Padding and stride in TensorFlow - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is padding in convolutional neural networks?

Padding means adding extra pixels (usually zeros) around the edges of an image before applying convolution. It helps keep the output size larger or the same as the input.

beginner

What does stride control in convolution?

Stride controls how many pixels the filter moves each step when sliding over the image. A stride of 1 moves one pixel at a time, stride 2 moves two pixels, making the output smaller.

intermediate

What is the difference between 'valid' and 'same' padding in TensorFlow?

'Valid' padding means no padding is added, so the output is smaller than the input. 'Same' padding adds zeros so the output size stays the same as the input size.

intermediate

How does increasing stride affect the output size?

Increasing stride makes the filter jump more pixels, so the output size becomes smaller because fewer positions are covered.

beginner

Why might you use padding in a convolutional layer?

Padding helps preserve important edge information and controls output size. Without padding, edges get ignored and output shrinks quickly.

What does 'same' padding do in a convolutional layer?

A Keeps output size the same as input size

B Removes pixels from the input

C Doubles the output size

D Adds random noise to input

'Same' padding adds zeros around the input so the output size matches the input size.

If stride is set to 2, what happens to the output size?

A Output size becomes zero

B Output size doubles

C Output size stays the same

D Output size halves approximately

Stride 2 moves the filter two pixels at a time, reducing output size roughly by half.

Which padding type means no padding is added?

A Same

B Full

C Valid

D Zero

'Valid' padding means no padding, so output is smaller than input.

Why do we add padding in convolutional layers?

A To keep edge information and control output size

B To increase the number of filters

C To speed up training

D To reduce model size

Padding preserves edges and helps keep output size as desired.

What happens if you use stride 1 and no padding?

A Output size is larger than input

B Output size is smaller than input

C Output size stays the same

D Model will not train

Without padding and stride 1, output shrinks because filter can't slide over edges fully.

Explain in your own words what padding and stride do in a convolutional neural network.

Think about how the filter moves and what happens at image edges.

Describe the difference between 'valid' and 'same' padding and how they affect the output size.

Consider how zeros around the image change the convolution result.

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