jhagnberger/smart
Official PyTorch implementation of the SMART model.
This tool helps aerodynamic engineers, automotive designers, and aerospace engineers quickly simulate airflow around objects. You input a 3D geometry (like a car or wing) and optionally, specific simulation parameters such as angle of attack or Mach number. The tool outputs predictions of airflow characteristics on the object's surface and in the surrounding volume, allowing for rapid analysis without traditional meshing.
Use this if you need to perform fast, mesh-free aerodynamic simulations directly from raw 3D geometries to get quick insights into fluid dynamics around complex shapes.
Not ideal if you require traditional CFD methods, very high-fidelity simulations that demand detailed mesh control, or prefer using commercial simulation software.
Stars
10
Forks
2
Language
Python
License
—
Category
Last pushed
Jan 31, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jhagnberger/smart"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MaximeVandegar/Papers-in-100-Lines-of-Code
Implementation of papers in 100 lines of code.
kk7nc/RMDL
RMDL: Random Multimodel Deep Learning for Classification
OML-Team/open-metric-learning
Metric learning and retrieval pipelines, models and zoo.
miguelvr/dropblock
Implementation of DropBlock: A regularization method for convolutional networks in PyTorch.
PaddlePaddle/models
Officially maintained, supported by PaddlePaddle, including CV, NLP, Speech, Rec, TS, big models...