Convolution operation concept in TensorFlow - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

What does a convolution operation do in a CNN?

Imagine you have a photo and you want to find edges or patterns in it. What does the convolution operation do in this context?

A It randomly changes pixel values to create new images.

B It multiplies the image by a filter to highlight specific features like edges or textures.

C It compresses the image into a smaller size without losing any information.

D It converts the image into text data for easier processing.

💡 Hint

Think about how a filter moves over an image to detect patterns.

The convolution operation applies a small filter (kernel) over the image to multiply and sum pixel values, highlighting features like edges or textures.

❓ Predict Output

intermediate

Output shape after convolution

Given a 28x28 grayscale image input and a convolutional layer with 16 filters, kernel size 3x3, stride 1, and 'valid' padding, what is the output shape?

TensorFlow

import tensorflow as tf
input_tensor = tf.random.uniform([1, 28, 28, 1])
conv_layer = tf.keras.layers.Conv2D(filters=16, kernel_size=3, strides=1, padding='valid')
output = conv_layer(input_tensor)
print(output.shape)

A (1, 27, 27, 16)

B (1, 28, 28, 16)

C (1, 25, 25, 16)

D (1, 26, 26, 16)

💡 Hint

Use the formula: output_size = input_size - kernel_size + 1 when padding is 'valid'.

With 'valid' padding, output height and width = 28 - 3 + 1 = 26. Number of filters = 16, batch size = 1.

❓ Hyperparameter

advanced

Effect of stride on convolution output size

If you increase the stride from 1 to 2 in a convolutional layer, what happens to the output feature map size?

A The output size becomes smaller because the filter moves more pixels at a time.

B The output size becomes unpredictable and random.

C The output size stays the same because stride does not affect size.

D The output size becomes larger because the filter covers more area.

💡 Hint

Think about how skipping pixels affects the number of positions the filter can be applied.

Increasing stride means the filter jumps more pixels, reducing the number of positions and thus output size.

❓ Metrics

advanced

Calculating number of parameters in a Conv2D layer

How many trainable parameters are there in a Conv2D layer with 32 filters, kernel size 3x3, and input channels 3?

A 864

B 288

C 896

D 320

💡 Hint

Use the formula: (kernel_height * kernel_width * input_channels + 1) * number_of_filters.

Each filter has 3*3*3=27 weights plus 1 bias. Total parameters = (27+1)*32 = 896.

🔧 Debug

expert

Why does this convolution code raise an error?

Consider this TensorFlow code snippet:

import tensorflow as tf
input_tensor = tf.random.uniform([1, 28, 28, 1])
conv_layer = tf.keras.layers.Conv2D(filters=16, kernel_size=3, strides=1, padding='same')
output = conv_layer(input_tensor[0])
print(output.shape)

Why does this code raise an error?

A Because input_tensor[0] removes the batch dimension, causing shape mismatch.

B Because kernel_size must be an odd number greater than 3.

C Because padding='same' is not supported in Conv2D.

D Because filters must be equal to input channels.

💡 Hint

Check the shape of input_tensor[0] compared to what Conv2D expects.

Conv2D expects a 4D tensor with batch size. input_tensor[0] removes batch dimension, making it 3D, causing an error.