torch_geometric.datasets.PascalPF

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

Bases: InMemoryDataset

The Pascal-PF dataset from the “Proposal Flow” paper, containing 4 to 16 keypoints per example over 20 categories.

Parameters:

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

  • category (str) – The category of the images (one of "Aeroplane", "Bicycle", "Bird", "Boat", "Bottle", "Bus", "Car", "Cat", "Chair", "Diningtable", "Dog", "Horse", "Motorbike", "Person", "Pottedplant", "Sheep", "Sofa", "Train", "TVMonitor")

  • 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)