mirtorch.linear.basics.Patch2D
- class mirtorch.linear.basics.Patch2D(size_in: Sequence[int], size_kernel: int, stride: int = 1, padded: bool = False)
Patch operator to decompose image into blocks
- kernel_size
int, isotropic kernel size
- stride
int, size of stride
- __init__(size_in: Sequence[int], size_kernel: int, stride: int = 1, padded: bool = False)
Initiate the linear operator.
Methods
__init__
(size_in, size_kernel[, stride, padded])Initiate the linear operator.
adjoint
(x)Apply the adjoint operator
apply
(x)Apply the forward operator
to
(*args, **kwargs)Copy to different devices
Attributes
H
Apply the (Hermitian) transpose