algorithms¶
-
class
pymethods.algorithms.BreadthFirstSearch(adjacency_list: Iterable[Iterable], properties=None, show_progress=False)¶ -
adjacency_list¶
-
clean()¶
-
query_current_vertex()¶
-
reset_progress_bar()¶
-
step_progress_bar()¶
-
curvature_fitting¶
-
curvature_fitting.can_lsq_fit(adj_list: numpy.ndarray, point_basis: numpy.ndarray, n_processors=None, eps=10000000.0) → Iterable[numpy.ndarray]¶ A python implementation of Curvature Estimation of 3D Point Cloud Surfaces Through the Fitting of NormalSection Curvatures http://www.nlpr.ia.ac.cn/2008papers/gjhy/gh129.pdf
- Args:
main_array (np.ndarray): pointcloud array 3xN adj_list (np.ndarray): adjacency list NxKNN point_basis (np.ndarray): Nx3x3
- Returns:
typing.Iterable[np.ndarray]: principle_curvatures, principle_directions
shapeModelling¶
-
class
pymethods.algorithms.shapeModelling.PointDistributionModel(dataPath)¶ -
class
NDSpace(meanShape, alignedShapes)¶ -
U¶
-
V_T¶
-
W¶
-
explained_variance()¶
-
recoverDimensions(shape)¶
-
svd(modes=6)¶
-
-
alignShapesToMean(shapeList, scale=False)¶
-
build(modes=10, eps=1e-05, countCap=1000, costlimit=0, scale=False, startShape=None)¶
-
explained_variance()¶
-
generateShape(C)¶
-
objectiveFunction(listShapes)¶
-
postProcessBuilt(shapes, scale=False)¶
-
postProcessGenerated(shape)¶
-
recommendedAmountModes(explainedVarReq=0.8)¶
-
class