Average Pool Output Calculator
Calculate the output feature map size after an average pooling operation.
Inputs
Output Size
16
Step by step
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
- Max Pool Output CalculatorCommonly used together
- CNN Output Shape CalculatorCommonly used together
- CNN Parameter Count CalculatorCommonly used together
- ConvTranspose Output CalculatorAlso in Neural Networks
- Trainable Parameters CalculatorAlso in Neural Networks
- Dense Layer Parameters CalculatorAlso in Neural Networks