Why CNNs detect spatial patterns in PyTorch - Why Metrics Matter

Metrics & Evaluation - Why CNNs detect spatial patterns

Which metric matters for this concept and WHY

For convolutional neural networks (CNNs) detecting spatial patterns, accuracy and loss during training are key metrics. Accuracy shows how well the model recognizes patterns in images or spatial data. Loss tells us how far off the model's predictions are from the true labels. Since CNNs focus on spatial features, metrics like precision and recall also matter when classes are imbalanced or some patterns are rare.

Confusion matrix or equivalent visualization (ASCII)

      Confusion Matrix Example:

          Predicted
          Cat   Dog
    True Cat  45    5
         Dog   3   47

    Here:
    - True Positives (TP) for Cat = 45
    - False Positives (FP) for Cat = 3
    - False Negatives (FN) for Cat = 5
    - True Negatives (TN) for Cat = 47

    This matrix helps us calculate precision and recall for each class.
    

Precision vs Recall tradeoff with concrete examples

Imagine a CNN detecting tumors in medical images (spatial patterns). Here, recall is very important because missing a tumor (false negative) is dangerous. We want the model to catch as many tumors as possible, even if it means some false alarms (lower precision).

On the other hand, if a CNN detects defects in manufactured parts, precision matters more. We want to avoid marking good parts as defective (false positives) to save costs.

Balancing precision and recall depends on the task and consequences of errors.

What "good" vs "bad" metric values look like for this use case

Good metrics:

• High accuracy (e.g., above 90%) on spatial pattern recognition tasks.
• Precision and recall both above 85%, showing balanced detection.
• Low loss values steadily decreasing during training.

Bad metrics:

• Accuracy near random guess (e.g., 50% for two classes).
• Very low recall (e.g., 20%) meaning many patterns missed.
• High loss or loss not improving, indicating poor learning.

Metrics pitfalls

• Accuracy paradox: High accuracy can be misleading if classes are imbalanced. For example, if 95% of images are background, a model always predicting background gets 95% accuracy but fails to detect patterns.
• Data leakage: If training and test data overlap, metrics look better but model won't generalize.
• Overfitting indicators: Training accuracy very high but test accuracy low means model memorizes training patterns but fails on new data.

Self-check question

Your CNN model for detecting spatial patterns has 98% accuracy but only 12% recall on the important class. Is it good for production? Why not?

Answer: No, it is not good. The low recall means the model misses most of the important patterns, even though overall accuracy is high. This can happen if the important class is rare and the model predicts mostly the other class. For production, recall must be higher to catch most patterns.

Key Result

For CNNs detecting spatial patterns, balanced precision and recall alongside accuracy best show model effectiveness.

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