HayeonLee/MetaD2A
Official PyTorch implementation of "Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets" (ICLR 2021)
This project helps machine learning practitioners efficiently find high-performing neural network architectures for their specific image datasets. You input your image dataset, and it quickly generates and recommends the most suitable neural network design, which you can then use for tasks like image classification. It's designed for researchers, MLOps engineers, or data scientists working on computer vision problems who need to optimize model performance without extensive manual experimentation.
No commits in the last 6 months.
Use this if you need to rapidly discover the best neural network architecture for a new or specific image dataset, significantly reducing the time and computational resources typically required for this process.
Not ideal if your primary goal is to train a model from scratch with a pre-defined architecture, rather than searching for an optimal one.
Stars
64
Forks
11
Language
Python
License
MIT
Category
Last pushed
Aug 05, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/HayeonLee/MetaD2A"
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
IDEALLab/EngiBench
Benchmarks for automated engineering design
AI-team-UoA/pyJedAI
An open-source library that leverages Python’s data science ecosystem to build powerful...