import os
from typing import Callable, List, Optional
from torch_geometric.data import (
Data,
InMemoryDataset,
download_url,
extract_zip,
)
from torch_geometric.io import fs
[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 = fs.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])