BerkeleyLab/fiats
A deep learning library for use in high-performance computing applications in modern Fortran
This project helps scientists and engineers working with complex computational models by training and deploying neural network 'surrogate models'. You provide scientific data and the tool generates a trained neural network that can quickly make predictions, dramatically speeding up simulations. This is designed for researchers and practitioners in computational science who need faster, more efficient model execution.
Use this if you need to accelerate computationally intensive scientific simulations by replacing parts of them with high-performance neural network models.
Not ideal if you are not working with Fortran or if your primary need is general-purpose deep learning outside of high-performance scientific computing.
Stars
70
Forks
28
Language
Fortran
License
—
Category
Last pushed
Mar 10, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/BerkeleyLab/fiats"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
mlverse/torch
R Interface to Torch
modern-fortran/neural-fortran
A parallel framework for deep learning
Beliavsky/Fortran-code-on-GitHub
Directory of Fortran codes on GitHub, arranged by topic
Cambridge-ICCS/FTorch
A library for directly calling PyTorch ML models from Fortran.
NVIDIA/TorchFort
An Online Deep Learning Interface for HPC programs on NVIDIA GPUs