torch_geometric.datasets.WILLOWObjectClass

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

Bases: InMemoryDataset

The WILLOW-ObjectClass dataset from the “Learning Graphs to Match” paper, containing 10 equal keypoints of at least 40 images in each category. The keypoints contain interpolated features from a pre-trained VGG16 model on ImageNet (relu4_2 and relu5_1).

Parameters:

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

  • category (str) – The category of the images (one of "Car", "Duck", "Face", "Motorbike", "Winebottle").

  • 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)

  • device (str or torch.device, optional) – The device to use for processing the raw data. If set to None, will utilize GPU-processing if available. (default: None)