Padding and stride in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a 2D convolutional layer with stride 1.

TensorFlow

conv_layer = tf.keras.layers.Conv2D(filters=32, kernel_size=3, strides=[1], padding='same')

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

A1

B2

C3

D0

Attempts:

3 left

💡 Hint

Common Mistakes

Using stride 0 causes an error because stride must be positive.

Using stride 2 changes the output size and is not what the question asks.

The stride parameter controls how the filter moves over the input. A stride of 1 means the filter moves one pixel at a time.

2fill in blank

medium

Complete the code to apply 'valid' padding in a Conv2D layer.

TensorFlow

conv_layer = tf.keras.layers.Conv2D(filters=64, kernel_size=5, strides=1, padding=[1])

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

A'same'

B'zero'

C'valid'

D'full'

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'same' padding keeps output size but is not what the question asks.

Using 'full' or 'zero' are not valid padding options in TensorFlow Conv2D.

'valid' padding means no padding is added, so the output size shrinks depending on the kernel size.

3fill in blank

hard

Fix the error in the stride parameter to correctly create a Conv2D layer with stride 2.

TensorFlow

conv_layer = tf.keras.layers.Conv2D(filters=16, kernel_size=3, strides=[1], padding='same')

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

A2

B(2, 2)

C[2, 2]

D'2'

Attempts:

3 left

💡 Hint

Common Mistakes

Using a string '2' causes a type error.

Using [2, 2] also works but tuple (2, 2) is the expected answer.

In TensorFlow, strides can be an integer or a tuple. For 2D convolution, a tuple like (2, 2) is preferred to specify stride in height and width.

4fill in blank

hard

Fill both blanks to create a Conv2D layer with kernel size 3 and stride 2.

TensorFlow

conv_layer = tf.keras.layers.Conv2D(filters=10, kernel_size=[1], strides=[2], padding='valid')

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

A3

B(2, 2)

C2

D(3, 3)

Attempts:

3 left

💡 Hint

Common Mistakes

Using stride as 2 (int) works but tuple is preferred for clarity.

Using kernel size as (3, 3) is valid but question expects int 3.

The kernel size is 3 (can be int or tuple), and stride is (2, 2) to move two pixels in height and width.

5fill in blank

hard

Fill all three blanks to create a Conv2D layer with kernel size (5,5), stride 1, and 'same' padding.

TensorFlow

conv_layer = tf.keras.layers.Conv2D(filters=20, kernel_size=[1], strides=[2], padding=[3])

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

A(5, 5)

B1

C'same'

D'valid'

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'valid' padding shrinks output size.

Using stride other than 1 changes output size.

Kernel size is (5,5) for a 5x5 filter, stride 1 moves one pixel at a time, and 'same' padding keeps output size same as input.