[](https://pypi.org/project/sinabs/)
[](https://sinabs.readthedocs.io)
[](https://codecov.io/gh/synsense/sinabs)
[](https://pepy.tech/project/sinabs)
[](https://discord.gg/V6FHBZURkg)
Sinabs (Sinabs Is Not A Brain Simulator) is a python library for the development and implementation of Spiking Convolutional Neural Networks (SCNNs).
The library implements several layers that are `spiking` equivalents of CNN layers.
In addition it provides support to import CNN models implemented in torch conveniently to test their `spiking` equivalent implementation.
This project is managed by SynSense (former aiCTX AG).
The `sinabs-dynapcnn` was incorporated to this project, and it enables porting sinabs models to chips and dev-kits with DYNAP-CNN technology.
Installation
------------
For the stable release on the main branch:
```
pip install sinabs
```
or (thanks to [@Tobias-Fischer](https://github.com/Tobias-Fischer))
```
conda install -c conda-forge sinabs
```
For the latest pre-release on the develop branch that passed the tests:
```
pip install sinabs --pre
```
The package has been tested on the following configurations
[](https://github.com/synsense/sinabs)
Documentation and Examples
--------------------------
[https://sinabs.readthedocs.io/](https://sinabs.readthedocs.io/)
Questions? Feedback?
--------------------
Please join us on the [#sinabs Discord channel](https://discord.gg/V6FHBZURkg)!
- If you would like to report bugs or push any changes, you can do this on our [github repository](https://github.com/synsense/sinabs/issues).
License
-------
Sinabs is published under AGPL v3.0. See the LICENSE file for details.
Contributing to Sinabs
------------------------
Checkout the [contributing](https://sinabs.readthedocs.io/en/develop/about/contributing.html) page for more info.
Citation
--------
In case you find this software library useful for your work please consider citing it as follows:
```
@software{sinabs,
author = {Sheik, Sadique and Lenz, Gregor and Bauer, Felix and Kuepelioglu, Nogay },
doi = {10.5281/zenodo.8385545},
license = {AGPL-3.0},
title = {{SINABS: A simple Pytorch based SNN library specialised for Speck}},
url = {https://github.com/synsense/sinabs}
}
```
Raw data
{
"_id": null,
"home_page": null,
"name": "sinabs",
"maintainer": null,
"docs_url": null,
"requires_python": null,
"maintainer_email": null,
"keywords": "spiking neural networks, machine learning, SNN, DYNAPCNN, Speck",
"author": "SynSense (formerly AiCTX)",
"author_email": "sinabs@synsense.ai",
"download_url": "https://files.pythonhosted.org/packages/f8/af/f204ffd7dc6df3a6d41f7acb743e9eed3ffee12f6a54d28df4921ac6fe46/sinabs-2.0.2.tar.gz",
"platform": null,
"description": "[](https://pypi.org/project/sinabs/)\n[](https://sinabs.readthedocs.io)\n[](https://codecov.io/gh/synsense/sinabs)\n[](https://pepy.tech/project/sinabs)\n[](https://discord.gg/V6FHBZURkg)\n\n\nSinabs (Sinabs Is Not A Brain Simulator) is a python library for the development and implementation of Spiking Convolutional Neural Networks (SCNNs).\nThe library implements several layers that are `spiking` equivalents of CNN layers.\nIn addition it provides support to import CNN models implemented in torch conveniently to test their `spiking` equivalent implementation.\nThis project is managed by SynSense (former aiCTX AG).\n\nThe `sinabs-dynapcnn` was incorporated to this project, and it enables porting sinabs models to chips and dev-kits with DYNAP-CNN technology.\n\n\nInstallation\n------------\nFor the stable release on the main branch:\n```\npip install sinabs\n```\nor (thanks to [@Tobias-Fischer](https://github.com/Tobias-Fischer))\n```\nconda install -c conda-forge sinabs\n```\n\nFor the latest pre-release on the develop branch that passed the tests:\n```\npip install sinabs --pre\n```\nThe package has been tested on the following configurations\n[](https://github.com/synsense/sinabs)\n\n\nDocumentation and Examples\n--------------------------\n[https://sinabs.readthedocs.io/](https://sinabs.readthedocs.io/)\n\nQuestions? Feedback?\n--------------------\nPlease join us on the [#sinabs Discord channel](https://discord.gg/V6FHBZURkg)!\n\n- If you would like to report bugs or push any changes, you can do this on our [github repository](https://github.com/synsense/sinabs/issues).\n\nLicense\n-------\nSinabs is published under AGPL v3.0. See the LICENSE file for details.\n\n\nContributing to Sinabs\n------------------------\nCheckout the [contributing](https://sinabs.readthedocs.io/en/develop/about/contributing.html) page for more info.\n\n\nCitation\n--------\n\nIn case you find this software library useful for your work please consider citing it as follows:\n\n```\n@software{sinabs,\nauthor = {Sheik, Sadique and Lenz, Gregor and Bauer, Felix and Kuepelioglu, Nogay },\ndoi = {10.5281/zenodo.8385545},\nlicense = {AGPL-3.0},\ntitle = {{SINABS: A simple Pytorch based SNN library specialised for Speck}},\nurl = {https://github.com/synsense/sinabs}\n}\n```\n\n\n\n",
"bugtrack_url": null,
"license": "GNU AGPLv3",
"summary": "SynSense Spiking Neural Network simulator for deep neural networks (DNNs).",
"version": "2.0.2",
"project_urls": {
"Documentation": "https://readthedocs.org/projects/sinabs/",
"Source code": "https://github.com/synsense/sinabs"
},
"split_keywords": [
"spiking neural networks",
" machine learning",
" snn",
" dynapcnn",
" speck"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "8555a26781ebe57d3f54a18daa8e8ae97329f5b2f7326df9925c66a83db6d5ad",
"md5": "8229125da270470763cd41e8295dd7cb",
"sha256": "ff03f97e3504d73f0dcdb25b2d481a39350cac58b1913afca6482814dc5f5c30"
},
"downloads": -1,
"filename": "sinabs-2.0.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "8229125da270470763cd41e8295dd7cb",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 107613,
"upload_time": "2025-01-23T16:37:21",
"upload_time_iso_8601": "2025-01-23T16:37:21.076242Z",
"url": "https://files.pythonhosted.org/packages/85/55/a26781ebe57d3f54a18daa8e8ae97329f5b2f7326df9925c66a83db6d5ad/sinabs-2.0.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "f8aff204ffd7dc6df3a6d41f7acb743e9eed3ffee12f6a54d28df4921ac6fe46",
"md5": "ecd38dcab4a2168df05473f8b7215740",
"sha256": "f4d0cc15c3ba09cb27e9c48d61ffe7a3f1b187e976f4633210014bb919c23887"
},
"downloads": -1,
"filename": "sinabs-2.0.2.tar.gz",
"has_sig": false,
"md5_digest": "ecd38dcab4a2168df05473f8b7215740",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 4457972,
"upload_time": "2025-01-23T16:37:23",
"upload_time_iso_8601": "2025-01-23T16:37:23.368617Z",
"url": "https://files.pythonhosted.org/packages/f8/af/f204ffd7dc6df3a6d41f7acb743e9eed3ffee12f6a54d28df4921ac6fe46/sinabs-2.0.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-01-23 16:37:23",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "synsense",
"github_project": "sinabs",
"travis_ci": false,
"coveralls": true,
"github_actions": true,
"requirements": [
{
"name": "pbr",
"specs": []
},
{
"name": "numpy",
"specs": []
},
{
"name": "torch",
"specs": [
[
">=",
"1.8"
]
]
},
{
"name": "nir",
"specs": []
},
{
"name": "nirtorch",
"specs": []
},
{
"name": "samna",
"specs": [
[
">=",
"0.33"
]
]
}
],
"lcname": "sinabs"
}
JSON
