Kernel size, stride, padding in PyTorch - ML Experiment: Train & Evaluate

Experiment - Kernel size, stride, padding

Problem:You have a convolutional neural network layer that processes images. The current layer uses a kernel size of 3, stride of 1, and no padding. The output feature map is smaller than expected, causing loss of important edge information.

Current Metrics:Input image size: 28x28, Output feature map size: 26x26

Issue:The output feature map is smaller than the input, which may cause loss of edge information. This happens because no padding is used and stride is 1 with kernel size 3.

Your Task

Adjust the kernel size, stride, and padding to keep the output feature map size the same as the input (28x28) while maintaining stride 1.

Stride must remain 1

Kernel size can be 3 or 5

Padding must be adjusted accordingly

Hint 1

Hint 2

Hint 3

Solution

PyTorch

import torch
import torch.nn as nn

# Define a convolutional layer with kernel size 3, stride 1, padding 1
conv_layer = nn.Conv2d(in_channels=1, out_channels=1, kernel_size=3, stride=1, padding=1)

# Create a dummy input tensor with batch size 1, 1 channel, 28x28 image
input_tensor = torch.randn(1, 1, 28, 28)

# Pass input through conv layer
output_tensor = conv_layer(input_tensor)

# Print output shape
print(f"Output shape with kernel=3, stride=1, padding=1: {output_tensor.shape}")

# Now try kernel size 5 with padding 2
conv_layer_5 = nn.Conv2d(in_channels=1, out_channels=1, kernel_size=5, stride=1, padding=2)
output_tensor_5 = conv_layer_5(input_tensor)
print(f"Output shape with kernel=5, stride=1, padding=2: {output_tensor_5.shape}")

Added padding to keep output size same as input

Used padding=1 for kernel size 3

Used padding=2 for kernel size 5

Kept stride fixed at 1

Results Interpretation

Before: Output size was 26x26 with kernel=3, stride=1, padding=0.
After: Output size is 28x28 with kernel=3, stride=1, padding=1 or kernel=5, stride=1, padding=2.

Padding controls the size of the output feature map. By adding appropriate padding, you can keep the output size the same as the input, preserving edge information. Kernel size and padding must be balanced to achieve this.

Bonus Experiment

Try changing the stride to 2 with kernel size 3 and padding 1. Observe how the output size changes.

💡 Hint

Use the output size formula and see how stride affects the output dimensions. Expect the output size to reduce roughly by half.

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