Why CNNs detect spatial patterns in PyTorch

Introduction

Convolutional Neural Networks (CNNs) are designed to find patterns in images or data that have a spatial layout, like shapes or edges. They look at small parts of the data at a time, which helps them understand where things are in the image.

When you want to recognize objects in photos, like cats or cars.

When you need to detect patterns in medical images, such as tumors in X-rays.

When analyzing satellite images to find roads or buildings.

When building systems that understand handwriting or text in pictures.

When working with any data that has a grid-like structure, like audio spectrograms.

Syntax

PyTorch

import torch
import torch.nn as nn

class SimpleCNN(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv = nn.Conv2d(in_channels=1, out_channels=1, kernel_size=3)

    def forward(self, x):
        return self.conv(x)

The nn.Conv2d layer looks at small 2D patches (called kernels) of the input.

It slides this kernel over the input image to detect spatial features like edges or textures.

Examples

This creates a convolutional layer that looks at color images with 3 channels and outputs 16 feature maps using 5x5 kernels.

PyTorch

conv = nn.Conv2d(in_channels=3, out_channels=16, kernel_size=5)

This runs a random 32x32 color image through the convolution and prints the output shape.

PyTorch

output = conv(torch.randn(1, 3, 32, 32))
print(output.shape)

Sample Model

This code creates a simple CNN with one convolutional layer. The kernel is set to detect horizontal edges. The input is a 5x5 image with a square pattern. The output shows where the horizontal edges are detected.

PyTorch

import torch
import torch.nn as nn

# Define a simple CNN
class SimpleCNN(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv = nn.Conv2d(1, 1, 3, padding=1)  # 3x3 kernel, padding to keep size

    def forward(self, x):
        return self.conv(x)

# Create a sample 5x5 image with a simple pattern
image = torch.tensor([[[
    [0, 0, 0, 0, 0],
    [0, 1, 1, 1, 0],
    [0, 1, 0, 1, 0],
    [0, 1, 1, 1, 0],
    [0, 0, 0, 0, 0]
]]], dtype=torch.float32)

model = SimpleCNN()

# Manually set the kernel to detect horizontal edges
with torch.no_grad():
    model.conv.weight[:] = torch.tensor([[[[-1, -1, -1],
                                          [ 0,  0,  0],
                                          [ 1,  1,  1]]]])
    model.conv.bias[:] = 0

output = model(image)
print(output[0,0])

Important Notes

CNNs use small kernels to focus on local parts of the image, which helps them learn spatial patterns.

Padding keeps the output size the same as input, so spatial information is preserved.

Weights in the kernel act like filters that detect specific features like edges or textures.

Summary

CNNs detect spatial patterns by sliding small filters over images.

These filters learn to recognize features like edges, shapes, or textures.

This makes CNNs very good for image and spatial data tasks.

Practice

1. Why do CNNs use small filters that slide over an image?

easy

A. To detect local spatial patterns like edges and textures

B. To reduce the image size drastically in one step

C. To convert images into text data

D. To randomly change pixel colors

Solution

1. Step 1: Understand the role of filters in CNNs

   Filters slide over small parts of the image to focus on local details like edges or shapes.

2. Step 2: Connect filter behavior to spatial pattern detection

   By scanning the image locally, filters learn to recognize important spatial features that help in tasks like image recognition.

3. Final Answer:

   To detect local spatial patterns like edges and textures -> Option A

4. Quick Check:

   Filters detect local patterns = A [OK]

Hint: Filters scan small areas to find edges and shapes [OK]

Common Mistakes:

• Thinking filters change image size drastically in one step
• Believing CNNs convert images to text directly
• Assuming filters randomly alter pixel colors

2. Which PyTorch code correctly creates a 2D convolutional layer with a 3x3 filter?

easy

A. torch.nn.Conv2d(in_channels=1, out_channels=10, kernel_size=3)

B. torch.nn.Conv1d(in_channels=1, out_channels=10, kernel_size=3)

C. torch.nn.Linear(in_features=3, out_features=10)

D. torch.nn.Conv2d(in_channels=1, out_channels=10, kernel_size=5)

Solution

1. Step 1: Identify the correct convolution layer type

   For images, 2D convolution (Conv2d) is used, not Conv1d or Linear layers.

2. Step 2: Check the kernel size matches 3x3

   kernel_size=3 means a 3x3 filter, so torch.nn.Conv2d(in_channels=1, out_channels=10, kernel_size=3) is correct; torch.nn.Conv2d(in_channels=1, out_channels=10, kernel_size=5) uses 5x5.

3. Final Answer:

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

4. Quick Check:

   Conv2d with kernel_size=3 = D [OK]

Hint: Use Conv2d and kernel_size=3 for 3x3 filters [OK]

Common Mistakes:

• Using Conv1d instead of Conv2d for images
• Confusing Linear layers with convolution layers
• Setting wrong kernel size for the filter

3. Given this PyTorch code snippet, what is the output shape after the convolution?

import torch
conv = torch.nn.Conv2d(1, 1, kernel_size=3)
input = torch.randn(1, 1, 5, 5)
output = conv(input)
print(output.shape)

medium

A. torch.Size([1, 1, 5, 5])

B. torch.Size([1, 3, 3, 3])

C. torch.Size([1, 1, 7, 7])

D. torch.Size([1, 1, 3, 3])

Solution

1. Step 1: Understand convolution output size formula

   Output size = Input size - Kernel size + 1 (assuming stride=1, padding=0). Here, 5 - 3 + 1 = 3.

2. Step 2: Apply formula to each spatial dimension

   Both height and width become 3, so output shape is (1 batch, 1 channel, 3 height, 3 width).

3. Final Answer:

   torch.Size([1, 1, 3, 3]) -> Option D

4. Quick Check:

   Output size = 5-3+1 = 3 [OK]

Hint: Output size = input - kernel + 1 if no padding [OK]

Common Mistakes:

• Assuming output size equals input size without padding
• Confusing batch and channel dimensions
• Misapplying kernel size in output calculation

4. What is wrong with this PyTorch code for a convolutional layer?

conv = torch.nn.Conv2d(in_channels=3, out_channels=6, kernel_size=3)
input = torch.randn(1, 1, 28, 28)
output = conv(input)
print(output.shape)

medium

A. Output channels must be less than input channels

B. Kernel size is too large for the input

C. Input channels do not match the layer's in_channels

D. Batch size must be greater than 1

Solution

1. Step 1: Check input and layer channel compatibility

   The layer expects 3 input channels, but input has only 1 channel, causing a mismatch error.

2. Step 2: Confirm other parameters are valid

   Kernel size 3 is valid for 28x28 input, output channels can be any positive number, batch size 1 is allowed.

3. Final Answer:

   Input channels do not match the layer's in_channels -> Option C

4. Quick Check:

   Input channels mismatch = A [OK]

Hint: Input channels must match Conv2d in_channels [OK]

Common Mistakes:

• Ignoring channel mismatch errors
• Thinking kernel size is invalid for input
• Believing batch size must be >1

5. How does using multiple convolutional layers help CNNs detect complex spatial patterns?

hard

A. Layers randomly shuffle pixels to create new patterns

B. Each layer learns higher-level features by combining simpler patterns from previous layers

C. Multiple layers reduce the image size to zero quickly

D. Each layer independently detects the same simple edges

Solution

1. Step 1: Understand feature hierarchy in CNNs

   Early layers detect simple features like edges; later layers combine these to form complex shapes and objects.

2. Step 2: Explain how multiple layers build complexity

   Stacking layers lets the network learn spatial patterns at increasing levels of abstraction, improving recognition.

3. Final Answer:

   Each layer learns higher-level features by combining simpler patterns from previous layers -> Option B

4. Quick Check:

   Layer stacking builds complex features = C [OK]

Hint: Layers build complexity by combining simpler features [OK]

Common Mistakes:

• Thinking layers just reduce image size quickly
• Believing layers shuffle pixels randomly
• Assuming all layers detect the same simple edges