optim_builder

deepinv.optim.optim_builder(iteration, max_iter=100, params_algo={'g_param': 0.05, 'lambda': 1.0, 'stepsize': 1.0}, data_fidelity=None, prior=None, F_fn=None, g_first=False, **kwargs)[source]

Helper function for building an instance of the BaseOptim() class.

Parameters:
  • iteration (str, deepinv.optim.optim_iterators.OptimIterator) – either the name of the algorithm to be used, or directly an optim iterator. If an algorithm name (string), should be either "GD" (gradient descent), "PGD" (proximal gradient descent), "ADMM" (ADMM), "HQS" (half-quadratic splitting), "CP" (Chambolle-Pock) or "DRS" (Douglas Rachford).

  • max_iter (int) – maximum number of iterations of the optimization algorithm. Default: 100.

  • params_algo (dict) – dictionary containing all the relevant parameters for running the algorithm, e.g. the stepsize, regularisation parameter, denoising standart deviation. Each value of the dictionary can be either Iterable (distinct value for each iteration) or a single float (same value for each iteration). See Parameters for more details. Default: {"stepsize": 1.0, "lambda": 1.0}.

  • deepinv.optim.DataFidelity (list,) – data-fidelity term. Either a single instance (same data-fidelity for each iteration) or a list of instances of deepinv.optim.DataFidelity() (distinct data-fidelity for each iteration). Default: None.

  • prior (list, deepinv.optim.Prior) – regularization prior. Either a single instance (same prior for each iteration) or a list of instances of deepinv.optim.Prior (distinct prior for each iteration). Default: None.

  • F_fn (callable) – Custom user input cost function. default: None.

  • g_first (bool) – whether to perform the step on \(g\) before that on \(f\) before or not. default: False

  • kwargs – additional arguments to be passed to the BaseOptim() class.

Returns:

an instance of the BaseOptim() class.

Examples using optim_builder:

Radio interferometric imaging with deepinverse

Radio interferometric imaging with deepinverse

Image deblurring with custom deep explicit prior.

Image deblurring with custom deep explicit prior.

Random phase retrieval and reconstruction methods.

Random phase retrieval and reconstruction methods.

Image deblurring with Total-Variation (TV) prior

Image deblurring with Total-Variation (TV) prior

Image inpainting with wavelet prior

Image inpainting with wavelet prior

Vanilla PnP for computed tomography (CT).

Vanilla PnP for computed tomography (CT).

DPIR method for PnP image deblurring.

DPIR method for PnP image deblurring.

Regularization by Denoising (RED) for Super-Resolution.

Regularization by Denoising (RED) for Super-Resolution.

PnP with custom optimization algorithm (Condat-Vu Primal-Dual)

PnP with custom optimization algorithm (Condat-Vu Primal-Dual)