Img2SpikeLayer#

class sinabs.layers.Img2SpikeLayer(image_shape, tw: int = 100, max_rate: float = 1000, norm: float = 255.0, squeeze: bool = False, negative_spikes: bool = False)[source]#

Layer to convert images to spikes.

Parameters
  • image_shape – tuple image shape

  • tw (int) – int Time window length

  • max_rate (float) – maximum firing rate of neurons

  • layer_name – string layer name

  • norm (float) – the supposed maximum value of the input (default 255.0)

  • squeeze (bool) – whether to remove singleton dimensions from the input

  • negative_spikes (bool) – whether to allow negative spikes in response to negative input

forward(img_input)[source]#

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.