A spiking deep neural network simulator, and neuromoprhic hardware emulator
Project description
SINABS
Getting started
Sinabs Is Not A Brain Simulator
NOTE: This project is mirrored to gitlab.com/aiCTX/sinabs and is managed by aiCTX AG.
sinabs
(pytorch based library) is developed to design and implement 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 keras conveniently to test their spiking
equivalent implementation.
NOTE: The conversion of CNNs to SCNNs is still a subject of research and we strive to keep the library updated to the state-of-the art in addition to providing options to compare various approaches both at a high level abstraction to low level implementation details.
NOTE: This library is an alpha release state and is subject to API changes.
Installation
You can install sinabs
with pip:
pip install sinabs
If you want to develop or have access to source code of sinabs, download the package from the git repository:
$ cd <to/your/software/folder>
$ git clone https://gitlab.com/aiCTX/sinabs.git>
$ cd sinabs
$ pip install -e . --user
For developers, we recommend that you install this package as a development version so that you can update the package without reinstalling the package.
Checkout our quick instructional on how to create a project based on sinabs
within a virtual environment using pyenv+pipenv
Documentation and Examples
https://aictx.gitlab.io/sinabs
If you would like to generate documentation locally, you can do that using sphynx
.
You can generate a sphynx documentation for this package by running the the following command.
Requirements: sphinx, pandoc, nbsphinx
$ cd /path/to/sinabs/docs/
$ make html
$ firefox build/html/index.html
This will build and auto generate html documentation at sinabs/docs/build/html/index.html
License
sinabs
is published under AGPL v3.0. See the LICENSE file for details.
Contributing to sinabs
Checkout CONTRIBUTING.md
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for sinabs-0.1.dev4-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 62b42b6cfd5094516677adf8118add2ca6056257767993fe162750425ece2b4b |
|
MD5 | 83adfa66e2e7539a8a6880c5955b9c77 |
|
BLAKE2b-256 | 9341f06731a27ac547fd234e64b1aa123da5c357e07696039666b51fd2da793f |