https://github.com/laurentpayot/graia

An *experimental* neural network library.
https://github.com/laurentpayot/graia

ai futhark jupyter-notebook neural-network

Last synced: 4 days ago
JSON representation

An *experimental* neural network library.

• Host: GitHub
• URL: https://github.com/laurentpayot/graia
• Owner: laurentpayot
• License: mit
• Created: 2024-03-02T08:21:04.000Z (9 months ago)
• Default Branch: main
• Last Pushed: 2024-10-30T00:01:29.000Z (17 days ago)
• Last Synced: 2024-10-30T00:44:47.519Z (17 days ago)
• Topics: ai, futhark, jupyter-notebook, neural-network
• Language: Jupyter Notebook
• Homepage: https://huggingface.co/spaces/LaurentPayot/Graia
• Size: 19.2 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# 🌄 Graia

An *experimental* neural network library.

## Goals

- *Not* using a retropropagation algorithm for training. Retropropagation works pretty well but the main goal of this project is to find a *biologically plausible* training algorithm that would work using only the information available *locally* to the nodes. Current status: **Work In Progress** 👩‍💻 (70% accuracy for now). ![Learning curves](learning.png)

- Python API similar to [TensorFlow](https://www.tensorflow.org/).

Graia’s core is written in [Futhark](https://futhark-lang.org/) to leverage OpenCL for GPU acceleration.

## Online Demo

For Graia to be usable, you’ll have to use it locally with a GPA as described below.

## Prerequisites

To build Graia on a Debian/Ubuntu system, you need:

- [Futhark](https://futhark.readthedocs.io/en/stable/installation.html#installing-from-a-precompiled-snapshot)

- [Futhark FFI](https://github.com/pepijndevos/futhark-pycffi) `pip install futhark-ffi`

- OpenCL

  - Native GPU drivers are prefered but if no OpenCL device is listed with `clinfo -l` you can install `pocl-opencl-icd` (slower and sometimes buggy).

  - If missing *CL/cl.h* error, install `opencl-headers`.

  - If missing *-lOpenCL* error, create an OpenCL link: `sudo ln -s /usr/lib/x86_64-linux-gnu/libOpenCL.so.1 /usr/lib/libOpenCL.so`.

Then simply run `make` to test and compile the Futhark files to the OpenCL library used by the `Graia` Python class.

## Jupyter Notebooks

To be sure to have all the Python packages needed, [Anaconda](https://docs.anaconda.com/free/anaconda/install/linux/) is highly recommended.

- Install [Futhark FFI](https://github.com/pepijndevos/futhark-pycffi): `pip install futhark-ffi`.

- As mentioned above, Native GPU drivers are prefered but if they don’t work you can Install [PoCL](http://portablecl.org/):`conda install conda-forge::pocl`.

## TODO

- implement real boolean values instead of infinite relu slope

- Save/load model https://documen.tician.de/pyopencl/array.html#pyopencl.array.Array.get then https://numpy.org/devdocs/reference/generated/numpy.save.html

- More Futhark tests