/PySigma

Python implementation of the Sigma cognitive and graphical architecture grounded on PyTorch tensor processing.

Primary LanguagePythonOtherNOASSERTION

Documentation Status

PySigma

Python implementation of the Sigma cognitive and graphical architecture grounded on PyTorch tensor processing.

For documentations and discussions of design crateria, please check the wiki page of this repo.

Install

PySigma requires Python version 3.7. It is recommended that you use a conda virtual environment to install necessary packages for PySigma:

conda create -n pysigma python=3.7

To activate the conda virtual environment, type the command:

conda activate pysigma

After activating the virtual environment, you need to install required packages using pip:

pip install -r requirements.txt

Note that the requirements.txt file only includes cpu-based PyTorch. To enable GPU acceleration, you need to install the correct version that supports CUDA. Follow PyTorch's official installation guide on how to do this.

Thanks, and have fun!