Random cut of patches on the icosahedron: use Direct Neighbors (DiNe) to build patches.

Examples

>>> from surfify.utils import icosahedron
>>> from surfify.datasets import make_classification
>>> from surfify.augmentation import SphericalRandomCut
>>> import matplotlib.pyplot as plt
>>> from surfify.plotting import plot_trisurf
>>> ico3_verts, ico3_tris = icosahedron(order=3)
>>> X, y = make_classification(ico3_verts, n_samples=1, n_classes=3,
                               scale=1, seed=42)
>>> processor = SphericalRandomCut(
        ico3_verts, ico3_tris, replacement_value=5)
>>> y_cut = processor(y)
>>> plot_trisurf(ico3_verts, triangles=ico3_tris, texture=y_cut,
                 is_label=True)
>>> plt.show()

__init__(vertices, triangles, neighs=None, patch_size=3, n_patches=1, replacement_value=0)[source]¶

Init class.

Parameters

vertices : array (N, 3)

icosahedron’s vertices.

triangles : array (M, 3)

icosahdron’s triangles.

neighs : dict, default None

optionnaly specify the DiNe neighboors of each vertex as build with sufify.utils.neighbors, ie. a dictionary with vertices row index as keys and a dictionary of neighbors vertices row indexes organized by rings as values.

n_rings : int, default 3

the number of neighboring rings from one node to be considered during the ablation.

n_patches : int, default 1

the number of patches to be considered.

replacement_value : float, default 0

the replacement patch value.