modern-fortran/neural-fortran
A parallel deep learning framework implemented in Fortran supporting dense, convolutional, and transformer neural networks with various optimizers and training/inference capabilities.
Not currently ranked — collecting fresh signals.
star history
neural-fortran is a parallel framework for deep learning written in Fortran. It provides implementations of dense, convolutional (1D and 2D), and transformer neural network architectures. The framework includes support for multiple optimizers including SGD, momentum variants, RMSProp, Adagrad, Adam, and AdamW. It offers various activation functions, loss functions, and metrics, and supports loading pre-trained models from Keras HDF5 files. Data-based parallelism is supported for distributed training.
Frequently asked
- What is modern-fortran/neural-fortran?
- A parallel deep learning framework implemented in Fortran supporting dense, convolutional, and transformer neural networks with various optimizers and training/inference capabilities.
- Is neural-fortran open source?
- Yes — modern-fortran/neural-fortran is open source, released under the MIT license.
- What language is neural-fortran written in?
- modern-fortran/neural-fortran is primarily written in Fortran.
- How popular is neural-fortran?
- modern-fortran/neural-fortran has 467 stars on GitHub.
- Where can I find neural-fortran?
- modern-fortran/neural-fortran is on GitHub at https://github.com/modern-fortran/neural-fortran.