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
aspre_transform
. To convert the mesh to a point cloud, use thetorch_geometric.transforms.SamplePoints
astransform
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 toNone
, 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
)