This documentation is for a development version. Click here for the latest stable release (v0.1.0).


Installing PyTorchSpiking

We recommend using pip to install PyTorchSpiking:

pip install pytorch-spiking

That’s it!


PyTorchSpiking works with Python 3.6 or later. pip will do its best to install all of PyTorchSpiking’s requirements automatically. However, if anything goes wrong during this process you can install the requirements manually and then try to pip install pytorch-spiking again.

Developer installation

If you want to modify PyTorchSpiking, or get the very latest updates, you will need to perform a developer installation:

git clone
pip install -e ./pytorch-spiking

Installing PyTorch

The PyTorch documentation has a useful tool to determine the appropriate command to install pytorch on your system. We would recommend using conda, as it will take care of installing the other GPU-related packages, like CUDA/cuDNN.