Repository files navigation

The SNN conversion toolbox (SNN-TB) is a framework to transform rate-basedartificial neural networks into spiking neural networks, and to run them usingvarious spike encodings. A unique feature about SNN-TB is that it accepts inputmodels from many different deep-learning libraries (Keras / TF, pytorch, ...)and provides an interface to several backends for simulation (pyNN, brian2,...) or deployment (SpiNNaker, Loihi).

Pleaserefer to theDocumentation for a completeuser guide and API reference. See also the accompanying articles[Rueckauer et al., 2017],[Rueckauer and Liu, 2018], and[Rueckauer and Liu, 2021].