VITA-Group/WeakNAS
[NeurIPS 2021] “Stronger NAS with Weaker Predictors“, Junru Wu, Xiyang Dai, Dongdong Chen, Yinpeng Chen, Mengchen Liu, Ye Yu, Zhangyang Wang, Zicheng Liu, Mei Chen and Lu Yuan
This project helps machine learning engineers efficiently design high-performing neural network architectures. It takes in predefined search spaces (like NAS-Bench-101, NAS-Bench-201, or MobileNet) and outputs optimized network configurations. The ideal end-user is a deep learning researcher or practitioner focused on neural architecture search.
No commits in the last 6 months.
Use this if you need to find the best-performing neural network architectures for image classification tasks with significantly reduced search time.
Not ideal if you are a beginner in deep learning or do not have experience with neural architecture search methodologies.
Stars
27
Forks
6
Language
Jupyter Notebook
License
—
Category
Last pushed
Sep 23, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/VITA-Group/WeakNAS"
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