torch_geometric.datasets.DynamicFAUST

class DynamicFAUST(root: str, subjects: Optional[List[str]] = None, categories: Optional[List[str]] = None, transform: Optional[Callable] = None, pre_transform: Optional[Callable] = None, pre_filter: Optional[Callable] = None)[source]

Bases: InMemoryDataset

The dynamic FAUST humans dataset from the “Dynamic FAUST: Registering Human Bodies in Motion” paper.

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.

  • subjects (list, optional) – List of subjects to include in the dataset. Can include the subjects "50002", "50004", "50007", "50009", "50020", "50021", "50022", "50025", "50026", "50027". If set to None, the dataset will contain all subjects. (default: None)

  • categories (list, optional) – List of categories to include in the dataset. Can include the categories "chicken_wings", "hips", "jiggle_on_toes", "jumping_jacks", "knees", "light_hopping_loose", "light_hopping_stiff", "one_leg_jump", "one_leg_loose", "personal_move", "punching", "running_on_spot", "running_on_spot_bugfix", "shake_arms", "shake_hips", "shoulders". 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)