modern-fortran / neural-fortran
A parallel framework for deep learning
Why this job: works in the areas we cover, but does not say which job it does
What it does
- Training and inference of dense (fully connected), convolutional (1-d and 2-d),
- Stochastic gradient descent optimizers. Classic, momentum, Nesterov momentum,
- More than a dozen activation functions and their derivatives
- Loss functions and metrics. Quadratic, Mean Squared Error, Pearson Correlation etc.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 13 days ago
- Stars
- 479
- On GitHub
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.24.0
- Released 10 months ago
- Built with
- Fortran
- 98% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 67% closed
- 38 still open
- Pull requests
- 104 merged
- 10 waiting
- Releases
- 26
- 2 in the last year
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| optuna / optuna-examples | 870 | 8 days ago | MIT | No downloads |
| lightgbm-org / LightGBM | 18,970 | 2 days ago | MIT | Mac, Windows, Linux |
| Cambridge-ICCS / FTorch | 209 | 2 days ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Fortran 98%
- CMake 2%
Topics
- fortran
- parallel
- neural-network
- machine-learning
- cnn
- deep-learning
Project record
- JobOther AI tools
- StatusListed
- Commits357
- Forks110
- Watching24
- Stars in 28 days+2
- CreatedJul 29, 2018
- First seen by usNov 7, 2026
- CheckedNov 8, 2026