Skip to content
Calcrivo

Average Pool Output Calculator

Calculate the output feature map size after an average pooling operation.

Inputs

Output Size

16

Step by step

  1. Output = floor((input + 2×pad − pool) / stride) + 1

    floor((32 + 2×0 − 2) / 2) + 1

    = 16

How it works

Average pooling computes the mean value within each pooling window, providing smoother downsampling than max pooling. The output size formula is identical to max pooling: floor((input + 2×padding − pool_size) / stride) + 1.

Formula

Avg Pool Output

output = floor((input + 2*padding - pool_size) / stride) + 1

pool_size
Size of the averaging window

Frequently Asked Questions

When is average pooling preferred?

Average pooling is preferred for global aggregation (Global Average Pooling before classifiers), in tasks where all feature values contribute (not just peaks), and in some GAN architectures.

What is Global Average Pooling?

GAP uses pool_size equal to the spatial dimension, collapsing each channel to a single number. It replaces fully connected layers at the end of CNNs, reducing overfitting.

You might also need