nn.MaxPool2d and nn.AvgPool2d in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What does nn.MaxPool2d do in a neural network?

nn.MaxPool2d takes the largest value from each small region (window) of the input image or feature map. It helps reduce size and keeps the strongest features.

beginner

How does nn.AvgPool2d differ from nn.MaxPool2d?

nn.AvgPool2d calculates the average value in each small region instead of the maximum. It smooths the features rather than picking the strongest one.

beginner

What is the role of the kernel_size parameter in nn.MaxPool2d and nn.AvgPool2d?

kernel_size sets the size of the window that moves over the input to pool values. For example, kernel_size=2 means a 2x2 window.

intermediate

Why do we use pooling layers like nn.MaxPool2d in convolutional neural networks?

Pooling layers reduce the size of data, making the model faster and less likely to overfit. Max pooling keeps important features by selecting the strongest signals.

intermediate

What happens if you set stride smaller than kernel_size in nn.MaxPool2d?

The pooling windows will overlap, which means some input values are pooled multiple times. This can give smoother downsampling but increases computation.

What does nn.MaxPool2d do with each pooling window?

A Calculates the average value

B Sums all values

C Selects the maximum value

D Selects the minimum value

nn.MaxPool2d selects the maximum value in each window to keep the strongest feature.

Which parameter controls the size of the pooling window in nn.AvgPool2d?

A kernel_size

B stride

C padding

D dilation

kernel_size sets the size of the window that moves over the input for pooling.

What is the main effect of applying pooling layers in CNNs?

A Reduce data size and keep important features

B Add noise to data

C Increase data size

D Convert images to grayscale

Pooling reduces data size and keeps important features, helping the model run faster and generalize better.

If stride is equal to kernel_size in nn.MaxPool2d, what happens?

A Pooling windows overlap

B Pooling windows do not overlap

C Pooling windows skip input values

D Pooling windows double in size

When stride equals kernel_size, windows move without overlapping, covering the input evenly.

Which pooling method smooths features by averaging values?

A nn.BatchNorm2d

B nn.MaxPool2d

C nn.Conv2d

D nn.AvgPool2d

nn.AvgPool2d calculates the average in each window, smoothing the features.

Explain in your own words how nn.MaxPool2d and nn.AvgPool2d work and why they are useful in CNNs.

Think about how these layers look at small parts of the image and summarize them.

Describe the effect of changing kernel_size and stride in nn.MaxPool2d on the output size and feature selection.

Consider how the window moves and how big it is.

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