gammagl.datasets.ModelNet40

class ModelNet40(root=None, transform=None, pre_transform=None, pre_filter=None, split='train', num_points=1024, force_reload: bool = False)

The ModelNet40 benchmark dataset used for classification from the “Dynamic Graph CNN for Learning on Point Clouds” paper, containing 12,311 meshed CAD models from 40 categories.

Parameters:

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

• transform (callable, optional) – A function/transform that takes in an gammagl.data.Graph 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 gammagl.data.Graph object and returns a transformed version. The data object will be transformed before being saved to disk. (default: None)

• split (string, optional) – The type of dataset split ("train", "test").

• num_points (int, optional) – The number of points used to train or test.

• (bool (force_reload) – (default: False)

• optional) (Whether to re-process the dataset.) – (default: False)

url = 'https://shapenet.cs.stanford.edu/media/modelnet40_ply_hdf5_2048.zip'

property raw_file_names: str | List[str] | Tuple

The name of the files in the self.raw_dir folder that must be present in order to skip downloading.

property processed_file_names: str | List[str] | Tuple

The name of the files in the self.processed_dir folder that must be present in order to skip processing.

property num_classes: int

Returns the number of classes in the dataset.

download()

Downloads the dataset to the self.raw_dir folder.

process()

Processes the dataset to the self.processed_dir folder.