Convolution operation concept in TensorFlow - ML Experiment: Train & Evaluate

Experiment - Convolution operation concept

Problem:You want to understand how a convolution operation works in a simple neural network layer using TensorFlow. Currently, you have a model that applies a convolution but you don't see how the output changes with different filters.

Current Metrics:No training metrics yet, just initial output shape and values from a convolution layer with one filter.

Issue:The model uses only one filter and the output is not very informative. You want to experiment with multiple filters and see how the convolution operation extracts different features.

Your Task

Modify the convolution layer to use multiple filters and observe how the output changes. Understand how the convolution operation transforms the input image.

Use TensorFlow and Keras layers only.

Keep the input shape fixed as (28, 28, 1) to simulate a grayscale image.

Do not add training or complex model layers; focus on convolution operation only.

Hint 1

Hint 2

Hint 3

Solution

TensorFlow

import tensorflow as tf
import numpy as np

# Create a dummy grayscale image of shape (1, 28, 28, 1)
input_image = np.random.rand(1, 28, 28, 1).astype(np.float32)

# Define a Conv2D layer with 3 filters and kernel size 3x3
conv_layer = tf.keras.layers.Conv2D(filters=3, kernel_size=(3,3), padding='same', activation='relu')

# Apply convolution
output = conv_layer(input_image)

# Print input and output shapes
print(f'Input shape: {input_image.shape}')
print(f'Output shape: {output.shape}')

# Print output values for the first filter at the first 5x5 region
print('Output values for filter 0, top-left 5x5 region:')
print(output[0, :5, :5, 0].numpy())

Increased the number of filters from 1 to 3 to see multiple feature maps.

Used kernel size (3,3) with 'same' padding to keep output size equal to input size.

Added ReLU activation to observe non-linear feature extraction.

Printed output shape and sample values to understand convolution effect.

Results Interpretation

Before: Output shape was (1, 28, 28, 1) with only one filter, showing a single feature map.

After: Output shape is (1, 28, 28, 3) with three filters, showing three different feature maps extracted by the convolution operation.

Increasing the number of filters in a convolution layer allows the model to extract multiple features from the input image, each filter detecting different patterns or edges.

Bonus Experiment

Try changing the kernel size to (5,5) and observe how the output changes.

💡 Hint

Larger kernels capture bigger patterns but may reduce spatial resolution; compare output shapes and values.

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