https://github.com/neuromorphicprocessorproject/snn_toolbox

Toolbox for converting analog to spiking neural networks (ANN to SNN), and running them in a spiking neuron simulator.
https://github.com/neuromorphicprocessorproject/snn_toolbox

brian brian2 caffe deep-learning deep-neural-networks keras lasagne loihi nest pynn pytorch spiking-neural-networks spinnaker tensorflow

Last synced: about 4 hours ago
JSON representation

Toolbox for converting analog to spiking neural networks (ANN to SNN), and running them in a spiking neuron simulator.

• Host: GitHub
• URL: https://github.com/neuromorphicprocessorproject/snn_toolbox
• Owner: NeuromorphicProcessorProject
• License: mit
• Created: 2016-07-27T07:58:19.000Z (about 8 years ago)
• Default Branch: master
• Last Pushed: 2023-01-13T10:01:01.000Z (over 1 year ago)
• Last Synced: 2024-09-28T01:41:28.985Z (about 4 hours ago)
• Topics: brian, brian2, caffe, deep-learning, deep-neural-networks, keras, lasagne, loihi, nest, pynn, pytorch, spiking-neural-networks, spinnaker, tensorflow
• Language: Python
• Size: 338 MB
• Stars: 360
• Watchers: 16
• Forks: 104
• Open Issues: 3
• Metadata Files:
  • Readme: README.rst
  • Changelog: CHANGELOG.rst
  • License: LICENSE.txt

Awesome Lists containing this project

README

        
|b1| |b2| |b3| |b4|

.. |b1| image:: https://travis-ci.org/NeuromorphicProcessorProject/snn_toolbox.svg?branch=master

    :target: https://travis-ci.org/NeuromorphicProcessorProject/snn_toolbox

.. |b2| image:: https://readthedocs.org/projects/snntoolbox/badge/?version=latest

    :target: https://snntoolbox.readthedocs.io/en/latest/?badge=latest

    :alt: Documentation Status

.. |b3| image:: https://badge.fury.io/py/snntoolbox.svg

    :target: https://badge.fury.io/py/snntoolbox

.. |b4| image:: https://pepy.tech/badge/snntoolbox

    :target: https://pepy.tech/project/snntoolbox

    

Spiking neural network conversion toolbox

=========================================

The SNN conversion toolbox (SNN-TB) is a framework to transform rate-based

artificial neural networks into spiking neural networks, and to run them using

various spike encodings. A unique feature about SNN-TB is that it accepts input

models from many different deep-learning libraries (Keras / TF, pytorch, ...)

and provides an interface to several backends for simulation (pyNN, brian2,

...) or deployment (SpiNNaker, Loihi).

Please

refer to the `Documentation `_ for a complete

user guide and API reference. See also the accompanying articles

`[Rueckauer et al., 2017] `_, `[Rueckauer and Liu, 2018] `_, and `[Rueckauer and Liu, 2021] `_.