Sinabs
A PyTorch-based deep learning library for building and training spiking convolutional neural networks with hardware deployment support.
What is Sinabs?
Sinabs is a Python library for developing and implementing Spiking Convolutional Neural Networks (SCNNs). It provides spiking equivalents of standard CNN layers and enables convenient conversion of PyTorch CNN models to their spiking counterparts, with a focus on fast training and neuromorphic hardware inference.
Researchers and engineers working in neuromorphic computing, particularly those using PyTorch for CNN development and seeking to deploy spiking neural networks on specialized hardware like DYNAP-CNN chips.
Developers choose Sinabs for its seamless PyTorch integration, allowing familiar workflows while enabling efficient training and deployment of spiking neural networks on neuromorphic hardware through its sinabs-dynapcnn extension.
Overview
A deep learning library for spiking neural networks which is based on PyTorch, focuses on fast training and supports inference on neuromorphic hardware.
Use Cases
Best For
- Converting existing PyTorch CNN models to spiking neural network equivalents.
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
