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.