CNN architecture review in Computer Vision - Model Pipeline Trace

Model Pipeline - CNN architecture review

This pipeline shows how a Convolutional Neural Network (CNN) learns to recognize images by processing raw pictures, extracting features, training on those features, and then making predictions.

Data Flow - 8 Stages

1Input Images

1000 images x 64 x 64 x 3→Raw color images of size 64x64 pixels with 3 color channels (RGB)→1000 images x 64 x 64 x 3

An image of a cat represented as a 64x64 grid with red, green, blue values

↓

2Convolutional Layer 1

1000 images x 64 x 64 x 3→Apply 32 filters of size 3x3 with ReLU activation→1000 images x 62 x 62 x 32

Filters detect edges and simple shapes in the image

↓

3Max Pooling Layer 1

1000 images x 62 x 62 x 32→Downsample by 2x2 max pooling→1000 images x 31 x 31 x 32

Reduce image size while keeping important features

↓

4Convolutional Layer 2

1000 images x 31 x 31 x 32→Apply 64 filters of size 3x3 with ReLU activation→1000 images x 29 x 29 x 64

Filters detect more complex shapes and textures

↓

5Max Pooling Layer 2

1000 images x 29 x 29 x 64→Downsample by 2x2 max pooling→1000 images x 14 x 14 x 64

Further reduce size, keep strongest features

↓

6Flatten Layer

1000 images x 14 x 14 x 64→Flatten 3D feature maps into 1D vectors→1000 images x 12544

Convert features into a long list for dense layers

↓

7Dense Layer

1000 images x 12544→Fully connected layer with 128 neurons and ReLU→1000 images x 128

Combine features to learn complex patterns

↓

8Output Layer

1000 images x 128→Fully connected layer with 10 neurons and softmax→1000 images x 10

Predict probabilities for 10 classes (e.g., digits 0-9)

Training Trace - Epoch by Epoch

Loss
2.0 |****
1.5 |*** 
1.0 |**  
0.5 |*   
0.0 +----
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	1.85	0.35	Model starts learning, accuracy low, loss high
2	1.20	0.55	Loss decreases, accuracy improves
3	0.85	0.70	Model learns important features
4	0.60	0.80	Good progress, model getting better
5	0.45	0.85	Loss low, accuracy high, training converging

Prediction Trace - 8 Layers

Layer 1: Input Image

Layer 2: Convolutional Layer 1

Layer 3: Max Pooling Layer 1

Layer 4: Convolutional Layer 2

Layer 5: Max Pooling Layer 2

Layer 6: Flatten Layer

Layer 7: Dense Layer

Layer 8: Output Layer

Model Quiz - 3 Questions

What does the first convolutional layer mainly detect?

A Edges and simple shapes

B Final class probabilities

C Flattened feature vectors

D Downsampled images

Key Insight

This CNN architecture shows how images are transformed step-by-step from raw pixels to class probabilities. Convolutional layers extract features, pooling layers reduce size while keeping important info, and dense layers learn complex patterns. Training improves accuracy by reducing loss steadily.

Practice

1. What is the main purpose of a Convolutional Neural Network (CNN) in computer vision?

easy

A. To perform text translation

B. To sort numbers in a list

C. To generate random images

D. To detect patterns and features in images

Solution

1. Step 1: Understand CNN function

   CNNs scan images to find important patterns like edges and shapes.

2. Step 2: Match purpose to options

   Only To detect patterns and features in images describes detecting patterns in images, which is CNN's main job.

3. Final Answer:

   To detect patterns and features in images -> Option D

4. Quick Check:

   CNN purpose = detect image patterns [OK]

Hint: CNNs find image features, not unrelated tasks like sorting [OK]

Common Mistakes:

• Confusing CNNs with general neural networks
• Thinking CNNs generate images
• Mixing CNNs with text processing models

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

easy

A. Dense(units=32, activation='relu')

B. Conv1D(filters=32, kernel_size=3, activation='relu')

C. Conv2D(filters=32, kernel_size=(3,3), activation='relu')

D. MaxPooling2D(pool_size=(2,2))

Solution

1. Step 1: Identify Conv2D syntax

   Conv2D requires filters, kernel_size as a tuple, and activation function.

2. Step 2: Compare options

   Conv2D(filters=32, kernel_size=(3,3), activation='relu') matches Conv2D syntax correctly; others are different layers or wrong dimensions.

3. Final Answer:

   Conv2D(filters=32, kernel_size=(3,3), activation='relu') -> Option C

4. Quick Check:

   Conv2D syntax = Conv2D(filters=32, kernel_size=(3,3), activation='relu') [OK]

Hint: Conv2D uses 2D kernel size tuple, not single int [OK]

Common Mistakes:

• Using Conv1D instead of Conv2D for images
• Confusing Dense layer with Conv2D
• Wrong kernel_size format

3. Given this Keras CNN snippet, what is the output shape after the Conv2D layer?

model = Sequential()
model.add(Conv2D(16, (3,3), input_shape=(28,28,1)))

medium

A. (26, 26, 16)

B. (28, 28, 16)

C. (30, 30, 16)

D. (28, 28, 1)

Solution

1. Step 1: Calculate output size after Conv2D

   With default 'valid' padding and kernel size 3, output dims = input - kernel + 1 = 28 - 3 + 1 = 26.

2. Step 2: Determine output channels

   Filters=16 means output depth is 16 channels.

3. Final Answer:

   (26, 26, 16) -> Option A

4. Quick Check:

   Output shape = (26,26,16) [OK]

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

Common Mistakes:

• Assuming output size equals input size without padding
• Confusing number of filters with spatial dimensions
• Forgetting default padding is 'valid'

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

model = Sequential()
model.add(Conv2D(32, (3,3), activation='relu', input_shape=(28,28)))
model.add(Flatten())
model.add(Dense(10, activation='softmax'))

medium

A. Dense layer should come before Flatten

B. input_shape missing channel dimension

C. Activation function 'relu' is invalid

D. Conv2D filters must be 64 or more

Solution

1. Step 1: Check input_shape format

   Conv2D expects input_shape with 3 dimensions: height, width, channels. Here channels are missing.

2. Step 2: Validate other parts

   Activation 'relu' is valid, Flatten before Dense is correct, filters can be any positive integer.

3. Final Answer:

   input_shape missing channel dimension -> Option B

4. Quick Check:

   Input shape must include channels [OK]

Hint: Conv2D input_shape needs (height, width, channels) [OK]

Common Mistakes:

• Ignoring channel dimension in input_shape
• Misordering Flatten and Dense layers
• Thinking filters must be >=64

5. You want to build a CNN for classifying 64x64 RGB images into 5 classes. Which architecture choice is best?

hard

A. Conv2D(32, (3,3)) + MaxPooling2D + Conv2D(64, (3,3)) + Flatten + Dense(5, softmax)

B. Dense(128) + Dense(64) + Dense(5, softmax)

C. Conv1D(32, 3) + Flatten + Dense(5, softmax)

D. Flatten + Dense(5, softmax)

Solution

1. Step 1: Identify suitable layers for image data

   Conv2D layers extract spatial features from 2D images; MaxPooling reduces size; Flatten prepares for Dense.

2. Step 2: Evaluate options

   Conv2D(32, (3,3)) + MaxPooling2D + Conv2D(64, (3,3)) + Flatten + Dense(5, softmax) uses Conv2D and pooling correctly for images. The Dense-only option lacks feature extraction, Conv1D is unsuitable for 2D images, and Flatten + Dense skips convolutions.

3. Final Answer:

   Conv2D(32, (3,3)) + MaxPooling2D + Conv2D(64, (3,3)) + Flatten + Dense(5, softmax) -> Option A

4. Quick Check:

   Use Conv2D + pooling for images [OK]

Hint: Use Conv2D layers for images, not Dense-only or Conv1D [OK]

Common Mistakes:

• Using Dense layers only for image input
• Applying Conv1D to 2D images
• Skipping pooling layers for downsampling