PositNN - Framework for training and inference with neural nets usings posits
-
Updated
Jan 22, 2022 - C++
PositNN - Framework for training and inference with neural nets usings posits
A Python Implementation of Posits and Quires (Drop-in replacement for IEEE Floats)
This repository contains benchmarks for Posit number format implementations, comparing performance between Posit and IEEE floating-point operations.
Add a description, image, and links to the posits topic page so that developers can more easily learn about it.
To associate your repository with the posits topic, visit your repo's landing page and select "manage topics."