torch_geometric.datasets.TOSCA

class TOSCA(root: str, categories: Optional[List[str]] = None, transform: Optional[Callable] = None, pre_transform: Optional[Callable] = None, pre_filter: Optional[Callable] = None, force_reload: bool = False)[source]

Bases: InMemoryDataset

The TOSCA dataset from the “Numerical Geometry of Non-Ridig Shapes” book, containing 80 meshes. Meshes within the same category have the same triangulation and an equal number of vertices numbered in a compatible way.

Note

Data objects hold mesh faces instead of edge indices. To convert the mesh to a graph, use the torch_geometric.transforms.FaceToEdge as pre_transform. To convert the mesh to a point cloud, use the torch_geometric.transforms.SamplePoints as transform to sample a fixed number of points on the mesh faces according to their face area.

Parameters:
  • root (str) – Root directory where the dataset should be saved.

  • categories (list, optional) – List of categories to include in the dataset. Can include the categories "Cat", "Centaur", "David", "Dog", "Gorilla", "Horse", "Michael", "Victoria", "Wolf". If set to None, the dataset will contain all categories. (default: None)

  • transform (callable, optional) – A function/transform that takes in an torch_geometric.data.Data object and returns a transformed version. The data object will be transformed before every access. (default: None)

  • pre_transform (callable, optional) – A function/transform that takes in an torch_geometric.data.Data object and returns a transformed version. The data object will be transformed before being saved to disk. (default: None)

  • pre_filter (callable, optional) – A function that takes in an torch_geometric.data.Data object and returns a boolean value, indicating whether the data object should be included in the final dataset. (default: None)

  • force_reload (bool, optional) – Whether to re-process the dataset. (default: False)