wf_psf.metrics.metrics_interface module

Metrics Interface.

A module which defines the classes and methods to manage metrics evaluation of the trained psf model.

Author:

Jennifer Pollack <jennifer.pollack@cea.fr>

class wf_psf.metrics.metrics_interface.MetricsParamsHandler(metrics_params, trained_model)

Bases: object

Metrics Parameters Handler.

A class to handle training parameters accessed:

Parameters:

• metrics_params (Recursive Namespace object) – Recursive Namespace object containing metrics input parameters

• trained_model (Recursive Namespace object) – Recursive Namespace object containing trained model input parameters

Methods

evaluate_metrics_mono_rmse(psf_model, ...)	Evaluate Monochromatic PSF RMSE Metrics.
evaluate_metrics_opd(psf_model, simPSF, dataset)	Evaluate OPD Metrics.
evaluate_metrics_polychromatic_lowres(...)	Evaluate Polychromatic PSF Low-Res Metrics.
evaluate_metrics_shape(psf_model, simPSF, ...)	Evaluate PSF Shape Metrics.

evaluate_metrics_mono_rmse(psf_model, simPSF, dataset)

Evaluate Monochromatic PSF RMSE Metrics.

A function to evaluate metrics for Monochromatic PSF.

evaluate_metrics_opd(psf_model, simPSF, dataset)

Evaluate OPD Metrics.

A function to evaluate metrics for Optical Path Differences.

evaluate_metrics_polychromatic_lowres(psf_model, simPSF, dataset)

Evaluate Polychromatic PSF Low-Res Metrics.

A function to evaluate metrics for Low-Res Polychromatic PSF.

evaluate_metrics_shape(psf_model, simPSF, dataset)

Evaluate PSF Shape Metrics.

A function to evaluate metrics for PSF shape.

wf_psf.metrics.metrics_interface.evaluate_model(metrics_params, trained_model_params, training_data, test_data, psf_model, weights_path, metrics_output)

Evaluate the trained model.

For parameters check the training script click help.

wf_psf.metrics.metrics_interface.ground_truth_psf_model(metrics_params, coeff_matrix)