flexi-framework/tffb
The TensorFlow Fortran Binding (TFFB) library allows to load and evaluate Keras models directly from Fortran.
This tool helps scientists and engineers integrate trained machine learning models directly into their high-performance Fortran simulations. You can take a Keras model saved in TensorFlow's `.pb` format and feed it your simulation data, receiving predictions back to enhance your computational fluid dynamics (CFD) or other scientific calculations. This is for researchers and developers who write or maintain complex Fortran-based simulation software.
No commits in the last 6 months.
Use this if you need to deploy pre-trained deep learning models, such as turbulence models, within existing Fortran scientific simulation codes to improve their predictive capabilities without rewriting your core Fortran logic.
Not ideal if you are looking to train new machine learning models within Fortran or if your primary development environment is not Fortran.
Stars
9
Forks
3
Language
PureBasic
License
MIT
Category
Last pushed
Jun 23, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/flexi-framework/tffb"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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