Quantization

AI and Machine Learning · Efficiency and Deployment · 2022 · quantization.yaml

Represents weights, and sometimes activations, as low-bit integers with a scale. Most of the difficulty is the handful of outlier channels whose range the rest cannot share.

Colour is the family; a dashed line is the second member of it.

Drag to pan · scroll to zoom · click a node to open it
G floating-point Floating-Point Arithmetic quantization Quantization quantization->floating-point integers plus a scale, trading range for footprint

This node

References