AAMMultilevelFittingResult¶
- class menpo.fitmultilevel.fittingresult.AAMMultilevelFittingResult(image, multiple_fitter, fitting_results, affine_correction, gt_shape=None, error_type='me_norm')[source]¶
Bases: MultilevelFittingResult
Object let us recover the state of an AAM Fitter after the latter has fitted a particular image.
Parameters: image: :class:`pybug.image.masked.MaskedImage` :
The fitted image.
aam_fitter: :class:`pybug.aam.fitter.AAMFitter` :
The aam_fitter object used to fitter the image.
basic_fittings: :class:`pybug.aam.fitting.BasicFitting` list :
A list of basic fitting objects.
_affine_correction: :class: `pybug.transforms.affine.Affine` :
An affine transform that maps the result of the top resolution fitting level to the space scale of the original image.
gt_shape: class:`pybug.shape.PointCloud`, optional :
The ground truth shape associated to the image.
Default: None
error_type: ‘me_norm’, ‘me’ or ‘rmse’, optional. :
Specifies the way in which the error between the fitted and ground truth shapes is to be computed.
Default: ‘me_norm’
- appearance_reconstructions(as_pixels=False)[source]¶
Generates a list containing the appearance reconstruction obtained at each fitting iteration.
Parameters: as_pixels : boolean, optional
Whether the result is returned as a list of Image or ndarray.
Returns: appearance_reconstructions : MaskedImage or ndarray list
A list containing the appearance reconstructions obtained at each fitting iteration.
- plot_cost(figure_id=None, new_figure=False, **kwargs)[source]¶
Plots the cost evolution throughout the fitting.
- plot_error(figure_id=None, new_figure=False, **kwargs)¶
Plots the error evolution throughout the fitting.
- shapes(as_points=False)¶
Generates a list containing the shapes obtained at each fitting iteration.
Parameters: as_points: boolean, optional :
Whether the results is returned as a list of PointClouds or ndarrays.
Default: False
Returns: shapes: :class:`menpo.shape.PointCoulds or ndarray list :
A list containing the shapes obtained at each fitting iteration.
- view(**kwargs)¶
View the object using the default rendering engine figure handling. For example, the default behaviour for Matplotlib is that all draw commands are applied to the same figure object.
Parameters: kwargs : dict
Passed through to specific rendering engine.
Returns: viewer : Renderer
The renderer instantiated.
- view_appearance_reconstructions(figure_id=None, new_figure=False, channels=None, **kwargs)[source]¶
Displays the appearance reconstructions.
- view_error_images(figure_id=None, new_figure=False, channels=None, **kwargs)[source]¶
Displays the error images.
- view_final_fitting(figure_id=None, new_figure=False, **kwargs)¶
Displays the final fitting result.
- view_ground_truth(figure_id=None, new_figure=False, **kwargs)¶
Displays the ground truth annotation.
- view_initialization(figure_id=None, new_figure=False, **kwargs)¶
Displays the initialization from which the fitting started.
- view_new(**kwargs)¶
View the object on a new figure.
Parameters: kwargs : dict
Passed through to specific rendering engine.
Returns: viewer : Renderer
The renderer instantiated.
- view_on(figure_id, **kwargs)¶
View the object on a a specific figure specified by the given id.
Parameters: figure_id : object
A unique identifier for a figure.
kwargs : dict
Passed through to specific rendering engine.
Returns: viewer : Renderer
The renderer instantiated.
- view_warped_images(figure_id=None, new_figure=False, channels=None, from_basic_fittings=False, **kwargs)[source]¶
Displays the warped images.
- warped_images(from_basic_fittings=False, as_pixels=False)[source]¶
Generates a list containing the warped images obtained at each fitting iteration.
Parameters: from_basic_fittings : boolean, optional
If True, the returned transform per iteration is used to warp the internal image representation used by each basic fitter. If False, the transforms are used to warp original image.
as_pixels : boolean, optional
Whether the result is returned as a list of Image or ndarray.
Returns: warped_images : MaskedImage or ndarray list
A list containing the warped images obtained at each fitting iteration.
- algorithm¶
Returns the name of the algorithm used by the Fitter.
- downscale¶
Returns the downscale factor used by the multiple fitter.
- error_type¶
Return the type of error.
- errors¶
Returns a list containing the error at each fitting iteration.
- final_error¶
Returns the final fitting error.
Type: float
- final_shape¶
Returns the final fitted shape.
- fitted¶
Returns the fitted state of each fitting object.
- gt_shape¶
Returns the original ground truth shape associated to the image.
- initial_error¶
Returns the initial fitting error.
Type: float
- initial_shape¶
Returns the initial shape from which the fitting started.
- n_iters¶
Returns the total number of iterations used to fitter the image.
- n_levels¶
Returns the number of levels of the fitter object.
- residual[source]¶
Returns the type of residual used by the basic fitter associated to each basic fitting.
- scaled_levels¶
Returns True if the shape results returned by the basic fitting_results must be scaled.