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

来自“Learning Graphs to Match”论文的WILLOW-ObjectClass数据集， 包含每个类别中至少40张图像的10个相同关键点。 这些关键点包含从预训练的VGG16模型在ImageNet上插值的特征 (relu4_2 和 relu5_1)。

Parameters:

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

  • category (str) – 图像的类别（其中之一为 "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 或 torch.device, 可选) – 用于处理原始数据的设备。如果设置为 None，将使用可用的GPU进行处理。（默认值：None）