Kernel size, stride, padding in PyTorch - Model Pipeline Trace

Model Pipeline - Kernel size, stride, padding

This pipeline shows how an image passes through a convolutional layer in a neural network. It explains how kernel size, stride, and padding affect the image size and feature extraction.

Data Flow - 3 Stages

1Input Image

1 image x 1 channel x 5 height x 5 width→Original grayscale image→1 image x 1 channel x 5 height x 5 width

[[1, 2, 3, 0, 1], [0, 1, 2, 3, 1], [1, 0, 1, 2, 2], [2, 1, 0, 1, 0], [1, 2, 1, 0, 1]]

↓

2Apply Padding

1 x 1 x 5 x 5→Add zero padding of 1 pixel around the image→1 x 1 x 7 x 7

[[0,0,0,0,0,0,0], [0,1,2,3,0,1,0], [0,0,1,2,3,1,0], [0,1,0,1,2,2,0], [0,2,1,0,1,0,0], [0,1,2,1,0,1,0], [0,0,0,0,0,0,0]]

↓

3Convolution with Kernel

1 x 1 x 7 x 7→Apply 3x3 kernel with stride 2→1 x 1 x 3 x 3

Sliding 3x3 kernel over padded image with steps of 2 pixels

Training Trace - Epoch by Epoch

Loss
1.0 |****
0.8 |****
0.6 |****
0.4 |****
0.2 |****
0.0 +----
      1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.85	0.45	Initial training with high loss and low accuracy
2	0.65	0.60	Loss decreased, accuracy improved
3	0.50	0.72	Model learning features well
4	0.40	0.80	Good convergence, loss decreasing steadily
5	0.35	0.85	Training stabilizing with high accuracy

Prediction Trace - 3 Layers

Layer 1: Input Image

Layer 2: Padding

Layer 3: Convolution with 3x3 kernel, stride 2

Model Quiz - 3 Questions

What does increasing the stride in a convolution do to the output size?

A Keeps output size the same

B Increases output size

C Decreases output size

D Removes padding

Key Insight

Kernel size controls the area the model looks at once. Stride controls how much the kernel moves each step, affecting output size. Padding helps keep output size larger by adding borders. Together, they shape how the model extracts features from images.

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