ssspy.bss.base

In this module, we provide base class of blind source separation methods.

Algorithms

class ssspy.bss.base.IterativeMethodBase(callbacks=None, record_loss=True)

Base class of iterative method.

This class provides prototype of iterative updates.

Parameters:

• callbacks (callable or list[callable], optional) – Callback functions. Each function is called before separation and at each iteration. Default: None.

• record_loss (bool) – Record the loss at each iteration of the update algorithm if record_loss=True. Default: True.

__call__(*args, n_iter=100, initial_call=True, **kwargs)

Iteratively call update_once.

Parameters:

• n_iter (int) – The number of iterations of demixing filter updates. Default: 100.

• initial_call (bool) – If True, perform callbacks (and computation of loss if necessary) before iterations.

Return type:

ndarray

compute_loss()

Compute loss.

Return type:

float

Returns:

Computed loss. The type is expected float.

update_once()

Update parameters once.

Return type:

None