FEDOT automates machine learning model development through its modeling framework.
Open source
24 alternativesneural-fortran
neural-fortran provides a parallel framework for deep learning in Fortran.
About neural-fortran
neural-fortran is an open-source Fortran repository that provides a parallel framework for deep learning. It supports training and inference for dense, 1-D and 2-D convolutional, and transformer neural networks, with stochastic gradient descent optimizers, activation functions, loss functions, and metrics. The code can be built with fpm or CMake. Parallel execution with GFortran requires OpenCoarrays, and BLAS or MKL offloading is currently available only with gfortran. Dense and convolutional models can be loaded from Keras HDF5 files using the nf-keras-hdf5 add-on.
Key features
- Trains and runs inference for dense, 1-D/2-D convolutional, and transformer neural networks
- Provides stochastic gradient descent optimizers including Adam, AdamW, RMSProp, Adagrad, and momentum
- Includes more than a dozen activation functions and their derivatives
- Supports loss functions and metrics such as quadratic, mean squared error, Pearson correlation
- Uses data-based parallelism; parallel GFortran builds require OpenCoarrays
- Loads dense and convolutional models from Keras HDF5 via nf-keras-hdf5 add-on
Best for: Fortran developers and researchers who need to build, train, or run inference for neural networks in Fortran and can manage compiler and parallel-runtime setup.
Good for
- Open-source Fortran framework for deep learning
- Includes a range of optimizers, activation functions, loss functions, and metrics
- Supports data-based parallelism and has been tested with gfortran, flang-new, ifort, and ifx
Watch out for
- Parallel execution with GFortran requires OpenCoarrays
- The BLAS or MKL offloading option is currently available only with gfortran
- Loading Keras HDF5 models requires the nf-keras-hdf5 add-on
neural-fortran at a glance
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
neural-fortran alternatives
Tools and sites you could use instead, ranked by how closely they match.
Detecto supports building and training computer vision models with the PyTorch machine learning framework.
Open source
24 alternatives
Katib automates machine learning on Kubernetes, including hyperparameter tuning and neural architecture search.
Open source
24 alternatives
PyTorch Geometric Temporal provides models and tools for spatiotemporal signal processing with neural learning.
Open source
24 alternatives
mgl provides a machine learning library in Common Lisp, including neural networks and Gaussian processes.
Open source
24 alternatives
AutoGL provides automated graph learning through a machine learning framework and toolkit.
Open source
24 alternativesPopular in ML Training & Optimization
Well-known listings from the same topic.
Edwardedwardlib.orgAerosolveaerosolve.airbnb.techDataturedatature.ioTogether AItogether.aiOptunaoptuna.orgCatBoostcatboost.ai
neural-fortran FAQ
What neural network types does neural-fortran support?
It supports training and inference of dense, convolutional (1-D and 2-D), and transformer neural networks.
How can neural-fortran be built and run in parallel?
It can be built with fpm or CMake. Parallel execution with GFortran requires OpenCoarrays, using the caf and cafrun compiler wrappers.
Can neural-fortran load Keras models?
Dense and convolutional models can be loaded from Keras HDF5 (.h5) files via the nf-keras-hdf5 add-on.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.