Sinabs

Sinabs supports fast training of spiking neural networks with PyTorch and inference on neuromorphic hardware.

github.com/synsense/sinabs
Sinabs homepage screenshot

About Sinabs

Sinabs is a Python library for development and implementation of Spiking Convolutional Neural Networks (SCNNs) based on PyTorch. It implements spiking equivalents of CNN layers and can import CNN models built in Torch to test their spiking equivalents. It supports inference on neuromorphic hardware and porting models to DYNAP-CNN chips and dev-kits.

Key features

  • Develop Spiking Convolutional Neural Networks in Python
  • Provides spiking equivalents of CNN layers
  • Import Torch CNN models to test spiking equivalents
  • Supports inference on neuromorphic hardware
  • Port models to DYNAP-CNN chips and dev-kits
  • Install via pip or conda-forge
Best for: Researchers and developers building PyTorch-based spiking neural networks for neuromorphic hardware.
Good for
  • Built on PyTorch for spiking neural network work
  • Published under Apache-2.0 license
  • Installable via pip and conda-forge

Sinabs at a glance

Type
Open-source project
Pricing
Not confirmed. Check the site
Open source
Yes · Source code
Language
English
Last checked
Oct 6, 2026 · Online when checked
Listed
Oct 5, 2026

Sinabs alternatives

Tools and sites you could use instead, ranked by how closely they match.

All 24 alternatives

Popular in AI Infrastructure & MLOps

Well-known listings from the same topic.

All 341

Sinabs FAQ

How do I install the stable release?
Use pip install sinabs or conda install -c conda-forge sinabs.
What license covers Sinabs?
Apache v2.0; see the LICENSE file for details.
Where can I report bugs or contribute changes?
Through the GitHub repository; discussion is on the #sinabs Discord channel.
Is something wrong or out of date?

Tell us and an editor will check it.

Own this website?

Claim the listing and suggest updates yourself. An editor checks every claim first.

Claim this listing