DeformableModelBuilder

class menpo.fitmultilevel.builder.DeformableModelBuilder

Bases: object

Abstract class with a set of functions useful to build a Deformable Model.

build(images, group=None, label='all')

Builds a Multilevel Deformable Model.

classmethod check_boundary(boundary)

Checks the boundary added around the reference shape that must be int >= 0.

classmethod check_downscale(downscale)

Checks the downscale factor of the pyramid that must be >= 1.

classmethod check_feature_type(feature_type, n_levels, pyramid_on_features)

Checks the feature type per level. If pyramid_on_features is False, it must be a string or a function/closure or a list of those containing 1 or {n_levels} elements. If pyramid_on_features is True, it must be a string or a function/closure or a list of 1 of those.

Parameters:

n_levels: int :

The number of pyramid levels.

pyramid_on_features: boolean :

If True, the pyramid will be applied to the feature image, so the user needs to define a single feature_type. If False, the pyramid will be applied to the intensities image and features will be extracted at each level, so the user can define a feature_type per level.

Returns:

feature_type_list: list :

A list of feature types. If pyramid_on_features is True, the list will have length 1. If pyramid_on_features is False, the list will have length {n_levels}.

classmethod check_max_components(max_components, n_levels, var_name)

Checks the maximum number of components per level either of the shape or the appearance model. It must be None or int or float or a list of those containing 1 or {n_levels} elements.

classmethod check_n_levels(n_levels)

Checks the number of pyramid levels that must be int > 0.

classmethod check_normalization_diagonal(normalization_diagonal)

Checks the diagonal length used to normalize the images’ size that must be >= 20.