tnmf.backends.PyTorch

A module that provides a PyTorch 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

PyTorch_Backend

Reconstruction is performed via an explicit convolution in coordinate space.

class tnmf.backends.PyTorch.PyTorch_Backend(**kwargs)

Bases: tnmf.backends._PyTorchBackend.PyTorchBackend

Reconstruction is performed via an explicit convolution in coordinate space.

reconstruct(self, W: torch.Tensor, H: torch.Tensor) → torch.Tensor