mantra.datasets

Datasets module

This module contains datasets describing triangulations of manifolds, following the API pytorch-geometric.

class mantra.datasets.ManifoldTriangulations(root, manifold='2', version='latest', transform=None, pre_transform=None, pre_filter=None)

__init__(root, manifold='2', version='latest', transform=None, pre_transform=None, pre_filter=None)

The dataset class for the manifold triangulations.

Parameters

manifold: string: Wether to use the 2 or 3 manifolds. Default is 2.
version: string: Version of the dataset to use. The version should correspond to a released version of the dataset which can be found ![here](https://github.com/aidos-lab/mantra/releases). Default is the latest version.

property raw_file_names: The name of the files in the self.raw_dir folder that must be present in order to skip downloading.

property processed_file_names: The name of the files in the self.processed_dir folder that must be present in order to skip processing.

download() → None: Downloads the dataset to the self.raw_dir folder.

process(): Processes the dataset to the self.processed_dir folder.