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, force_reload: bool = False)[source]

Bases: InMemoryDataset

来自“动态FAUST：注册运动中的人体”论文的动态FAUST人类数据集。

注意

数据对象持有网格面而不是边索引。 要将网格转换为图，请使用 torch_geometric.transforms.FaceToEdge 作为 pre_transform。 要将网格转换为点云，请使用 torch_geometric.transforms.SamplePoints 作为 transform 来 根据网格面的面积在网格面上采样固定数量的点。

Parameters:

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

  • subjects (list, optional) – 要包含在数据集中的主题列表。可以包括主题 "50002", "50004", "50007", "50009", "50020", "50021", "50022", "50025", "50026", "50027". 如果设置为 None，数据集将包含所有主题。 (默认值: None)

  • categories (list, optional) – 要包含在数据集中的类别列表。可以包括以下类别："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". 如果设置为 None，数据集将包含所有类别。 (默认值: 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)