Cuda error in SpikingActivation Function

[Rwik2000]

Dear Team,
In the functional.py, SpikingActivation class, forward function,
Please do add the provision for GPU usage. The initial state which is initialised if not given prior hand is in the cpu, whereas everything else remains in gpu (if course we use gpu). Can you add a provision of a gpu(.cuda())

[drasmuss]

Hi @Rwik2000. We don't want to assume that the initial state will be on the GPU, as that would cause errors for people running on CPU. You can opt-in to GPU usage by passing in an explicit initial state (which you can assign to the GPU). It's possible that there's a more elegant way to support running on both CPU and GPU, if you have any ideas we would welcome a PR!