pylops.TorchOperator

class pylops.TorchOperator(Op, batch=False, flatten=True, device='cpu', devicetorch='cpu')

Wrap a PyLops operator into a Torch function.

This class can be used to wrap a pylops operator into a torch function. Doing so, users can mix native torch functions (e.g. basic linear algebra operations, neural networks, etc.) and pylops operators.

Since all operators in PyLops are linear operators, a Torch function is simply implemented by using the forward operator for its forward pass and the adjoint operator for its backward (gradient) pass.

Parameters

Oppylops.LinearOperator

PyLops operator

batchbool, optional

Input has single sample (False) or batch of samples (True). If batch==False the input must be a 1-d Torch tensor or a tensor of size equal to Op.dims; if batch==True the input must be a 2-d Torch tensor with batches along the first dimension or a tensor of size equal to [nbatch, *Op.dims] where nbatch is the size of the batch

flattenbool, optional

Input is flattened along Op.dims (True) or not (False)

devicestr, optional

Device to be used when applying operator (cpu or gpu)

devicetorchstr, optional

Device to be assigned the output of the operator to (any Torch-compatible device)

Attributes

transpfnumpy.ndarray

Indices to transpose batch to last dimension before applying Op

transpbnumpy.ndarray

Indices to transpose back batch to first dimension after applying Op

Methods

__init__(Op[, batch, flatten, device, ...])
apply(x)	Apply forward pass to input vector

Examples using pylops.TorchOperator

20. Torch Operator

20. Torch Operator