Dropout layers in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to add a dropout layer with 0.3 dropout rate.

TensorFlow

model = tf.keras.Sequential([
    tf.keras.layers.Dense(64, activation='relu'),
    tf.keras.layers.Dropout([1]),
    tf.keras.layers.Dense(10, activation='softmax')
])

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

ANone

B3

C30

D0.3

Attempts:

3 left

💡 Hint

Common Mistakes

Using an integer instead of a decimal for dropout rate.

Setting dropout rate greater than 1 or less than 0.

The dropout rate should be a float between 0 and 1 representing the fraction of neurons to drop. Here, 0.3 means 30% of neurons are randomly dropped during training.

2fill in blank

medium

Complete the code to import the Dropout layer from TensorFlow Keras.

TensorFlow

from tensorflow.keras.layers import [1]

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

ADense

BDropout

CFlatten

DConv2D

Attempts:

3 left

💡 Hint

Common Mistakes

Importing Dense or other layers instead of Dropout.

Forgetting to import the Dropout layer.

To use dropout layers, you must import Dropout from tensorflow.keras.layers.

3fill in blank

hard

Fix the error in the dropout layer definition by completing the code.

TensorFlow

dropout_layer = tf.keras.layers.Dropout(rate=[1])

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

A0.5

B3

C-0.1

D1.5

Attempts:

3 left

💡 Hint

Common Mistakes

Using values greater than 1 or less than 0 for dropout rate.

Using integers instead of decimals.

The dropout rate must be between 0 and 1. 0.5 means 50% dropout, which is valid.

4fill in blank

hard

Fill both blanks to create a dropout layer with 0.4 rate and apply it to input tensor x.

TensorFlow

dropout = tf.keras.layers.[1](rate=[2])
x_dropped = dropout(x)

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

ADropout

BDense

C0.4

D0.8

Attempts:

3 left

💡 Hint

Common Mistakes

Using Dense instead of Dropout layer.

Using dropout rate greater than 1.

Use Dropout layer with rate 0.4 to drop 40% of neurons. Then apply it to input x.

5fill in blank

hard

Fill all three blanks to define a model with input layer, dropout with 0.25 rate, and output layer.

TensorFlow

model = tf.keras.Sequential([
    tf.keras.layers.InputLayer(input_shape=(784,)),
    tf.keras.layers.[1](128, activation='relu'),
    tf.keras.layers.Dropout(rate=[2]),
    tf.keras.layers.[3](10, activation='softmax')
])

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

ADense

B0.25

DDropout

Attempts:

3 left

💡 Hint

Common Mistakes

Using Dropout instead of Dense for hidden or output layers.

Setting dropout rate incorrectly.

The model has a Dense hidden layer, a Dropout layer with 0.25 rate, and a Dense output layer with 10 units.