Max Pool Output Calculator
Calculate the output feature map size after a max 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
Max pooling downsamples feature maps by taking the maximum value in each pooling window. The output size is computed as floor((input + 2×padding − pool_size) / stride) + 1. Standard 2×2 max pooling with stride 2 halves the spatial dimensions.
Formula
Pooling Output
output = floor((input + 2*padding - pool_size) / stride) + 1
- pool_size
- Size of the pooling window
- stride
- Step size between pooling windows
Frequently Asked Questions
Does max pooling have trainable parameters?
No — max pooling is a fixed operation with no learned parameters. It simply selects the maximum value in each window.
Why use max pooling instead of average pooling?
Max pooling preserves the strongest feature activations and provides some translation invariance. Average pooling is smoother and preferred in later layers or for global aggregation.
You might also need
- Average Pool Output CalculatorCommonly used together
- ConvTranspose Output CalculatorCommonly used together
- CNN Output Shape CalculatorCommonly used together
- CNN Parameter Count CalculatorCommonly used together
- Dense Layer Parameters CalculatorAlso in Neural Networks
- Multi-head Attention Parameters CalculatorAlso in Neural Networks