Ren-Research/OneProxy
[SIGMETRICS 2022] One Proxy Device Is Enough for Hardware-Aware Neural Architecture Search
This project helps machine learning engineers and researchers efficiently design neural network architectures that perform well on specific hardware devices. It takes information about different neural network designs and various target hardware devices, then outputs optimized network architectures that are fast and efficient on those devices. This is for professionals building and deploying machine learning models on diverse hardware like mobile phones or embedded systems.
No commits in the last 6 months.
Use this if you need to find the best neural network architecture for a variety of different hardware platforms without spending a huge amount of time evaluating each design on every single device.
Not ideal if you are working with a single target device and simple neural network architectures where exhaustive search is already feasible.
Stars
13
Forks
—
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Nov 03, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Ren-Research/OneProxy"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pykt-team/pykt-toolkit
pyKT: A Python Library to Benchmark Deep Learning based Knowledge Tracing Models
microsoft/archai
Accelerate your Neural Architecture Search (NAS) through fast, reproducible and modular research.
google-research/morph-net
Fast & Simple Resource-Constrained Learning of Deep Network Structure
AI-team-UoA/pyJedAI
An open-source library that leverages Python’s data science ecosystem to build powerful...
IDEALLab/EngiBench
Benchmarks for automated engineering design