Condensa has built-in compression operators. To recover any accuracy lost during compression, Condensa uses a constrained optimization and Augmented Lagrangian-based algorithm as the optimizer. Source Code https://github.com/NVLabs/condensa API Documentation https://nvlabs.github.io/condensa/
-
-
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Our Programming System for Model Compression https://github.com/NVlabs/condensa was well received at Systems for ML
#Sysml at#NeurIPS2019, we would like to thank@slbird@DanCrankshaw@sidsen1@mejoeyg Aparna Lakshmi and other for bring together experts working at the crossroads of ML+Syspic.twitter.com/o7iuYO5qdx
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.