Padding and stride in TensorFlow - Model Pipeline Trace

Model Pipeline - Padding and stride

This pipeline shows how padding and stride affect the size of images as they pass through a convolutional layer in a neural network. Padding adds extra pixels around the image edges, and stride controls how the filter moves over the image.

Data Flow - 3 Stages

1Input Image

1 image x 28 height x 28 width x 1 channel→Original grayscale image→1 image x 28 height x 28 width x 1 channel

A 28x28 pixel handwritten digit image

↓

2Apply Padding

1 image x 28 height x 28 width x 1 channel→Add 1 pixel zero padding around all edges→1 image x 30 height x 30 width x 1 channel

Image now has a 1-pixel black border around it

↓

3Convolution with stride

1 image x 30 height x 30 width x 1 channel→Apply 3x3 filter with stride 2→1 image x 14 height x 14 width x 1 channel

Filter moves 2 pixels at a time, reducing size

Training Trace - Epoch by Epoch

Loss
0.7 |****
0.6 |*** 
0.5 |**  
0.4 |*   
0.3 |    
0.2 |    
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.65	0.60	Model starts learning, loss is high, accuracy low
2	0.48	0.75	Loss decreases, accuracy improves as model learns features
3	0.35	0.85	Model captures patterns well, loss drops further
4	0.28	0.90	Good convergence, accuracy nearing 90%
5	0.22	0.93	Model stabilizes with low loss and high accuracy

Prediction Trace - 3 Layers

Layer 1: Input Image

Layer 2: Padding

Layer 3: Convolution with stride 2

Model Quiz - 3 Questions

What effect does adding padding have on the image size before convolution?

A Decreases image size by cropping edges

B Does not change image size

C Increases image size by adding pixels around edges

D Changes image colors

Key Insight

Padding helps keep the image size from shrinking too much during convolution, preserving edge details. Stride controls how much the filter moves, affecting output size and computation. Together, they balance detail retention and efficiency in feature extraction.

Practice

1. What does padding do in a convolutional layer in TensorFlow?

easy

A. Changes the filter size

B. Adjusts the learning rate

C. Controls the number of filters

D. Adds extra space around the input edges

Solution

1. Step 1: Understand padding role

   Padding adds pixels around the input image edges to control output size and preserve edge information.

2. Step 2: Compare options

   Only Adds extra space around the input edges correctly describes padding as adding space around input edges.

3. Final Answer:

   Adds extra space around the input edges -> Option D

4. Quick Check:

   Padding = Adds space around input edges [OK]

Hint: Padding adds border space around input images [OK]

Common Mistakes:

• Confusing padding with stride
• Thinking padding changes filter size
• Assuming padding controls learning rate

2. Which of the following is the correct way to specify stride of 2 in TensorFlow's Conv2D layer?

easy

A. strides=(2)

B. stride=(2)

C. strides=(2, 2)

D. stride=2

Solution

1. Step 1: Recall Conv2D stride syntax

   TensorFlow Conv2D expects strides as a tuple for height and width, e.g., (2, 2).

2. Step 2: Check options

   Only strides=(2, 2) uses the correct parameter name and tuple format.

3. Final Answer:

   strides=(2, 2) -> Option C

4. Quick Check:

   Stride syntax = strides=(2, 2) [OK]

Hint: Use tuple for strides in Conv2D: strides=(height, width) [OK]

Common Mistakes:

• Using 'stride' instead of 'strides'
• Passing a single integer instead of a tuple
• Omitting parentheses around stride values

3. Given an input of size 28x28, a filter size of 3x3, stride of 2, and 'valid' padding, what is the output size after Conv2D?

medium

A. 13x13

B. 14x14

C. 15x15

D. 12x12

Solution

1. Step 1: Calculate output size formula for 'valid' padding

   Output size = floor((Input - Filter) / Stride) + 1 = floor((28 - 3) / 2) + 1 = floor(25 / 2) + 1 = 12 + 1 = 13.

2. Step 2: Confirm output dimensions

   Output height and width are both 13, so output size is 13x13.

3. Final Answer:

   13x13 -> Option A

4. Quick Check:

   Output size = 13x13 with valid padding [OK]

Hint: Use formula: floor((input-filter)/stride)+1 for 'valid' padding [OK]

Common Mistakes:

• Using 'same' padding formula instead
• Forgetting to floor the division
• Adding padding when 'valid' means no padding

4. You wrote this code but get an error:

tf.keras.layers.Conv2D(filters=32, kernel_size=3, strides=2, padding='samee')

What is the error?

medium

A. Strides must be a tuple, not integer

B. Invalid padding value 'samee'

C. Kernel size must be a tuple

D. Filters must be a list

Solution

1. Step 1: Check padding parameter

   Padding accepts only 'valid' or 'same'. 'samee' is a typo and invalid.

2. Step 2: Verify other parameters

   Strides can be integer or tuple, kernel_size can be int or tuple, filters is integer. So no error there.

3. Final Answer:

   Invalid padding value 'samee' -> Option B

4. Quick Check:

   Padding typo causes error [OK]

Hint: Check spelling of padding values: 'same' or 'valid' only [OK]

Common Mistakes:

• Misspelling padding values
• Assuming strides must be tuple always
• Confusing kernel_size type requirements

5. You want to keep the output size same as input (28x28) after Conv2D with filter size 5x5. Which padding and stride should you use?

hard

A. padding='same', strides=(1, 1)

B. padding='valid', strides=(1, 1)

C. padding='same', strides=(2, 2)

D. padding='valid', strides=(2, 2)

Solution

1. Step 1: Understand output size preservation

   To keep output size same as input, use 'same' padding and stride 1 so filter slides over every pixel with padding added.

2. Step 2: Check options

   Only padding='same', strides=(1, 1) uses 'same' padding and stride (1,1), which preserves size.

3. Final Answer:

   padding='same', strides=(1, 1) -> Option A

4. Quick Check:

   Same padding + stride 1 keeps size [OK]

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

Common Mistakes:

• Using 'valid' padding which shrinks output
• Using stride > 1 which reduces output size
• Confusing filter size effect on output