FirasBDarwish / ConvKAN3D

Python package for 3D convolutional layers using Kolmogorov-Arnold Network (KAN)

ConvKAN

Kolmogorov-Arnold Networks (KANs) meet 3D Convolutional Layers (Conv3d)
Read the KANs Paper »

· Report Bug · Request Feature

Table of Contents

1. About The Project
2. Getting Started
   • Installation
3. Roadmap
4. License
5. Authors
6. Acknowledgements

About The Project

Python package for 3D convolutional layers using Kolmogorov-Arnold Networks (KANs). I am new to packaging and distributing software in this manner--especially ML packages--so please go easy on me.

Getting Started

Using this package should be fairly simple!

Installation

   $ pip install ConvKAN3D

Once you've installed the package and once in Python, make sure to import:

   from ConvKAN3D.ConvKAN3D import effConvKAN3D

Now, you're all good to use effConvKAN3D just as you would with Conv3d (with some added hyperparameters for the underlying KAN module being used).

Roadmap

See the open issues for a list of proposed features (and known issues).

License

Distributed under the GNU General Public License. See LICENSE for more information.

Authors

firasbdarwish - [e-mail]

Project Link: https://github.com/FirasBDarwish/ConvKAN3D

Acknowledgements

• Official KAN Repo
• AwesomeKAN Repo
• EfficentKAN Implementation
• KAN-Conv2D Implementation that outlines how to easily apply KAN implementations to convolutional layers

Thank you