Kernel size, stride, padding in PyTorch - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output shape after convolution with stride and padding

Given a 1-channel input tensor of shape (1, 1, 10, 10), a convolutional layer with kernel size 3, stride 2, and padding 1 is applied. What is the shape of the output tensor?

PyTorch

import torch
import torch.nn as nn

input_tensor = torch.randn(1, 1, 10, 10)
conv = nn.Conv2d(in_channels=1, out_channels=1, kernel_size=3, stride=2, padding=1)
output = conv(input_tensor)
output.shape

A (1, 1, 6, 6)

B (1, 1, 4, 4)

C (1, 1, 7, 7)

D (1, 1, 5, 5)

💡 Hint

Recall the formula for output size: floor((input + 2*padding - kernel_size)/stride) + 1

The output height and width are calculated as floor((10 + 2*1 - 3)/2) + 1 = floor(9/2) + 1 = 4 + 1 = 5. So output shape is (1, 1, 5, 5).

🧠 Conceptual

intermediate

Effect of stride on convolution output size

Which statement correctly describes the effect of increasing the stride in a convolutional layer?

A Increasing stride has no effect on output spatial dimensions.

B Increasing stride increases the output spatial dimensions.

C Increasing stride decreases the output spatial dimensions.

D Increasing stride increases the number of output channels.

💡 Hint

Think about how stride controls the step size when sliding the kernel.

Stride controls how far the kernel moves each step. Larger stride means fewer positions, so output size decreases.

❓ Metrics

advanced

Padding effect on output size with kernel size 5

A convolutional layer uses kernel size 5 and stride 1 on an input of size 28x28. Which padding value will keep the output size the same as the input size?

A Padding = 2

B Padding = 1

C Padding = 0

D Padding = 3

💡 Hint

Use the formula: output = floor((input + 2*padding - kernel_size)/stride) + 1

To keep output size same as input (28), solve 28 = floor((28 + 2*padding - 5)/1) + 1. This gives padding = 2.

🔧 Debug

advanced

Identify the error in convolution output size calculation

A user calculates the output size of a convolution as output = (input_size - kernel_size + 2*padding) / stride + 1 without flooring the division. What problem can this cause?

A Output size will always be larger than input size.

B Output size may be a float, which is invalid for tensor dimensions.

C Padding will be ignored during convolution.

D Stride will be treated as 1 regardless of value.

💡 Hint

Tensor shapes must be integers.

Output size must be an integer because tensor dimensions cannot be fractional. Not flooring leads to float output size, causing errors.

❓ Model Choice

expert

Choosing padding and stride for specific output size

You want a convolutional layer with kernel size 4 on a 32x32 input to produce an output of size 15x15. Which combination of stride and padding achieves this?

A Stride = 2, Padding = 0

B Stride = 3, Padding = 0

C Stride = 1, Padding = 1

D Stride = 2, Padding = 1

💡 Hint

Use output size formula and solve for stride and padding.

Using output = floor((32 + 2*padding - kernel_size)/stride) + 1, with stride=2 and padding=0: floor((32 + 0 - 4)/2) + 1 = floor(28/2) + 1 = 14 + 1 = 15.

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