CompRhys/aviary

The Wren sits on its Roost in the Aviary.

52
/ 100
Established

Unified framework implementing three complementary deep learning architectures for materials property prediction: coordinate-free models (Roost, Wren, WrenFormer) that require only elemental composition, and structure-based CGCNN that leverages pymatgen-parsed crystal structures. Supports both CLI and Python APIs for training, evaluation, and inference across regression and classification tasks with configurable loss functions and robustness options on materials datasets in CSV/JSON formats.

No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

61

Forks

13

Language

Python

License

MIT

Last pushed

Jan 06, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/CompRhys/aviary"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.