https://github.com/nengo/pytorch-spiking

Spiking neuron integration for PyTorch
https://github.com/nengo/pytorch-spiking

deep-learning python pytorch spiking-neural-networks

Last synced: 8 months ago
JSON representation

Spiking neuron integration for PyTorch

• Host: GitHub
• URL: https://github.com/nengo/pytorch-spiking
• Owner: nengo
• License: other
• Created: 2020-08-21T12:39:44.000Z (over 5 years ago)
• Default Branch: main
• Last Pushed: 2025-03-18T17:53:32.000Z (9 months ago)
• Last Synced: 2025-04-12T07:51:59.882Z (8 months ago)
• Topics: deep-learning, python, pytorch, spiking-neural-networks
• Language: Python
• Homepage: https://www.nengo.ai/pytorch-spiking/
• Size: 8.52 MB
• Stars: 40
• Watchers: 4
• Forks: 6
• Open Issues: 2
• Metadata Files:
  • Readme: README.rst
  • Changelog: CHANGES.rst
  • Contributing: CONTRIBUTING.rst
  • License: LICENSE.rst

Awesome Lists containing this project

• awesome-snn - nengo/pytorch-spiking - spiking?style=social"/> : Spiking neuron integration for PyTorch. www.nengo.ai/pytorch-spiking/. (Frameworks)

README

          
.. image:: https://img.shields.io/pypi/v/pytorch-spiking.svg

  :target: https://pypi.org/project/pytorch-spiking

  :alt: Latest PyPI version

.. image:: https://img.shields.io/pypi/pyversions/pytorch-spiking.svg

  :target: https://pypi.org/project/pytorch-spiking

  :alt: Python versions

**************

PyTorchSpiking

**************

PyTorchSpiking provides tools for training and running spiking neural networks

directly within the PyTorch framework. The main feature is

``pytorch_spiking.SpikingActivation``, which can be used to transform

any activation function into a spiking equivalent. For example, we can translate a

non-spiking model, such as

.. code-block:: python

    torch.nn.Sequential(

        torch.nn.Linear(5, 10),

        torch.nn.ReLU(),

    )

into the spiking equivalent:

.. code-block:: python

    torch.nn.Sequential(

        torch.nn.Linear(5, 10),

        pytorch_spiking.SpikingActivation(torch.nn.ReLU()),

    )

Models with SpikingActivation layers can be optimized and evaluated in the same way as

any other PyTorch model. They will automatically take advantage of PyTorchSpiking's

"spiking aware training": using the spiking activations on the forward pass and the

non-spiking (differentiable) activation function on the backwards pass.

PyTorchSpiking also includes various tools to assist in the training of spiking models,

such as `filtering layers

`_.

If you are interested in building and optimizing spiking neuron models, you may also

be interested in `NengoDL `_. See

`this page `_ for a

comparison of the different use cases supported by these two packages.

**Documentation**

Check out the `documentation `_ for

- `Installation instructions

  `_

- `More detailed example introducing the features of PyTorchSpiking

  `_

- `API reference `_