Struct GradientDescent 

pub struct GradientDescent {

    pub iterations: usize,
    pub object_step: f64,
    pub batch_size: usize,
    pub epsilon: f64,
    pub loss_type: LossType,
    pub recover_illumination: bool,
    pub illumination_step: f64,
    pub illumination_finite_difference: f64,
    pub maximum_illumination_correction: f64,
    pub recover_pupil: bool,
    pub pupil_step: f64,
    pub constrain_pupil_support: bool,
    pub object_tv_weight: f64,
    pub object_tv_epsilon: f64,
    pub pupil_smoothing_weight: f64,
    pub parallel_workers: usize,
}

Wirtinger-style loss-gradient reconstruction for Fourier ptychography.

Method

The solver differentiates a selected real-valued data loss through the complex FPM forward model, accumulates gradients from a mini-batch, and applies a pupil-power-preconditioned update to the shared object spectrum. This is the Fourier-ptychographic Wirtinger-flow viewpoint: phase retrieval is treated as direct optimization rather than alternating hard projections. Losses are evaluated after accounting for known linear gain and background, so detector count scaling does not change the intrinsic update scale.

Optional extensions recover the pupil with an analogous normalized gradient, estimate illumination offsets with finite-difference derivatives and diagonal Gauss–Newton scaling, and regularize the complex object or pupil. Incoherent multiplexing, these calibration updates, and the selectable losses extend the reference formulation.

Reference

L. Bian, J. Suo, G. Zheng, K. Guo, F. Chen, and Q. Dai, “Fourier ptychographic reconstruction using Wirtinger flow optimization,” Optics Express 23(4), 4856–4866 (2015), doi:10.1364/OE.23.004856.

Fields

iterations: usize

Number of complete passes through the acquisition schedule.

object_step: f64

Step size of the pupil-power-preconditioned object update.

batch_size: usize

Number of frame gradients averaged into one update.

epsilon: f64

Positive numerical floor used by losses and preconditioners.

loss_type: LossType

Data-fidelity objective to differentiate and report.

recover_illumination: bool

Whether to estimate a Fourier-grid offset for every illumination source.

illumination_step: f64

Step size of the diagonally scaled illumination-offset update.

illumination_finite_difference: f64

Central finite-difference spacing in Fourier-grid pixels.

maximum_illumination_correction: f64

Maximum absolute row or column correction, in Fourier-grid pixels.

recover_pupil: bool

Whether to update the complex pupil alongside the object.

pupil_step: f64

Step size of the normalized pupil update.

constrain_pupil_support: bool

Whether to zero recovered pupil values outside the compiled aperture.

object_tv_weight: f64

Weight of the isotropic total-variation step on the complex object; 0 disables it.

object_tv_epsilon: f64

Positive smoothing constant in the differentiable TV norm.

pupil_smoothing_weight: f64

Weight of quadratic nearest-neighbor pupil smoothing; 0 disables it and positive values require pupil recovery.

parallel_workers: usize

Maximum number of frame-gradient worker threads.

Implementations

impl GradientDescent

pub fn iterations(self, iterations: usize) -> Self

pub fn object_step(self, step: f64) -> Self

pub fn batch_size(self, batch_size: usize) -> Self

pub fn loss_type(self, loss_type: LossType) -> Self

pub fn recover_illumination(self, recover: bool) -> Self

pub fn illumination_step(self, step: f64) -> Self

pub fn illumination_finite_difference(self, distance: f64) -> Self

pub fn illumination_bounds(self, maximum_absolute_correction: f64) -> Self

pub fn recover_pupil(self, recover: bool) -> Self

pub fn pupil_step(self, step: f64) -> Self

pub fn constrain_pupil_support(self, constrain: bool) -> Self

pub fn object_tv(self, weight: f64) -> Self

pub fn object_tv_epsilon(self, epsilon: f64) -> Self

pub fn pupil_smoothing(self, weight: f64) -> Self

pub fn parallel_workers(self, workers: usize) -> Self

Sets the maximum number of frame-gradient workers. Object, pupil, and illumination-calibration contributions are reduced deterministically.

Trait Implementations

impl Clone for GradientDescent

fn clone(&self) -> GradientDescent

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for GradientDescent

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for GradientDescent

fn default() -> Self

Returns the “default value” for a type.

impl ReconstructionAlgorithm for GradientDescent

fn validate(&self) -> Result<()>

fn step<M: MeasurementRead>( &mut self, problem: &ReconstructionProblem<M>, state: &mut ReconstructionState, batch: &Batch, iteration: usize, ) -> Result<StepDiagnostics>

fn iterations(&self) -> usize

fn batch_size(&self) -> usize

fn validate_problem<M: MeasurementRead>( &self, _problem: &ReconstructionProblem<M>, ) -> Result<()>

fn initialize<M: MeasurementRead>( &self, problem: &ReconstructionProblem<M>, ) -> Result<ReconstructionState>

fn initialize_with_backend<M: MeasurementRead>( &self, problem: &ReconstructionProblem<M>, backend: Arc<dyn Backend>, ) -> Result<ReconstructionState>

fn run<M: MeasurementRead>( self, problem: &ReconstructionProblem<M>, ) -> Result<ReconstructionResult>

where Self: Sized,

fn run_with_callbacks<M: MeasurementRead>( self, problem: &ReconstructionProblem<M>, callbacks: Vec<Box<dyn Callback>>, ) -> Result<ReconstructionResult>

where Self: Sized,

fn run_from_checkpoint<M: MeasurementRead>( self, problem: &ReconstructionProblem<M>, checkpoint: ReconstructionCheckpoint, ) -> Result<ReconstructionResult>

where Self: Sized,