tnmf.backends.NumPy
¶
A module that provides a NumPy based backend for computing the gradients of the factorization model. Shift-invariance is implemented via explicit convolution operations in the coordinate space.
Module Contents¶
Classes¶
A plain NumPy backend for computing the gradients of the factorization model in coordinate space (no FFT, no PyTorch). |
-
class
tnmf.backends.NumPy.
NumPy_Backend
(reconstruction_mode: str = 'valid')¶ Bases:
tnmf.backends._NumPyBackend.NumPyBackend
A plain NumPy backend for computing the gradients of the factorization model in coordinate space (no FFT, no PyTorch).
Convolutions are computed efficiently as contractions of properly strided arrays.
-
reconstruction_gradient_W
(self, V: numpy.ndarray, W: numpy.ndarray, H: numpy.ndarray, s: slice = sliceNone) → Tuple[numpy.ndarray, numpy.ndarray]¶
-
reconstruction_gradient_H
(self, V: numpy.ndarray, W: numpy.ndarray, H: numpy.ndarray, s: slice = sliceNone) → Tuple[numpy.ndarray, numpy.ndarray]¶
-
reconstruct
(self, W: numpy.ndarray, H: numpy.ndarray) → numpy.ndarray¶
-