sinabs
A deep learning library for spiking neural networks which is based on PyTorch, focuses on fast training and supports inference on neuromorphic hardware.
Science Score: 67.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
✓DOI references
Found 1 DOI reference(s) in README -
○Academic publication links
-
✓Committers with academic emails
2 of 28 committers (7.1%) from academic institutions -
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (17.4%) to scientific vocabulary
Keywords
Keywords from Contributors
Repository
A deep learning library for spiking neural networks which is based on PyTorch, focuses on fast training and supports inference on neuromorphic hardware.
Basic Info
- Host: GitHub
- Owner: synsense
- License: apache-2.0
- Language: Python
- Default Branch: develop
- Homepage: https://sinabs.readthedocs.io
- Size: 18.2 MB
Statistics
- Stars: 104
- Watchers: 5
- Forks: 13
- Open Issues: 43
- Releases: 24
Topics
Metadata Files
README.md
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)
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
Documentation and Examples
https://sinabs.readthedocs.io/
Questions? Feedback?
Please join us on the #sinabs Discord channel!
- If you would like to report bugs or push any changes, you can do this on our github repository.
License
Sinabs is published under Apache v2.0. See the LICENSE file for details.
Contributing to Sinabs
Checkout the contributing 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 = {Apache-2.0},
title = {{SINABS: A simple Pytorch based SNN library specialised for Speck}},
url = {https://github.com/synsense/sinabs}
}
Owner
- Name: SynSense
- Login: synsense
- Kind: organization
- Location: Zurich Switzerland
- Website: https://synsense.ai/
- Repositories: 13
- Profile: https://github.com/synsense
Citation (CITATION.cff)
# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!
cff-version: 1.2.0
title: >-
SINABS: A simple Pytorch based SNN library specialised for
Speck
message: >-
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 The project is hosted
at https://github.com/synsense/sinabs
type: software
authors:
- given-names: Sadique
family-names: Sheik
email: sadique.sheik@synsense.ai
affiliation: SynSense AI
orcid: 'https://orcid.org/0000-0003-0302-8511'
- given-names: 'Gregor '
family-names: Lenz
affiliation: 'SynSense AG, Neurobus'
- given-names: Felix
family-names: Bauer
email: felix.bauer@synsense.ai
affiliation: SynSense AG
- given-names: 'Nogay '
family-names: Kuepelioglu
affiliation: SynSense AG
keywords:
- spiking Neural Networks
- pytorch
- Bapckpropagation Through Time
- Neuromorphic Engineering
- Computational Efficiency
- Speck
license: Apache-2.0
doi: 10.5281/zenodo.8385545
url: https://github.com/synsense/sinabs
GitHub Events
Total
- Create event: 17
- Release event: 7
- Issues event: 45
- Watch event: 20
- Delete event: 9
- Issue comment event: 25
- Push event: 167
- Pull request event: 23
- Pull request review comment event: 107
- Pull request review event: 108
- Fork event: 5
Last Year
- Create event: 17
- Release event: 7
- Issues event: 45
- Watch event: 20
- Delete event: 9
- Issue comment event: 25
- Push event: 167
- Pull request event: 23
- Pull request review comment event: 107
- Pull request review event: 108
- Fork event: 5
Committers
Last synced: 8 months ago
Top Committers
| Name | Commits | |
|---|---|---|
| Sadique Sheik | s****k@s****i | 425 |
| Gregor Lenz | g****z@s****i | 331 |
| Felix Bauer | f****r@a****i | 200 |
| Martino Sorbaro | m****o@p****t | 102 |
| nogay.kuepelioglu | n****u@s****i | 82 |
| Yalun_Hu | y****u@s****i | 82 |
| Vanessa Leite | v****e@s****i | 78 |
| Martino Sorbaro | m****o@e****k | 74 |
| Sadique Sheik | s****k@a****m | 18 |
| qian.liu | q****u@a****m | 15 |
| yannan xing | y****g@s****i | 15 |
| Felix Bauer | f****r@s****i | 11 |
| shynuie | y****n@s****i | 8 |
| Nogay Küpelioğlu | k****n@m****r | 7 |
| Massimo Bortone | m****e@a****i | 5 |
| Willian-Girao | w****o@g****m | 4 |
| yijing.lv | y****v@s****i | 2 |
| qian.liu | q****u@a****i | 2 |
| martino.sorbaro | m****o@a****i | 2 |
| li.bo | b****i@s****i | 1 |
| felix.bauer | f****r@a****m | 1 |
| dacian.herbei | d****i@s****i | 1 |
| Roberto Cattaneo | r****o@s****i | 1 |
| Carsten Nielsen | c****n@a****m | 1 |
| edghyhdz | e****z@h****m | 1 |
| Dylan Perdigão | 3****o | 1 |
| allan | a****n@1****m | 1 |
| MurphyWu | w****x@1****m | 1 |
Committer Domains (Top 20 + Academic)
Issues and Pull Requests
Last synced: 6 months ago
All Time
- Total issues: 64
- Total pull requests: 40
- Average time to close issues: 7 months
- Average time to close pull requests: 18 days
- Total issue authors: 11
- Total pull request authors: 4
- Average comments per issue: 0.5
- Average comments per pull request: 0.6
- Merged pull requests: 26
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 27
- Pull requests: 21
- Average time to close issues: 4 days
- Average time to close pull requests: about 4 hours
- Issue authors: 7
- Pull request authors: 2
- Average comments per issue: 0.07
- Average comments per pull request: 0.14
- Merged pull requests: 13
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
- ssinhaleite (22)
- bauerfe (15)
- biphasic (9)
- sheiksadique (8)
- mihneasteiu (4)
- fabio-innatera (1)
- MANUPRIYASINGH (1)
- mrontio (1)
- cowolff (1)
- crashkk (1)
- hovren (1)
Pull Request Authors
- ssinhaleite (23)
- bauerfe (8)
- sheiksadique (7)
- mrontio (2)
Top Labels
Issue Labels
Pull Request Labels
Packages
- Total packages: 2
-
Total downloads:
- pypi 856 last-month
-
Total dependent packages: 3
(may contain duplicates) -
Total dependent repositories: 2
(may contain duplicates) - Total versions: 267
- Total maintainers: 3
proxy.golang.org: github.com/synsense/sinabs
- Documentation: https://pkg.go.dev/github.com/synsense/sinabs#section-documentation
- License: apache-2.0
-
Latest release: v3.0.3+incompatible
published 7 months ago
Rankings
pypi.org: sinabs
SynSense Spiking Neural Network simulator for deep neural networks (DNNs).
- Documentation: https://readthedocs.org/projects/sinabs/
- License: Apache 2.0
-
Latest release: 3.0.3
published 7 months ago
Rankings
Maintainers (3)
Dependencies
- actions/checkout v2 composite
- actions/checkout v3 composite
- actions/setup-python v2 composite
- codecov/codecov-action v2 composite
- pypa/gh-action-pypi-publish release/v1 composite
- softprops/action-gh-release v1 composite
- ipywidgets *
- matplotlib *
- myst_nb *
- pbr *
- sphinx >=4.0
- sphinx-book-theme *
- sphinx-gallery *
- torchvision *
- numpy *
- pbr *
- torch >=1.8
- matplotlib * test
- onnx * test
- onnxruntime * test
- pytest * test
- pytest-cov * test
- torch >=1.8 test
- torchvision * test
- pytest * develop
- sinabs *
- sphinx *
- attrs ==21.2.0 develop
- iniconfig ==1.1.1 develop
- packaging ==20.9 develop
- pluggy ==0.13.1 develop
- py ==1.10.0 develop
- pyparsing ==2.4.7 develop
- pytest ==6.2.4 develop
- toml ==0.10.2 develop
- alabaster ==0.7.12
- babel ==2.9.1
- certifi ==2021.5.30
- chardet ==4.0.0
- docutils ==0.17.1
- idna ==2.10
- imagesize ==1.2.0
- jinja2 ==3.0.1
- markupsafe ==2.0.1
- numpy ==1.20.3
- packaging ==20.9
- pandas ==1.2.4
- pbr ==5.6.0
- pygments ==2.9.0
- pyparsing ==2.4.7
- python-dateutil ==2.8.1
- pytz ==2021.1
- requests ==2.25.1
- sinabs ==0.2.1.dev53
- six ==1.16.0
- snowballstemmer ==2.1.0
- sphinx ==4.0.2
- sphinxcontrib-applehelp ==1.0.2
- sphinxcontrib-devhelp ==1.0.2
- sphinxcontrib-htmlhelp ==2.0.0
- sphinxcontrib-jsmath ==1.0.1
- sphinxcontrib-qthelp ==1.0.3
- sphinxcontrib-serializinghtml ==1.1.5
- torch ==1.8.1
- typing-extensions ==3.10.0.0
- urllib3 ==1.26.5
- black *
- ipywidgets *
- jupyterlab *
- jupyterlab-code-formatter *
- jupyterlab-lsp *
- matplotlib *
- pillow *
- python-lsp-server *
- tqdm *