Ctrl+K

dynapcnn_layer

dynapcnn_layer#

This module defines the DynapcnnLayer class that is used to reproduce the behavior of a layer on the dynapcnn chip.

class sinabs.backend.dynapcnn.dynapcnn_layer.DynapcnnLayer(conv: Conv2d, spk: IAFSqueeze, in_shape: Tuple[int, int, int], pool: SumPool2d | None = None, discretize: bool = True, rescale_weights: int = 1)[source]#

Create a DynapcnnLayer object representing a dynapcnn layer.

Requires a convolutional layer, a sinabs spiking layer and an optional pooling value. The layers are used in the order conv -> spike -> pool.

Parameters:

  • conv (torch.nn.Conv2d or torch.nn.Linear) – Convolutional or linear layer (linear will be converted to convolutional)

  • spk (sinabs.layers.IAFSqueeze) – Sinabs IAF layer

  • in_shape (tuple of int) – The input shape, needed to create dynapcnn configs if the network does not contain an input layer. Convention: (features, height, width)

  • pool (int or None) – Integer representing the sum pooling kernel and stride. If None, no pooling will be applied.

  • discretize (bool) – Whether to discretize parameters.

  • rescale_weights (int) – Layer weights will be divided by this value.

forward(x)[source]#

Torch forward pass.

get_neuron_shape() → Tuple[int, int, int][source]#

Return the output shape of the neuron layer.

Return type:

features, height, width

memory_summary()[source]#

Computes the amount of memory required for each of the components. Note that this is not necessarily the same as the number of parameters due to some architecture design constraints.

\[K_{MT} = c \cdot 2^{\lceil \log_2\left(k_xk_y\right) \rceil + \lceil \log_2\left(f\right) \rceil}\]
\[N_{MT} = f \cdot 2^{ \lceil \log_2\left(f_y\right) \rceil + \lceil \log_2\left(f_x\right) \rceil }\]
Return type:

A dictionary with keys kernel, neuron and bias and the corresponding memory sizes

zero_grad(set_to_none: bool = False) → None[source]#

Reset gradients of all model parameters.

See similar function under torch.optim.Optimizer for more context.

Parameters:

set_to_none (bool) – instead of setting to zero, set the grads to None. See torch.optim.Optimizer.zero_grad() for details.

Return type:

None

Contents