Cambridge-ICCS/fortran-tf-lib

A library for directly calling TensorFlow / Keras ML models from Fortran.

41
/ 100
Emerging

This tool helps scientific researchers and engineers integrate pre-trained machine learning models, specifically those developed with TensorFlow, directly into their existing Fortran applications. You can take a TensorFlow model saved in Keras's 'tf' format, feed it input data from your Fortran code, and receive the model's predictions back within Fortran. This is ideal for Fortran developers working in fields like computational science or engineering who want to embed ML inference capabilities into their high-performance Fortran simulations.

No commits in the last 6 months.

Use this if you have a TensorFlow machine learning model and need to run its predictions directly within a Fortran program without external Python calls.

Not ideal if you need to train a TensorFlow model within Fortran, or if your machine learning models are built with PyTorch instead of TensorFlow.

computational-science scientific-computing high-performance-computing numerical-simulation engineering-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

35

Forks

12

Language

Fortran

License

MIT

Last pushed

Sep 03, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Cambridge-ICCS/fortran-tf-lib"

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