Source code for torch_geometric.datasets.mnist_superpixels

import os
from typing import Callable, List, Optional

import torch

from torch_geometric.data import (
    Data,
    InMemoryDataset,
    download_url,
    extract_zip,
)


[docs]class MNISTSuperpixels(InMemoryDataset): r"""MNIST superpixels dataset from the `"Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs" <https://arxiv.org/abs/1611.08402>`_ paper, containing 70,000 graphs with 75 nodes each. Every graph is labeled by one of 10 classes. Args: root (str): Root directory where the dataset should be saved. train (bool, optional): If :obj:`True`, loads the training dataset, otherwise the test dataset. (default: :obj:`True`) transform (callable, optional): A function/transform that takes in an :obj:`torch_geometric.data.Data` object and returns a transformed version. The data object will be transformed before every access. (default: :obj:`None`) pre_transform (callable, optional): A function/transform that takes in an :obj:`torch_geometric.data.Data` object and returns a transformed version. The data object will be transformed before being saved to disk. (default: :obj:`None`) pre_filter (callable, optional): A function that takes in an :obj:`torch_geometric.data.Data` object and returns a boolean value, indicating whether the data object should be included in the final dataset. (default: :obj:`None`) force_reload (bool, optional): Whether to re-process the dataset. (default: :obj:`False`) **STATS:** .. list-table:: :widths: 10 10 10 10 10 :header-rows: 1 * - #graphs - #nodes - #edges - #features - #classes * - 70,000 - 75 - ~1,393.0 - 1 - 10 """ url = 'https://data.pyg.org/datasets/MNISTSuperpixels.zip' def __init__( self, root: str, train: bool = True, transform: Optional[Callable] = None, pre_transform: Optional[Callable] = None, pre_filter: Optional[Callable] = None, force_reload: bool = False, ) -> None: super().__init__(root, transform, pre_transform, pre_filter, force_reload=force_reload) path = self.processed_paths[0] if train else self.processed_paths[1] self.load(path) @property def raw_file_names(self) -> str: return 'MNISTSuperpixels.pt' @property def processed_file_names(self) -> List[str]: return ['train_data.pt', 'test_data.pt'] def download(self) -> None: path = download_url(self.url, self.raw_dir) extract_zip(path, self.raw_dir) os.unlink(path) def process(self) -> None: inputs = torch.load(self.raw_paths[0]) for i in range(len(inputs)): data_list = [Data(**data_dict) for data_dict in inputs[i]] if self.pre_filter is not None: data_list = [d for d in data_list if self.pre_filter(d)] if self.pre_transform is not None: data_list = [self.pre_transform(d) for d in data_list] self.save(data_list, self.processed_paths[i])