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.