# spkan - Sparse Convolutions with Kolmogorov-Arnold Network
### Introducing Sparse Convolutional KANs
This project extends the idea of the innovative architecture of Kolmogorov-Arnold Networks (KAN) to sparse convolutions.
view the PyPI [here](https://pypi.org/project/spkan/)
### Authors
This repository was made by:
- Mellon Zhang | meilongz@gatech.edu | [LinkedIn](https://www.linkedin.com/in/meilongzhang/)
### Credits
This repository builds upon an implementation of Convolutional-KANs which is available [here](https://github.com/AntonioTepsich/Convolutional-KANs).
This repository uses an efficient implementation of KAN which is available [here](https://github.com/Blealtan/efficient-kan).
The original implementation of KAN is available [here](https://github.com/KindXiaoming/pykan).
The original paper of the KAN is available [here](https://arxiv.org/pdf/2404.19756).
# Installation
To use as package:
currently compatible with:
Python: 3.7/3.8/3.9
CUDA: 11.3/11.8
```bash
pip install spkan
```
To edit:
Use python==3.9 torch>=2.3.0 and spconv-cu118
```bash
git clone https://github.com/meilongzhang/spkan.git
```
Raw data
{
"_id": null,
"home_page": null,
"name": "spkan",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": null,
"keywords": "kan, sparse, convolutions, kolmogorov-arnold, submanifold",
"author": null,
"author_email": "\"Mellon M. Zhang\" <meilongz@gatech.edu>",
"download_url": "https://files.pythonhosted.org/packages/d7/aa/c056f685ec8a27a7740685948c513ab73c085dd84643aaf6e4c8a770e742/spkan-0.0.2a4.tar.gz",
"platform": null,
"description": "# spkan - Sparse Convolutions with Kolmogorov-Arnold Network\n### Introducing Sparse Convolutional KANs\nThis project extends the idea of the innovative architecture of Kolmogorov-Arnold Networks (KAN) to sparse convolutions.\n\nview the PyPI [here](https://pypi.org/project/spkan/)\n\n### Authors\nThis repository was made by:\n - Mellon Zhang | meilongz@gatech.edu | [LinkedIn](https://www.linkedin.com/in/meilongzhang/)\n\n### Credits\nThis repository builds upon an implementation of Convolutional-KANs which is available [here](https://github.com/AntonioTepsich/Convolutional-KANs).\nThis repository uses an efficient implementation of KAN which is available [here](https://github.com/Blealtan/efficient-kan).\nThe original implementation of KAN is available [here](https://github.com/KindXiaoming/pykan). \nThe original paper of the KAN is available [here](https://arxiv.org/pdf/2404.19756).\n\n# Installation\nTo use as package: \ncurrently compatible with:\nPython: 3.7/3.8/3.9\nCUDA: 11.3/11.8\n\n\n```bash\npip install spkan\n```\n\nTo edit: \nUse python==3.9 torch>=2.3.0 and spconv-cu118\n\n```bash\ngit clone https://github.com/meilongzhang/spkan.git\n```\n",
"bugtrack_url": null,
"license": null,
"summary": "A drop-in replacement for sparse convolutions using Kolmogorov-Arnold Networks",
"version": "0.0.2a4",
"project_urls": {
"Homepage": "https://github.com/meilongzhang/spkan",
"Issues": "https://github.com/meilongzhang/spkan/issues"
},
"split_keywords": [
"kan",
" sparse",
" convolutions",
" kolmogorov-arnold",
" submanifold"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "bd74b83b8f7e72e96d75b6e0328c2bcde88fdcd28ae702ad30887c032a696529",
"md5": "fa71a99e28e1152328360166ea8cc9f3",
"sha256": "62da0fd73eeb16a2e8e2f491bfdd970f200c166357fdebf1c950707fcf9cffdd"
},
"downloads": -1,
"filename": "spkan-0.0.2a4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "fa71a99e28e1152328360166ea8cc9f3",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 17621,
"upload_time": "2024-09-08T04:15:11",
"upload_time_iso_8601": "2024-09-08T04:15:11.819878Z",
"url": "https://files.pythonhosted.org/packages/bd/74/b83b8f7e72e96d75b6e0328c2bcde88fdcd28ae702ad30887c032a696529/spkan-0.0.2a4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "d7aac056f685ec8a27a7740685948c513ab73c085dd84643aaf6e4c8a770e742",
"md5": "e900cac4c27a8140505bc838bd1be7ff",
"sha256": "642645dbbc8640af6bcdd1188a91b239c6fdd28f51efb8699e027641efe73ee9"
},
"downloads": -1,
"filename": "spkan-0.0.2a4.tar.gz",
"has_sig": false,
"md5_digest": "e900cac4c27a8140505bc838bd1be7ff",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 16709,
"upload_time": "2024-09-08T04:15:13",
"upload_time_iso_8601": "2024-09-08T04:15:13.171278Z",
"url": "https://files.pythonhosted.org/packages/d7/aa/c056f685ec8a27a7740685948c513ab73c085dd84643aaf6e4c8a770e742/spkan-0.0.2a4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-09-08 04:15:13",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "meilongzhang",
"github_project": "spkan",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [
{
"name": "matplotlib",
"specs": [
[
"==",
"3.6.2"
]
]
},
{
"name": "numpy",
"specs": [
[
"==",
"1.26.4"
]
]
},
{
"name": "pandas",
"specs": [
[
"==",
"2.2.2"
]
]
},
{
"name": "scikit-learn",
"specs": [
[
"==",
"1.4.2"
]
]
},
{
"name": "tqdm",
"specs": [
[
"==",
"4.66.4"
]
]
},
{
"name": "torch",
"specs": [
[
"==",
"2.3.0+cu118"
]
]
},
{
"name": "torch",
"specs": [
[
"==",
"2.3.0"
]
]
},
{
"name": "torchvision",
"specs": [
[
"==",
"0.18.0"
]
]
}
],
"lcname": "spkan"
}
JSON
