AI engineering glossary · Computer vision
What is inception module?
Inception module (also called GoogLeNet): A building block that applies several convolutions of different sizes (1 x 1, 3 x 3, 5 x 5) and pooling in parallel and joins their outputs, letting the network capture patterns at multiple scales. 1 x 1 convolutions keep the cost down.
Inception module: an example
GoogLeNet stacked Inception modules to reach strong accuracy with far fewer parameters than VGG.
Related terms
More Computer vision terms
- Instance segmentation
- Intersection over union
- Mask R-CNN
- Max pooling
- Median filter
- Mixup
- MobileNet
- Morphological operations
Where you learn it
Inception module is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.