evilsocket/pwnagotchi

find a way to optimize AI loading times

Aberta

#166 aberto em 5 de out. de 2019

 (6 comentários) (0 reação) (1 responsável)JavaScript (978 forks)batch import
enhancementhacktoberfesthelp wantedidea

Métricas do repositório

Stars
 (6.243 estrelas)
Métricas de merge de PR
 (Métricas PR pendentes)

Description

TensorFlow takes minutes to import on a Raspberry Pi Zero W and that's probably because of the huge .so file with native primitives it has to load, among other things. Given the nature of the project, that stuff is imported only once, so caching it in memory wouldn't speed things up. Switching frameworks is not feasible, unless we have the same exact features (unlikely given that stable-baselines is TF based). For instance, there's no stable-baselines port for TF-lite.

Guia do colaborador