nn.MaxPool2d and nn.AvgPool2d in PyTorch - Model Metrics & Evaluation

Metrics & Evaluation - nn.MaxPool2d and nn.AvgPool2d

Which metric matters for nn.MaxPool2d and nn.AvgPool2d and WHY

Pooling layers like nn.MaxPool2d and nn.AvgPool2d reduce image size to help models learn faster and avoid overfitting. The key metrics to check are model accuracy and loss after adding pooling. These show if pooling helps the model find important features without losing too much detail.

Confusion matrix or equivalent visualization

Confusion Matrix Example (for classification after pooling):

          Predicted
          0    1
Actual 0 50   10
       1  5   35

TP = 35, FP = 10, TN = 50, FN = 5

Precision = 35 / (35 + 10) = 0.78
Recall = 35 / (35 + 5) = 0.875
F1 = 2 * (0.78 * 0.875) / (0.78 + 0.875) ≈ 0.825
    

This shows how well the model predicts classes after using pooling layers.

Precision vs Recall tradeoff with concrete examples

Pooling layers simplify images but can lose details. If too much detail is lost, recall may drop because the model misses some true positives. If pooling keeps important features, precision improves because predictions are more accurate.

Example: In a face recognition app, max pooling helps keep strong features (eyes, nose) improving precision. But if pooling is too aggressive, recall drops because some faces are missed.

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

Good: Accuracy above 80%, balanced precision and recall (both above 75%) after pooling means the model keeps important info and generalizes well.

Bad: Accuracy below 60%, or very low recall (under 50%) means pooling removed too much detail, hurting model predictions.

Metrics pitfalls

• Accuracy paradox: High accuracy can hide poor recall if classes are imbalanced.
• Data leakage: If pooling is applied differently in training and testing, metrics become unreliable.
• Overfitting indicators: If training accuracy is high but test accuracy drops after pooling, pooling might be too weak or too strong.

Self-check question

Your model uses nn.MaxPool2d and shows 98% accuracy but only 12% recall on the positive class. Is it good for production? Why or why not?

Answer: No, it is not good. The low recall means the model misses most positive cases, which can be critical depending on the task. High accuracy here is misleading because the model likely predicts the negative class most of the time.

Key Result

Pooling layers affect model accuracy and recall; balanced precision and recall after pooling show good feature retention.

Practice

1. What is the main difference between nn.MaxPool2d and nn.AvgPool2d in PyTorch?

easy

A. nn.MaxPool2d selects the maximum value in each window, while nn.AvgPool2d computes the average value.

B. nn.MaxPool2d computes the average value, while nn.AvgPool2d selects the maximum value.

C. Both perform the same operation but on different input shapes.

D. nn.MaxPool2d increases data size, nn.AvgPool2d decreases it.

Solution

1. Step 1: Understand pooling operations

   nn.MaxPool2d picks the highest value in each sliding window, emphasizing strong features. nn.AvgPool2d calculates the average, smoothing the features.

2. Step 2: Compare their behavior

   Max pooling keeps the strongest signals, while average pooling provides a smoothed summary of the window.

3. Final Answer:

   nn.MaxPool2d selects the maximum value in each window, while nn.AvgPool2d computes the average value. -> Option A

4. Quick Check:

   MaxPool2d = max, AvgPool2d = average [OK]

Hint: MaxPool picks max; AvgPool averages values [OK]

Common Mistakes:

• Confusing max and average operations
• Thinking both increase data size
• Assuming they work on different input shapes

2. Which of the following is the correct way to create a 2D max pooling layer with a kernel size of 3 and stride of 2 in PyTorch?

easy

A. nn.AvgPool2d(kernel=3, stride=2)

B. nn.MaxPool2d(kernel_size=3, stride=2)

C. nn.MaxPool2d(stride=3, kernel_size=2)

D. nn.MaxPool2d(size=3, step=2)

Solution

1. Step 1: Check PyTorch pooling layer parameters

   The correct parameters for nn.MaxPool2d are kernel_size and stride. The order does not matter if named.

2. Step 2: Validate each option

   nn.MaxPool2d(kernel_size=3, stride=2) uses correct parameter names and values. nn.MaxPool2d(stride=3, kernel_size=2) swaps kernel_size and stride values incorrectly. nn.AvgPool2d(kernel=3, stride=2) uses AvgPool2d instead of MaxPool2d. nn.MaxPool2d(size=3, step=2) uses invalid parameter names.

3. Final Answer:

   nn.MaxPool2d(kernel_size=3, stride=2) -> Option B

4. Quick Check:

   Correct params: kernel_size, stride [OK]

Hint: Use kernel_size and stride parameters exactly [OK]

Common Mistakes:

• Using wrong parameter names like size or step
• Confusing MaxPool2d with AvgPool2d
• Swapping kernel_size and stride values

3. What is the output shape of the following PyTorch code snippet?

import torch
import torch.nn as nn

input_tensor = torch.randn(1, 1, 6, 6)
pool = nn.MaxPool2d(kernel_size=2, stride=2)
output = pool(input_tensor)
print(output.shape)

medium

A. torch.Size([1, 1, 2, 2])

B. torch.Size([1, 1, 6, 6])

C. torch.Size([1, 1, 4, 4])

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

Solution

1. Step 1: Understand input and pooling parameters

   Input shape is (batch=1, channels=1, height=6, width=6). Kernel size and stride are both 2.

2. Step 2: Calculate output dimensions

   Output height = floor((6 - 2) / 2) + 1 = floor(4 / 2) + 1 = 2 + 1 = 3. Similarly, output width = 3. So output shape is (1, 1, 3, 3).

3. Final Answer:

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

4. Quick Check:

   Output size = floor((input - kernel)/stride)+1 [OK]

Hint: Output size = floor((input - kernel)/stride) + 1 [OK]

Common Mistakes:

• Forgetting to apply floor function
• Mixing up height and width calculations
• Assuming output size equals input size

4. Identify the error in the following PyTorch code using nn.AvgPool2d:

import torch
import torch.nn as nn

input_tensor = torch.randn(1, 1, 5, 5)
pool = nn.AvgPool2d(kernel_size=2, stride=3)
output = pool(input_tensor)
print(output.shape)

medium

A. No error; code runs correctly

B. Kernel size must be odd

C. Stride cannot be greater than kernel size

D. Input tensor shape is invalid

Solution

1. Step 1: Check parameter validity

   PyTorch allows stride to be different from kernel size, including stride > kernel size. Kernel size can be even or odd. Input tensor shape is valid.

2. Step 2: Confirm code runs without error

   Running this code produces a valid output shape without errors.

3. Final Answer:

   No error; code runs correctly -> Option A

4. Quick Check:

   Stride can differ from kernel size [OK]

Hint: Stride can be any positive int, not limited by kernel size [OK]

Common Mistakes:

• Assuming stride must be <= kernel size
• Thinking kernel size must be odd
• Believing input shape is invalid for pooling

5. You want to reduce the spatial size of a feature map from (1, 1, 10, 10) to (1, 1, 3, 3) using pooling layers. Which combination of nn.MaxPool2d or nn.AvgPool2d with kernel size and stride will achieve this output shape?

hard

A. Use nn.MaxPool2d with kernel_size=2, stride=2 twice sequentially

B. Use nn.AvgPool2d with kernel_size=4, stride=4

C. Use nn.MaxPool2d with kernel_size=3, stride=3

D. Use nn.AvgPool2d with kernel_size=5, stride=5

Solution

1. Step 1: Calculate output size for kernel_size=3, stride=3

   Output size = floor((10 - 3)/3) + 1 = floor(7/3) + 1 = 2 + 1 = 3, matching desired size.

2. Step 2: Check other options

   nn.AvgPool2d(kernel_size=4, stride=4): floor((10-4)/4)+1 = floor(6/4)+1 = 1 + 1 = 2 ≠ 3.
   nn.MaxPool2d(kernel_size=2, stride=2) twice: first floor((10-2)/2)+1 = 4 + 1 = 5, second floor((5-2)/2)+1 = 1 + 1 = 2 ≠ 3.
   nn.AvgPool2d(kernel_size=5, stride=5): floor((10-5)/5)+1 = 1 + 1 = 2 ≠ 3.

3. Final Answer:

   Use nn.MaxPool2d with kernel_size=3, stride=3 -> Option C

4. Quick Check:

   Output size = floor((input - kernel)/stride) + 1 [OK]

Hint: Output size = floor((input - kernel)/stride) + 1 [OK]

Common Mistakes:

• Ignoring floor function in output size calculation
• Assuming one pooling layer can't reduce to 3x3
• Confusing stride and kernel size effects