mirtorch.linear.basics.Convolve2d
- class mirtorch.linear.basics.Convolve2d(size_in: Sequence[int], weight: torch.Tensor, bias=None, stride: int = 1, padding: int = 0, dilation: int = 1)
2D cross-correlation linear map. The attributes follow the definition of torch.nn.Functional.conv2d
- __init__(size_in: Sequence[int], weight: torch.Tensor, bias=None, stride: int = 1, padding: int = 0, dilation: int = 1)
Initiate the linear operator.
Methods
__init__
(size_in, weight[, bias, stride, ...])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