I have a 1D signal, which I subject to the following operations:
- Split into overlapping frames. I can do that with
torch.Tensor.unfold
function. - Work with each frame individually.
- Combine the result back into 1D. The originally overlapping regions need to be summed up.
How can i perform the 3rd step efficiently? There is a class torch.nn.Fold
, but it only works for image-like tensors with a channel dimension.