evilsocket/pwnagotchi

find a way to optimize AI loading times

Open

#166 opened on Oct 5, 2019

View on GitHub
 (6 comments) (0 reactions) (1 assignee)JavaScript (6,243 stars) (978 forks)batch import
enhancementhacktoberfesthelp wantedidea

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.

Contributor guide

Tech stack
pythontensorflow
Domain
machine learningperformance
Issue type
performance
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
5
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
over 1 week
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
mostly clear
Prerequisites
Python programmingFamiliarity with TensorFlowRaspberry Pi experienceKnowledge of shared libraries
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
10
Research direction
Investigate the TensorFlow import process on Raspberry Pi Zero W. Profile the import to identify which .so files are loaded and their sizes. Consider alternatives such as TensorFlow Lite or precompiled binaries. Look into reducing the number of loaded modules or lazy loading.