Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A parallel framework for deep learning
| Date | Stars |
|---|---|
| 2026-07-31 | 469 |
| 2026-08-01 | 469 |
| 2026-08-06 | 469 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# neural-fortran A parallel framework for deep learning. Read the paper [here](https://arxiv.org/abs/1902.06714). * [Features](https://github.com/modern-fortran/neural-fortran#features) * [Getting started](https://github.com/modern-fortran/neural-fortran#getting-started) - [Building with fpm](https://github.com/modern-fortran/neural-fortran#building-with-fpm) - [Building with CMake](https://github.com/modern-fortran/neural-fortran#building-with-cmake) * [Examples](https://github.com/modern-fortran/neural-fortran#examples) * [API documentation](https://github.com/modern-fortran/neural-fortran#api-documentation) * [Contributing](https://github.com/modern-fortran/neural-fortran#contributing) * [Acknowledgement](https://github.com/modern-fortran/neural-fortran#acknowledgement) * [Related projects](https://github.com/modern-fortran/neural-fortran#related-projects) ## Features * Training and inference of dense (fully connected), convolutional (1-d and 2-d), and transformer neural networks * Stochastic gradient descent optimizers: Classic, momentum, Nesterov momentum, RMSProp, Adagrad, Adam, AdamW * More than a dozen activation functions and their derivatives * Loss functions and metrics: Quadratic, Mean Squared Error, Pearson Correlation etc. * Data-based parallelism * Loading dense and convolutional models from Keras HDF5 (.h5) files (see the [nf-keras-hdf5](https://github.com/neural-fortran/nf-keras-hdf5) add-on) ### Available layers | Layer type | Constructor name | Supported input layers | Rank of output array | Forward pass | Backward pass | |------------|------------------|------------------------|----------------------|--------------|---------------| | Input | `input` | n/a | 1, 2, 3 | n/a | n/a | | Embedding | `embedding` | n/a | 2 | ✅ | ✅ | | Dense (fully-connected) | `dense` | `input`, `dense`, `dropout`, `flatten` | 1 | ✅ | ✅ | | Dropout | `dropout` | `dense`, `flatten`, `input1d` | 1 | ✅ | ✅ | | Locally connected (2-d) | `locally_connected` | `input`, `locally_connected`, `conv`, `avgpool`, `maxpool`, `reshape` | 2 | ✅ | ✅ | | Convolutional (1-d and 2-d) | `conv` | `input`, `conv`, `avgpool`, `maxpool`, `reshape` | 2, 3 | ✅ | ✅ | | Average pooling (1-d and 2-d) | `avgpool` | `input`, `conv`, `avgpool`, `maxpool`, `reshape` | 2, 3 | ✅ | ✅ | | Max-pooling (1-d and 2-d) | `maxpool` | `input`, `conv`, `avgpool`, `maxpool`, `reshape` | 2, 3 | ✅ | ✅ | | Linear (2-d) | `linear2d` | `input`, `layernorm`, `linear2d`, `self_attention` | 2 | ✅ | ✅ | | Self-attention | `self_attention` | `input`, `layernorm`, `linear2d`, `self_attention` | 2 | ✅ | ✅ | | Layer Normalization | `layernorm` | `linear2d`, `self_attention` | 2 | ✅ | ✅ | | Flatten | `flatten` | `input`, `conv`, `avgpool`, `maxpool`, `reshape` | 1 | ✅ | ✅ | | Reshape (1-d to 2-d or 3-d) | `reshape` | `dense`, `dropout`, `flatten`, `input` | 2, 3 | ✅ | ✅ | ## Getting started Get the code: ``` git clone https://github.com/modern-fortran/neural-fortran cd neural-fortran ``` ### Dependencies Required dependencies are: * A Fortran compiler * [fpm](https://github.com/fortran-lang/fpm) or [CMake](https://cmake.org) to build the code Optional dependencies are: * OpenCoarrays (for parallel execution with GFortran) * BLAS, MKL, or similar (for offloading `matmul` and `dot_product` calls) * curl (for downloading testing and example datasets) Compilers tested include: * flang-new 20.0.0 * gfortran 13.2.0, 14.0.1 * ifort 2021.13.1 * ifx 2024.2.1 ### Building with fpm #### Building in serial mode With gfortran, the following will create an optimized build of neural-fortran: ``` fpm build --profile release ``` #### Building in parallel mode If you use GFortran and want to run neural-fortran in parallel, you must first install [OpenCoarrays](https://github.com/sourceryinstitute/OpenCoarrays). Once installed, use the compiler wrappers `caf` and `cafrun` to build and execute in parallel, respectively: ``` fpm build --compiler caf --profile release --flag "-cp
Excerpt of 10,683 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:2473355621c704bd, topic:deep-learning, topic:neural-network