Sequential model API in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a simple sequential model with one dense layer.

TensorFlow

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense

model = Sequential()
model.add(Dense([1], input_shape=(10,), activation='relu'))

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

ASequential

B32

C10

D'relu'

Attempts:

3 left

💡 Hint

Common Mistakes

Using the activation function name instead of number of units.

Passing the input shape as the first argument instead of units.

The first Dense layer needs the number of units as an integer. Here, 32 units is a common choice.

2fill in blank

medium

Complete the code to compile the model with mean squared error loss.

TensorFlow

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

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

Amean_squared_error

Bcategorical_crossentropy

Caccuracy

Dadam

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'accuracy' as loss instead of a loss function.

Using 'adam' as loss instead of optimizer.

For regression tasks, mean squared error is a common loss function.

3fill in blank

hard

Fix the error in the code to add a dropout layer after the first dense layer.

TensorFlow

from tensorflow.keras.layers import Dropout

model = Sequential()
model.add(Dense(64, input_shape=(20,), activation='relu'))
model.add([1](0.5))

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

ADropout

BDense

CActivation

DFlatten

Attempts:

3 left

💡 Hint

Common Mistakes

Using Dense instead of Dropout for dropout layer.

Forgetting to import Dropout layer.

Dropout layer is added by calling Dropout with the dropout rate.

4fill in blank

hard

Fill both blanks to create a sequential model with two dense layers and compile it with Adam optimizer and categorical crossentropy loss.

TensorFlow

model = Sequential()
model.add(Dense([1], activation='relu', input_shape=(15,)))
model.add(Dense([2], activation='softmax'))
model.compile(optimizer='[3]', loss='categorical_crossentropy')

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

A64

B10

C32

Dadam

Attempts:

3 left

💡 Hint

Common Mistakes

Using wrong number of units in output layer.

Using wrong optimizer name.

The first dense layer has 64 units with relu activation. The second dense layer has 10 units for 10 classes with softmax activation. Adam optimizer is used for compiling.

5fill in blank

hard

Fill all three blanks to create a sequential model with input shape, two dense layers, and compile it with RMSprop optimizer and binary crossentropy loss.

TensorFlow

model = Sequential()
model.add(Dense([1], activation='relu', input_shape=([2],)))
model.add(Dense([3], activation='sigmoid'))
model.compile(optimizer='rmsprop', loss='binary_crossentropy')

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

A128

B20

C1

D64

Attempts:

3 left

💡 Hint

Common Mistakes

Using more than 1 unit in output layer for binary classification.

Wrong input shape format.

The first dense layer has 128 units with relu activation and input shape of 20 features. The output layer has 1 unit with sigmoid activation for binary classification.