Upsampling#
- class deepinv.physics.Upsampling(img_size, filter=None, factor=2, padding='circular', device='cpu', **kwargs)[source]#
Bases:
Downsampling
Upsampling operator.
This operator performs the operation
\[y = h^T * S^T (x)\]where \(S^T\) is the adjoint of the subsampling operator and \(h\) is a low-pass filter.
- Parameters:
filter (torch.Tensor, str, None) – Upsampling filter. It can be
'gaussian'
,'bilinear'
,'bicubic'
,'sinc'
or a customtorch.Tensor
filter. IfNone
, no filtering is applied.factor (int) – upsampling factor
padding (str) – options are
'circular'
,'replicate'
and'reflect'
.device (str) – cpu or cuda