CNN architecture for image classification in TensorFlow

Introduction

A CNN helps a computer learn to recognize pictures by looking at small parts step-by-step.

When you want a computer to tell if a photo has a cat or a dog.

When sorting pictures into groups like cars, trees, or people.

When building apps that read handwritten numbers or letters.

When you want to find objects in photos automatically.

When improving photo search by understanding image content.

Syntax

TensorFlow

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense

model = Sequential([
    Conv2D(filters=32, kernel_size=(3,3), activation='relu', input_shape=(height, width, channels)),
    MaxPooling2D(pool_size=(2,2)),
    Conv2D(filters=64, kernel_size=(3,3), activation='relu'),
    MaxPooling2D(pool_size=(2,2)),
    Flatten(),
    Dense(units=128, activation='relu'),
    Dense(units=num_classes, activation='softmax')
])

Conv2D finds patterns like edges in small image parts.

MaxPooling2D shrinks the image to keep important info and reduce size.

Examples

This layer looks for 16 patterns using 5x5 squares on 28x28 grayscale images.

TensorFlow

Conv2D(filters=16, kernel_size=(5,5), activation='relu', input_shape=(28,28,1))

This layer reduces the image size by taking the biggest value in each 3x3 block.

TensorFlow

MaxPooling2D(pool_size=(3,3))

This layer outputs probabilities for 10 classes, like digits 0-9.

TensorFlow

Dense(units=10, activation='softmax')

Sample Model

This program trains a simple CNN on handwritten digit images and shows how well it learned.

TensorFlow

import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense

# Load example data: MNIST handwritten digits
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()

# Normalize images to 0-1 and add channel dimension
x_train = x_train.astype('float32') / 255.0
x_test = x_test.astype('float32') / 255.0
x_train = x_train[..., tf.newaxis]
x_test = x_test[..., tf.newaxis]

num_classes = 10

# Build CNN model
model = Sequential([
    Conv2D(32, (3,3), activation='relu', input_shape=(28,28,1)),
    MaxPooling2D((2,2)),
    Conv2D(64, (3,3), activation='relu'),
    MaxPooling2D((2,2)),
    Flatten(),
    Dense(128, activation='relu'),
    Dense(num_classes, activation='softmax')
])

# Compile model
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])

# Train model for 1 epoch (for quick demo)
history = model.fit(x_train, y_train, epochs=1, batch_size=64, validation_split=0.1)

# Evaluate on test data
loss, accuracy = model.evaluate(x_test, y_test)

print(f'Test loss: {loss:.4f}')
print(f'Test accuracy: {accuracy:.4f}')

Important Notes

Use small kernel sizes like (3,3) to capture fine details.

Pooling layers help reduce image size and computation.

Softmax activation in the last layer gives probabilities for each class.

Summary

CNNs look at images in small parts to find patterns.

Layers like Conv2D and MaxPooling2D help the model learn and shrink images.

Dense layers at the end decide the final class based on learned features.

Practice

1. What is the main role of the Conv2D layer in a CNN for image classification?

easy

A. To reduce the size of the image by pooling

B. To decide the final class of the image

C. To flatten the image into a 1D array

D. To detect patterns like edges and shapes in small parts of the image

Solution

1. Step 1: Understand the function of Conv2D

   The Conv2D layer scans small parts of the image to find patterns such as edges and textures.

2. Step 2: Compare with other layers

   Pooling layers reduce size, flatten layers reshape data, and dense layers classify. Conv2D focuses on pattern detection.

3. Final Answer:

   To detect patterns like edges and shapes in small parts of the image -> Option D

4. Quick Check:

   Conv2D = pattern detection [OK]

Hint: Conv2D finds patterns; pooling shrinks images [OK]

Common Mistakes:

• Confusing Conv2D with pooling layers
• Thinking Conv2D flattens the image
• Believing Conv2D decides the final class

2. Which of the following is the correct way to add a MaxPooling2D layer in TensorFlow Keras?

easy

A. tf.keras.layers.MaxPooling2D(pool_size=(2, 2))

B. tf.keras.layers.MaxPooling(pool=(2, 2))

C. tf.keras.layers.MaxPool2D(size=(2, 2))

D. tf.keras.layers.Pooling2D(pool_size=2)

Solution

1. Step 1: Recall correct TensorFlow layer syntax

   The correct class name is MaxPooling2D and it uses the argument pool_size to set the window size.

2. Step 2: Check each option

   tf.keras.layers.MaxPooling2D(pool_size=(2, 2)) uses correct class and argument. Others have wrong class names or argument names.

3. Final Answer:

   tf.keras.layers.MaxPooling2D(pool_size=(2, 2)) -> Option A

4. Quick Check:

   MaxPooling2D with pool_size=(2,2) is correct [OK]

Hint: MaxPooling2D uses pool_size, not pool or size [OK]

Common Mistakes:

• Using wrong layer class names
• Using incorrect argument names like pool or size
• Omitting parentheses or tuple for pool_size

3. What will be the output shape after applying this CNN block on an input image of shape (64, 64, 3)?

model = tf.keras.Sequential([
  tf.keras.layers.Conv2D(32, (3,3), activation='relu', input_shape=(64,64,3)),
  tf.keras.layers.MaxPooling2D(pool_size=(2,2))
])
output_shape = model.output_shape

medium

A. (None, 32, 32, 32)

B. (None, 62, 62, 32)

C. (None, 31, 31, 32)

D. (None, 64, 64, 32)

Solution

1. Step 1: Calculate Conv2D output shape

   Conv2D with kernel size 3x3 and default padding='valid' reduces each spatial dimension by 2: 64 - 3 + 1 = 62, so output shape is (62, 62, 32).

2. Step 2: Calculate MaxPooling2D output shape

   MaxPooling2D with pool size 2x2 halves each spatial dimension: 62 / 2 = 31, so output shape is (31, 31, 32).

3. Final Answer:

   (None, 31, 31, 32) -> Option C

4. Quick Check:

   Conv2D valid padding reduces size; pooling halves it [OK]

Hint: Conv2D valid padding shrinks; pooling halves size [OK]

Common Mistakes:

• Assuming padding='same' by default
• Forgetting spatial dimension reduction by Conv2D
• Misapplying pooling size effect

4. Identify the error in this CNN model code snippet:

model = tf.keras.Sequential([
  tf.keras.layers.Conv2D(64, (3,3), activation='relu', input_shape=(28,28,1)),
  tf.keras.layers.MaxPooling2D(pool_size=2),
  tf.keras.layers.Dense(10, activation='softmax')
])

medium

A. Missing Flatten layer before Dense

B. Wrong input_shape format

C. MaxPooling2D pool_size should be a tuple

D. Dense layer should have no activation

Solution

1. Step 1: Check layer order and compatibility

   Conv2D and MaxPooling2D output 3D tensors, but Dense expects 1D input.

2. Step 2: Identify missing layer

   A Flatten layer is needed to convert 3D output to 1D before Dense.

3. Final Answer:

   Missing Flatten layer before Dense -> Option A

4. Quick Check:

   Dense needs 1D input; add Flatten [OK]

Hint: Add Flatten before Dense after Conv/Pooling [OK]

Common Mistakes:

• Skipping Flatten layer before Dense
• Assuming Dense accepts 3D input
• Confusing pool_size tuple requirement

5. You want to build a CNN to classify 100x100 RGB images into 5 classes. Which architecture below is best suited for this task?

hard

A. Dense(128, relu) -> Dense(64, relu) -> Dense(5, softmax)

B. Conv2D(16, (3,3)) -> MaxPooling2D(2,2) -> Conv2D(32, (3,3)) -> MaxPooling2D(2,2) -> Flatten -> Dense(5, softmax)

C. Conv2D(64, (5,5), padding='same') -> Flatten -> Dense(5, softmax)

D. Conv2D(32, (3,3)) -> Conv2D(32, (3,3)) -> Dense(5, softmax)

Solution

1. Step 1: Analyze each architecture's suitability

   Conv2D(16, (3,3)) -> MaxPooling2D(2,2) -> Conv2D(32, (3,3)) -> MaxPooling2D(2,2) -> Flatten -> Dense(5, softmax) uses multiple Conv2D and MaxPooling layers to extract features and reduce size, then flattens before classification. This is a standard CNN design.

2. Step 2: Identify issues in other options

   Dense(128, relu) -> Dense(64, relu) -> Dense(5, softmax) uses only Dense layers, ignoring spatial info. Conv2D(64, (5,5), padding='same') -> Flatten -> Dense(5, softmax) lacks pooling, risking large feature maps. Conv2D(32, (3,3)) -> Conv2D(32, (3,3)) -> Dense(5, softmax) misses Flatten and pooling, causing shape errors.

3. Final Answer:

   Conv2D(16, (3,3)) -> MaxPooling2D(2,2) -> Conv2D(32, (3,3)) -> MaxPooling2D(2,2) -> Flatten -> Dense(5, softmax) -> Option B

4. Quick Check:

   Multiple Conv+Pooling layers + Flatten + Dense = best CNN [OK]

Hint: Use Conv + Pooling layers before Flatten and Dense [OK]

Common Mistakes:

• Using only Dense layers for images
• Skipping pooling layers
• Missing Flatten before Dense