quark0/darts
Differentiable architecture search for convolutional and recurrent networks
This project helps machine learning researchers efficiently design high-performing neural network architectures for tasks like image classification and language modeling. It takes dataset inputs (e.g., CIFAR-10, ImageNet, Penn Treebank) and outputs optimized convolutional or recurrent network structures. The primary users are machine learning engineers or researchers focused on deep learning model development.
3,993 stars. No commits in the last 6 months.
Use this if you need to automatically find efficient and effective neural network architectures for image or text data using limited computational resources.
Not ideal if you are looking for a pre-trained, ready-to-use model without needing to customize or search for new architectures.
Stars
3,993
Forks
844
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 03, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/quark0/darts"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
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...