

5fill in blank

hard

Fill all three blanks to train the model on data X_train and y_train for 5 epochs with batch size 32.

TensorFlow

model.fit([1], [2], epochs=[3], batch_size=32)

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

AX_train

By_train

C5

D10

Attempts:

3 left

💡 Hint

Common Mistakes

Swapping input data and labels.

Using too many epochs without reason.

To train a model, pass the input data, labels, and specify epochs. Batch size controls how many samples per update.