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.

Practice

1. What is the main purpose of the convolution operation in TensorFlow when processing images?

easy

A. To convert images into text

B. To randomly shuffle image pixels

C. To slide filters over the image to detect patterns

D. To increase the image size without change

Solution

1. Step 1: Understand convolution basics

   Convolution applies filters that slide over input data to find features like edges or shapes.

2. Step 2: Identify the purpose in image processing

   This operation helps models recognize patterns by scanning the image with filters.

3. Final Answer:

   To slide filters over the image to detect patterns -> Option C

4. Quick Check:

   Convolution = sliding filters to detect patterns [OK]

Hint: Convolution = sliding filters to find patterns [OK]

Common Mistakes:

• Thinking convolution shuffles pixels
• Confusing convolution with resizing
• Assuming convolution converts images to text

2. Which of the following is the correct TensorFlow syntax to create a 2D convolutional layer with 32 filters and a 3x3 kernel?

easy

A. tf.keras.layers.Conv2D(filters=3, kernel_size=(32,32))

B. tf.keras.layers.Dense(units=32, kernel_size=(3,3))

C. tf.keras.layers.Conv1D(filters=32, kernel_size=3)

D. tf.keras.layers.Conv2D(filters=32, kernel_size=(3,3))

Solution

1. Step 1: Identify correct layer type for 2D convolution

   Conv2D is used for 2D convolution layers, Dense is for fully connected layers, Conv1D is for 1D convolution.

2. Step 2: Check filter and kernel size parameters

   Filters=32 and kernel_size=(3,3) correctly specify 32 filters with 3x3 kernels.

3. Final Answer:

   tf.keras.layers.Conv2D(filters=32, kernel_size=(3,3)) -> Option D

4. Quick Check:

   Conv2D with filters=32 and kernel_size=(3,3) [OK]

Hint: Conv2D + filters + kernel_size for 2D conv layers [OK]

Common Mistakes:

• Using Dense layer instead of Conv2D
• Using Conv1D for 2D data
• Swapping filters and kernel sizes

3. Given this TensorFlow code snippet, what is the shape of the output tensor?

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

medium

A. (1, 26, 26, 16)

B. (1, 28, 28, 16)

C. (1, 25, 25, 16)

D. (1, 30, 30, 16)

Solution

1. Step 1: Understand input and convolution parameters

   Input shape is (1, 28, 28, 3). Kernel size is 3x3, stride 1, padding 'valid' means no padding.

2. Step 2: Calculate output spatial dimensions

   Output height and width = input size - kernel size + 1 = 28 - 3 + 1 = 26. Number of filters = 16.

3. Final Answer:

   (1, 26, 26, 16) -> Option A

4. Quick Check:

   Output size = 28-3+1 = 26 [OK]

Hint: Output size = input - kernel + 1 with 'valid' padding [OK]

Common Mistakes:

• Assuming padding='valid' keeps size same
• Confusing stride effect
• Forgetting number of filters changes channels

4. Identify the error in this TensorFlow convolution code and select the fix:

import tensorflow as tf
input_tensor = tf.random.normal([1, 28, 28, 3])
conv_layer = tf.keras.layers.Conv2D(filters=16, kernel_size=3, strides=2, padding='same')
output = conv_layer(input_tensor)
print(output.shape)

medium

A. Add activation='relu' to Conv2D to fix error

B. No error; code runs correctly

C. Change padding to 'valid' to fix shape error

D. Change strides to 1 to avoid shape mismatch

Solution

1. Step 1: Analyze convolution parameters

   Strides=2 and padding='same' are valid and supported in Conv2D.

2. Step 2: Check for errors in code execution

   This code runs without error and outputs a tensor with shape adjusted by stride and padding.

3. Final Answer:

   No error; code runs correctly -> Option B

4. Quick Check:

   Strides=2 with padding='same' is valid [OK]

Hint: Strides and padding='same' work together without error [OK]

Common Mistakes:

• Assuming stride 2 causes error
• Thinking padding='same' is invalid
• Believing activation needed to fix shape

5. You want to preserve the input image size after convolution in TensorFlow. Which combination of parameters achieves this for a 5x5 kernel?

hard

A. padding='same' and stride=1

B. padding='valid' and stride=1

C. padding='same' and stride=2

D. padding='valid' and stride=2

Solution

1. Step 1: Understand effect of padding and stride on output size

   Padding='same' adds zeros to keep output size equal to input when stride=1.

2. Step 2: Analyze kernel size and stride impact

   With kernel size 5 and stride 1, 'same' padding keeps size; 'valid' padding reduces size.

3. Final Answer:

   padding='same' and stride=1 -> Option A

4. Quick Check:

   Same padding + stride 1 preserves size [OK]

Hint: Use padding='same' and stride=1 to keep size [OK]

Common Mistakes:

• Using 'valid' padding expecting same size
• Using stride > 1 expecting same size
• Ignoring kernel size effect