Library for geometric algebra-based attention mechanisms
Project description
Introduction
This is a library in development for implementing geometric algebra attention mechanisms (as detailed in the paper Geometric Algebra Attention Networks for Small Point Clouds in tensorflow, keras, pytorch, and jax.
Installation
The latest tagged version of geometric-algebra-attention
is
available on PyPI for installation via pip:
$ pip install geometric-algebra-attention
Alternatively, install the package from source:
$ git clone https://github.com/klarh/geometric_algebra_attention
$ pip install ./geometric_algebra_attention
Documentation
The documentation is available as standard sphinx documentation:
$ cd doc
$ pip install -r requirements.txt
$ make html
Automatically-built documentation is available at https://geometric-algebra-attention.readthedocs.io .
Examples
Jupyter notebook examples for various backends are available in the
examples
directory of the source repository.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file geometric_algebra_attention-0.4.0.tar.gz
.
File metadata
- Download URL: geometric_algebra_attention-0.4.0.tar.gz
- Upload date:
- Size: 24.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.1 CPython/3.8.10
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 9810655bd8d25816dc8d7eef472c2549273c3b3ca142876aebe56e71b7dd38a3 |
|
MD5 | b1a128217523b9f0bdaaa5211c7edf0f |
|
BLAKE2b-256 | 6b961a13fd01e8c9ef032c17513a9b60f0a09cbad2745380b6f634e52def345e |
File details
Details for the file geometric_algebra_attention-0.4.0-py3-none-any.whl
.
File metadata
- Download URL: geometric_algebra_attention-0.4.0-py3-none-any.whl
- Upload date:
- Size: 53.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.1 CPython/3.8.10
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 7ee2c9222fe171e270160f80ef66008bd7de939c0a79fc0b10c0bf386e98ddde |
|
MD5 | 19a23f873c5b3be56d9a64f9fe164658 |
|
BLAKE2b-256 | 8ee17c4f07041b65981bd58e84455685fd531af950a898275431dec8556e207e |