Do not fill InMemoryDataset cache on dataset.num_features (#5264)

* do not fill cache

* changelog

CHANGELOG.md

@@ -13,8 +13,9 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/).
 - Added `BaseStorage.get()` functionality ([#5240](https://github.com/pyg-team/pytorch_geometric/pull/5240))
 - Added a test to confirm that `to_hetero` works with `SparseTensor` ([#5222](https://github.com/pyg-team/pytorch_geometric/pull/5222))
 ### Changed
-- Changed tests relying on `dblp` datasets to instead use  synthetic data. ([#5250](https://github.com/pyg-team/pytorch_geometric/pull/5250))
-- Fixed a bug for the initialization of activation function examples in `custom_graphgym`. ([#5243](https://github.com/pyg-team/pytorch_geometric/pull/5243))
+- Do not fill `InMemoryDataset` cache on `dataset.num_features` ([#5264](https://github.com/pyg-team/pytorch_geometric/pull/5264))
+- Changed tests relying on `dblp` datasets to instead use  synthetic data ([#5250](https://github.com/pyg-team/pytorch_geometric/pull/5250))
+- Fixed a bug for the initialization of activation function examples in `custom_graphgym` ([#5243](https://github.com/pyg-team/pytorch_geometric/pull/5243))
 ### Removed
 
 ## [2.1.0] - 2022-08-17

torch_geometric/data/dataset.py

@@ -101,6 +101,9 @@ def processed_dir(self) -> str:
     def num_node_features(self) -> int:
         r"""Returns the number of features per node in the dataset."""
         data = self[0]
+        # Do not fill cache for `InMemoryDataset`:
+        if hasattr(self, '_data_list') and self._data_list is not None:
+            self._data_list[0] = None
         data = data[0] if isinstance(data, tuple) else data
         if hasattr(data, 'num_node_features'):
             return data.num_node_features
@@ -117,6 +120,9 @@ def num_features(self) -> int:
     def num_edge_features(self) -> int:
         r"""Returns the number of features per edge in the dataset."""
         data = self[0]
+        # Do not fill cache for `InMemoryDataset`:
+        if hasattr(self, '_data_list') and self._data_list is not None:
+            self._data_list[0] = None
         data = data[0] if isinstance(data, tuple) else data
         if hasattr(data, 'num_edge_features'):
             return data.num_edge_features