AI engineering glossary · Computer vision
What is GAP (global average pooling)?
Global average pooling (also called GAP): Averaging each entire feature map down to a single number, so a stack of C channels becomes a vector of length C. It replaces large fully connected layers at the end of a CNN, cutting parameters and letting the network accept varying image sizes.
Global average pooling: an example
A final 7 x 7 x 512 feature map becomes a 512-value vector that feeds one small classification layer.
Related terms
More Computer vision terms
- Grad-CAM
- Grayscale image
- Histogram equalisation
- Histogram of oriented gradients
- Homography
- Horizontal flip
- HSV colour space
- Image classification
Where you learn it
Global average pooling is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.