Kernel size, stride, padding in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is kernel size in a convolutional layer?

Kernel size is the size of the small window (filter) that slides over the input image or feature map to detect patterns. For example, a 3x3 kernel looks at 3 pixels wide and 3 pixels tall at a time.

beginner

Explain stride in convolution.

Stride is how many pixels the kernel moves each time it slides over the input. A stride of 1 moves the kernel one pixel at a time, while a stride of 2 skips one pixel, making the output smaller.

beginner

What does padding do in convolutional layers?

Padding adds extra pixels (usually zeros) around the input edges. This helps keep the output size the same as the input or controls how much the output shrinks after convolution.

intermediate

How does increasing stride affect the output size?

Increasing stride makes the kernel jump further each step, so the output feature map becomes smaller because fewer positions are covered.

intermediate

Why might you use padding='same' in PyTorch convolution?

Padding='same' adds just enough padding so the output size matches the input size, which is useful when you want to keep spatial dimensions unchanged through layers.

What does a kernel size of (5,5) mean in a convolution?

A The filter looks at 5 pixels wide and 5 pixels tall at a time

B The stride moves 5 pixels each step

C Padding adds 5 pixels around the input

D The output size will be 5 times smaller

Kernel size defines the filter window size, so (5,5) means 5 pixels wide and 5 pixels tall.

If stride=2, how does the output size change compared to stride=1?

A Output size doubles

B Output size becomes zero

C Output size halves approximately

D Output size stays the same

A stride of 2 skips pixels, so the output size roughly halves compared to stride 1.

What is the main purpose of padding in convolution?

A To add extra pixels around input edges

B To increase the number of channels

C To reduce the kernel size

D To speed up training

Padding adds pixels (usually zeros) around the input edges to control output size.

Which PyTorch parameter controls how far the kernel moves each step?

A kernel_size

B dilation

C padding

D stride

Stride controls the step size of the kernel movement.

What happens if you use no padding with a 3x3 kernel and stride 1 on a 28x28 input?

A Output size remains 28x28

B Output size becomes 26x26

C Output size becomes 30x30

D Output size becomes 1x1

Without padding, output size shrinks by kernel_size - 1, so 28 - 3 + 1 = 26.

Describe how kernel size, stride, and padding affect the output size of a convolutional layer.

Think about how the filter moves and how edges are handled.

Explain why padding might be important when stacking many convolutional layers.

Consider what happens to image size after many convolutions.

Practice

1. What does the stride parameter control in a convolutional layer in PyTorch?

easy

A. How far the filter moves on the input each step

B. The size of the filter scanning the input

C. The number of filters used in the layer

D. The amount of zero padding added around the input

Solution

1. Step 1: Understand stride in convolution

   Stride defines the step size the filter moves when scanning the input image or feature map.

2. Step 2: Differentiate stride from other parameters

   Kernel size is the filter size, padding adds pixels around input, and number of filters controls output depth.

3. Final Answer:

   How far the filter moves on the input each step -> Option A

4. Quick Check:

   Stride = step size of filter movement [OK]

Hint: Stride = filter step size, not size or padding [OK]

Common Mistakes:

• Confusing stride with kernel size
• Thinking stride controls padding
• Mixing stride with number of filters

2. Which of the following is the correct way to create a 2D convolutional layer in PyTorch with kernel size 3, stride 2, and padding 1?

easy

A. nn.Conv2d(in_channels=1, out_channels=10, kernel_size=3, stride=2, padding=1)

B. nn.Conv2d(1, 10, kernel=3, stride=2, pad=1)

C. nn.Conv2d(1, 10, kernel_size=3, stride=1, padding=2)

D. nn.Conv2d(in_channels=1, out_channels=10, kernel_size=2, stride=2, padding=1)

Solution

1. Step 1: Check PyTorch Conv2d parameter names

   Correct parameters are in_channels, out_channels, kernel_size, stride, and padding.

2. Step 2: Match values to question

   Kernel size=3, stride=2, padding=1 matches only nn.Conv2d(in_channels=1, out_channels=10, kernel_size=3, stride=2, padding=1) exactly.

3. Final Answer:

   nn.Conv2d(in_channels=1, out_channels=10, kernel_size=3, stride=2, padding=1) -> Option A

4. Quick Check:

   Correct parameter names and values used [OK]

Hint: Use exact PyTorch parameter names: kernel_size, stride, padding [OK]

Common Mistakes:

• Using wrong parameter names like kernel or pad
• Mixing stride and padding values
• Wrong kernel size or stride values

3. Given an input tensor of size (1, 1, 7, 7), a Conv2d layer with kernel_size=3, stride=2, and padding=1 is applied. What is the output spatial size (height and width)?

medium

A. (1, 1, 3, 3)

B. (1, 1, 5, 5)

C. (1, 1, 2, 2)

D. (1, 1, 4, 4)

Solution

1. Step 1: Use output size formula for Conv2d

   Output size = floor((Input + 2*padding - kernel_size)/stride) + 1

2. Step 2: Calculate output height and width

   Input=7, padding=1, kernel=3, stride=2
   Output = floor((7 + 2*1 - 3)/2) + 1 = floor((7 + 2 - 3)/2) + 1 = floor(6/2) + 1 = 3 + 1 = 4

3. Final Answer:

   (1, 1, 4, 4) -> Option D

4. Quick Check:

   Output size formula applied correctly [OK]

Hint: Apply formula: floor((I+2P-K)/S)+1 for each dimension [OK]

Common Mistakes:

• Forgetting to add padding twice
• Using ceil instead of floor
• Mixing stride and kernel size in formula

4. You wrote this PyTorch code but get an error:

nn.Conv2d(1, 10, kernel_size=3, stride=2, padding=0)

on input size (1, 1, 1, 1). What is the likely cause?

medium

A. Kernel size must be even number

B. Padding is too small for the input size causing negative output dimension

C. Stride value must be 1 for kernel size 3

D. Input channels and output channels are swapped

Solution

1. Step 1: Check output size with given parameters

   Output size = floor((1 + 2*0 - 3)/2) + 1 = floor((-2)/2) + 1 = floor(-1) + 1 = -1 + 1 = 0 (invalid)

2. Step 2: Consider if padding causes error

   Padding=0 on small input (1x1) causes the calculated output size to be zero, which PyTorch raises as a runtime error due to insufficient padding for the kernel size.

3. Final Answer:

   Padding is too small for the input size causing negative output dimension -> Option B

4. Quick Check:

   Padding too small -> invalid output size [OK]

Hint: Check if padding is too small for input size [OK]

Common Mistakes:

• Assuming stride must be 1 for kernel 3
• Thinking kernel size must be even
• Swapping input and output channels

5. You want to keep the output size the same as the input size (7x7) after a Conv2d layer with kernel_size=5 and stride=1. What padding value should you use?

hard

A. 1

B. 0

C. 2

D. 3

Solution

1. Step 1: Use formula for output size with stride=1

   Output size = Input size if padding = (kernel_size - 1) / 2

2. Step 2: Calculate padding

   Padding = (5 - 1) / 2 = 4 / 2 = 2

3. Final Answer:

   2 -> Option C

4. Quick Check:

   Padding = (kernel_size - 1)/2 keeps size same [OK]

Hint: Padding = (kernel_size - 1) / 2 for same size with stride 1 [OK]

Common Mistakes:

• Using padding 0 or 1 incorrectly
• Forgetting stride must be 1 for same size
• Using padding larger than needed