torch_geometric.datasets.CoMA

class CoMA(root: str, train: bool = True, transform: Optional[Callable] = None, pre_transform: Optional[Callable] = None, pre_filter: Optional[Callable] = None, force_reload: bool = False)[source]

Bases: InMemoryDataset

The CoMA 3D faces dataset from the “Generating 3D faces using Convolutional Mesh Autoencoders” paper, containing 20,466 meshes of extreme expressions captured over 12 different subjects.

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.

  • train (bool, optional) – If True, loads the training dataset, otherwise the test dataset. (default: True)

  • 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)

STATS:

#graphs

#nodes

#edges

#features

#classes

20,465

5,023

29,990

3

12