LIFSqueeze#

class sinabs.layers.LIFSqueeze(batch_size=None, num_timesteps=None, **kwargs)[source]#

LIF layer with 4-dimensional input (Batch*Time, Channel, Height, Width).

Same as parent LIF class, only takes in squeezed 4D input (Batch*Time, Channel, Height, Width) instead of 5D input (Batch, Time, Channel, Height, Width) in order to be compatible with layers that can only take a 4D input, such as convolutional and pooling layers.

Shape:
  • Input: \((Batch \times Time, Channel, Height, Width)\) or \((Batch \times Time, Channel)\)

  • Output: Same as input.

v_mem#

The membrane potential resets according to reset_fn for every spike.

i_syn#

This attribute is only available if tau_syn is not None.

forward(input_data: Tensor) Tensor[source]#

Forward call wrapper that will flatten the input to and unflatten the output from the super class forward call.

Parameters:

input_data (Tensor) –

Return type:

Tensor