ZeroPrior#

class deepinv.optim.ZeroPrior[source]#

Bases: Prior

Zero prior \(\reg{x} = 0\).

fn(x, *args, **kwargs)[source]#

Computes the zero prior \(\reg{x} = 0\) at \(x\).

Parameters:

x (torch.Tensor) – Variable \(x\) at which the prior is computed.

Returns:

(torch.Tensor) prior \(\reg{x}\).

grad(x, *args, **kwargs)[source]#

Computes the gradient of the zero prior \(\reg{x} = 0\) at \(x\).

Parameters:

x (torch.Tensor) – Variable \(x\) at which the prior is computed.

Returns:

(torch.Tensor) gradient at \(x\).

prox(x, ths=1.0, gamma=1.0, *args, **kwargs)[source]#

Computes the proximal operator of the zero prior \(\reg{x} = 0\) at \(x\).

Parameters:

x (torch.Tensor) – Variable \(x\) at which the prior is computed.

Returns:

(torch.Tensor) proximity operator at \(x\).

Examples using ZeroPrior:#

Random phase retrieval and reconstruction methods.

Random phase retrieval and reconstruction methods.