pyg-nightly 2.7.0.dev20241113__py3-none-any.whl → 2.7.0.dev20241114__py3-none-any.whl

{pyg_nightly-2.7.0.dev20241113.dist-info → pyg_nightly-2.7.0.dev20241114.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: pyg-nightly
-Version: 2.7.0.dev20241113
+Version: 2.7.0.dev20241114
 Summary: Graph Neural Network Library for PyTorch
 Keywords: deep-learning,pytorch,geometric-deep-learning,graph-neural-networks,graph-convolutional-networks
 Author-email: Matthias Fey <matthias@pyg.org>
@@ -446,12 +446,12 @@ We recommend to start with a minimal installation, and install additional depend
 
 For ease of installation of these extensions, we provide `pip` wheels for all major OS/PyTorch/CUDA combinations, see [here](https://data.pyg.org/whl).
 
-#### PyTorch 2.4
+#### PyTorch 2.5
 
-To install the binaries for PyTorch 2.4.0, simply run
+To install the binaries for PyTorch 2.5.0, simply run
 
 ```
-pip install pyg_lib torch_scatter torch_sparse torch_cluster torch_spline_conv -f https://data.pyg.org/whl/torch-2.4.0+${CUDA}.html
+pip install pyg_lib torch_scatter torch_sparse torch_cluster torch_spline_conv -f https://data.pyg.org/whl/torch-2.5.0+${CUDA}.html
 ```
 
 where `${CUDA}` should be replaced by either `cpu`, `cu118`, `cu121`, or `cu124` depending on your PyTorch installation.
@@ -462,23 +462,23 @@ where `${CUDA}` should be replaced by either `cpu`, `cu118`, `cu121`, or `cu124`
 | **Windows** | ✅    | ✅      | ✅      | ✅      |
 | **macOS**   | ✅    |         |         |         |
 
-#### PyTorch 2.3
+#### PyTorch 2.4
 
-To install the binaries for PyTorch 2.3.0, simply run
+To install the binaries for PyTorch 2.4.0, simply run
 
 ```
-pip install pyg_lib torch_scatter torch_sparse torch_cluster torch_spline_conv -f https://data.pyg.org/whl/torch-2.3.0+${CUDA}.html
+pip install pyg_lib torch_scatter torch_sparse torch_cluster torch_spline_conv -f https://data.pyg.org/whl/torch-2.4.0+${CUDA}.html
 ```
 
-where `${CUDA}` should be replaced by either `cpu`, `cu118`, or `cu121` depending on your PyTorch installation.
+where `${CUDA}` should be replaced by either `cpu`, `cu118`, `cu121`, or `cu124` depending on your PyTorch installation.
 
-|             | `cpu` | `cu118` | `cu121` |
-| ----------- | ----- | ------- | ------- |
-| **Linux**   | ✅    | ✅      | ✅      |
-| **Windows** | ✅    | ✅      | ✅      |
-| **macOS**   | ✅    |         |         |
+|             | `cpu` | `cu118` | `cu121` | `cu124` |
+| ----------- | ----- | ------- | ------- | ------- |
+| **Linux**   | ✅    | ✅      | ✅      | ✅      |
+| **Windows** | ✅    | ✅      | ✅      | ✅      |
+| **macOS**   | ✅    |         |         |         |
 
-**Note:** Binaries of older versions are also provided for PyTorch 1.4.0, PyTorch 1.5.0, PyTorch 1.6.0, PyTorch 1.7.0/1.7.1, PyTorch 1.8.0/1.8.1, PyTorch 1.9.0, PyTorch 1.10.0/1.10.1/1.10.2, PyTorch 1.11.0, PyTorch 1.12.0/1.12.1, PyTorch 1.13.0/1.13.1, PyTorch 2.0.0/2.0.1, PyTorch 2.1.0/2.1.1/2.1.2, and PyTorch 2.2.0/2.2.1/2.2.2 (following the same procedure).
+**Note:** Binaries of older versions are also provided for PyTorch 1.4.0, PyTorch 1.5.0, PyTorch 1.6.0, PyTorch 1.7.0/1.7.1, PyTorch 1.8.0/1.8.1, PyTorch 1.9.0, PyTorch 1.10.0/1.10.1/1.10.2, PyTorch 1.11.0, PyTorch 1.12.0/1.12.1, PyTorch 1.13.0/1.13.1, PyTorch 2.0.0/2.0.1, PyTorch 2.1.0/2.1.1/2.1.2, PyTorch 2.2.0/2.2.1/2.2.2, and PyTorch 2.3.0/2.3.1 (following the same procedure).
 **For older versions, you might need to explicitly specify the latest supported version number** or install via `pip install --no-index` in order to prevent a manual installation from source.
 You can look up the latest supported version number [here](https://data.pyg.org/whl).
 

{pyg_nightly-2.7.0.dev20241113.dist-info → pyg_nightly-2.7.0.dev20241114.dist-info}/RECORD

@@ -1,5 +1,5 @@
-torch_geometric/__init__.py,sha256=Mca3sSBlw54VQCuXnQZuuiaMSeoXOxn1Rvj2mKD91tc,1904
-torch_geometric/_compile.py,sha256=REjj1_qX8YBrva6iqr3AsNiDueTAy2BhLZkdezKL2MY,1322
+torch_geometric/__init__.py,sha256=48k-an8_K-Va5jV0wsOlouiB4PjW_d1wuzw3wABJB3M,1904
+torch_geometric/_compile.py,sha256=f-WQeH4VLi5Hn9lrgztFUCSrN_FImjhQa6BxFzcYC38,1338
 torch_geometric/_onnx.py,sha256=V9ffrIKSqhDw6xUZ12lkuSfNs48cQp2EeJ6Z19GfnVw,349
 torch_geometric/backend.py,sha256=lVaf7aLoVaB3M-UcByUJ1G4T4FOK6LXAg0CF4W3E8jo,1575
 torch_geometric/config_mixin.py,sha256=DGQXStKNiPp4iBvtx7aVoofWcUSuVKEHdG5WUL2oNJs,4230
@@ -18,7 +18,7 @@ torch_geometric/logging.py,sha256=HmHHLiCcM64k-6UYNOSfXPIeSGNAyiGGcn8cD8tlyuQ,85
 torch_geometric/resolver.py,sha256=fn-_6mCpI2xv7eDZnIFcYrHOn0IrwbkWFLDb9laQrWI,1270
 torch_geometric/seed.py,sha256=MJLbVwpb9i8mK3oi32sS__Cq-dRq_afTeoOL_HoA9ko,372
 torch_geometric/template.py,sha256=rqjDWgcSAgTCiV4bkOjWRPaO4PpUdC_RXigzxxBqAu8,1060
-torch_geometric/typing.py,sha256=OU7zhpnwarQ5cCzl8Sfvh5aKr3RDG3tZot7-WO4a_Yo,13865
+torch_geometric/typing.py,sha256=0pxCLue4iqqFC-k5ByqAeyg2mogtWXqgtod3ZOEMq1A,13933
 torch_geometric/warnings.py,sha256=t114CbkrmiqkXaavx5g7OO52dLdktf-U__B5QqYIQvI,413
 torch_geometric/contrib/__init__.py,sha256=0pWkmXfZtbdr-AKwlii5LTFggTEH-MCrSKpZxrtPlVs,352
 torch_geometric/contrib/datasets/__init__.py,sha256=lrGnWsEiJf5zsBRmshGZZFN_uYR2ezDjbj9n9nCpvtk,23
@@ -38,7 +38,7 @@ torch_geometric/data/datapipes.py,sha256=9_Cq3j_7LIF4plQFzbLaqyy0LcpKdAic6yiKgMq
 torch_geometric/data/dataset.py,sha256=TX2AM3OQkMLOx5Ie8IFtFFYuoA3AGeYwoT3ZqW56N7c,16768
 torch_geometric/data/download.py,sha256=kcesTu6jlgmCeePpOxDQOnVhxB_GuZ9iu9ds72KEORc,1889
 torch_geometric/data/extract.py,sha256=X_f0JEo67DF9hOpIlq3QPWXA9RF8uoVFi195UjstzDc,2324
-torch_geometric/data/feature_store.py,sha256=m_VzeKl_WLEPaT_OsPbVdBNUWH2vdKfxk28qCa1iVfA,20153
+torch_geometric/data/feature_store.py,sha256=ma65GAHHEoYiZqHs_CkMGAYxeepGc1Bp0TMXmioIfCs,20044
 torch_geometric/data/graph_store.py,sha256=oFrLDNP5hKf3HWWsFsjcamx5vLIEk8JnLjuGpjrFLdc,13867
 torch_geometric/data/hetero_data.py,sha256=q0L3bENyEvo_BGLPwZPVzh730Aak6sQ7yXoawPgM72E,47982
 torch_geometric/data/hypergraph_data.py,sha256=33hsXW25Yz4Ju8mKajYinZOrkqrUi1SqThG7MlOOYNM,8294
@@ -515,7 +515,7 @@ torch_geometric/transforms/cartesian.py,sha256=_gdFrPP5q3aPmQW6QvYeI8-nvKNVyQF-W
 torch_geometric/transforms/center.py,sha256=4avx4_wm7Q11epOaMQ2YaVcdcTFjozPBEWG2h6GyKc4,645
 torch_geometric/transforms/compose.py,sha256=P5AFGd6s9L-lpb8io1jKIm2LjAccp_6Q2XocR5T1z5c,1658
 torch_geometric/transforms/constant.py,sha256=zDJbO1sEds1vjbRmgzSd-8D8gM4PtvWESuC-gX2qB9E,2005
-torch_geometric/transforms/delaunay.py,sha256=-7JIDKhjk8h1cFGVYiqRszwHFDf5dMzKOiB1ejUah_o,1273
+torch_geometric/transforms/delaunay.py,sha256=2mbTqs7oeDZQdifrqldLaLeCZz7pGd_5VMSLOzKMIGE,2668
 torch_geometric/transforms/distance.py,sha256=DvvI2vAYpxklnKCz3-4w2EXz7AYra0xBZ5m7MAL1tok,2360
 torch_geometric/transforms/face_to_edge.py,sha256=ohAWtpiCs_qHwrrYmz2eLvAcd_bhfPsxkpHdFnAZkhk,2144
 torch_geometric/transforms/feature_propagation.py,sha256=GPiKiGU7OuOpBBJeATlCtAtBUy_DSHUoBnJdDK8T81E,3056
@@ -584,7 +584,7 @@ torch_geometric/utils/_select.py,sha256=BZ5P6-1riR4xhCIJZnsNg5HmeAGelRzH42TpADj9
 torch_geometric/utils/_softmax.py,sha256=6dTVbWX04laemRP-ZFPMS6ymRZtRa8zYF22QCXl_m4w,3242
 torch_geometric/utils/_sort_edge_index.py,sha256=oPS1AkAmPm5Aq8sSGI-e-OkeXOnU5X58Q86eamHi4gA,4500
 torch_geometric/utils/_spmm.py,sha256=uRq21nCgostC2jE6SKfp2xIY4_BtrXOG5YHbWUEPv10,5794
-torch_geometric/utils/_subgraph.py,sha256=T7olS3B4QAy6BbC6FaHIgKT9usTdDBzcRnP-VCGmWL8,18311
+torch_geometric/utils/_subgraph.py,sha256=GcOGNUcVe97tifuQyi5qBZ88A_Wo3-o17l9xCSIsau4,18456
 torch_geometric/utils/_to_dense_adj.py,sha256=hl1sboUBvED5Er66bqLms4VdmxKA-7Y3ozJIR-YIAUc,3606
 torch_geometric/utils/_to_dense_batch.py,sha256=-K5NjjfvjKYKJQ3kXgNIDR7lwMJ_GGISI45b50IGMvY,4582
 torch_geometric/utils/_train_test_split_edges.py,sha256=KnBDgnaKuJYTHUOIlvFtzvkHUe-93DG3ckST4-wOERM,3569
@@ -618,6 +618,6 @@ torch_geometric/utils/undirected.py,sha256=H_nfpI0_WluOG6VfjPyldvcjL4w5USAKWu2x5
 torch_geometric/visualization/__init__.py,sha256=PyR_4K5SafsJrBr6qWrkjKr6GBL1b7FtZybyXCDEVwY,154
 torch_geometric/visualization/graph.py,sha256=ZuLPL92yGRi7lxlqsUPwL_EVVXF7P2kMcveTtW79vpA,4784
 torch_geometric/visualization/influence.py,sha256=CWMvuNA_Nf1sfbJmQgn58yS4OFpeKXeZPe7kEuvkUBw,477
-pyg_nightly-2.7.0.dev20241113.dist-info/WHEEL,sha256=CpUCUxeHQbRN5UGRQHYRJorO5Af-Qy_fHMctcQ8DSGI,82
-pyg_nightly-2.7.0.dev20241113.dist-info/METADATA,sha256=mfvaeek9VqMAvaZRS0W_IUhuyVk-eQA3q3Mylf0w1u0,62897
-pyg_nightly-2.7.0.dev20241113.dist-info/RECORD,,
+pyg_nightly-2.7.0.dev20241114.dist-info/WHEEL,sha256=CpUCUxeHQbRN5UGRQHYRJorO5Af-Qy_fHMctcQ8DSGI,82
+pyg_nightly-2.7.0.dev20241114.dist-info/METADATA,sha256=urxpy2ZlbcTbEvAnn12xbIIGtjyQbXfja_co7d7DC9c,62979
+pyg_nightly-2.7.0.dev20241114.dist-info/RECORD,,

torch_geometric/__init__.py

@@ -30,7 +30,7 @@ from .lazy_loader import LazyLoader
 contrib = LazyLoader('contrib', globals(), 'torch_geometric.contrib')
 graphgym = LazyLoader('graphgym', globals(), 'torch_geometric.graphgym')
 
-__version__ = '2.7.0.dev20241113'
+__version__ = '2.7.0.dev20241114'
 
 __all__ = [
     'Index',

torch_geometric/_compile.py

@@ -38,4 +38,4 @@ def compile(
     """
     warnings.warn("'torch_geometric.compile' is deprecated in favor of "
                   "'torch.compile'")
-    return torch.compile(model, *args, **kwargs)
+    return torch.compile(model, *args, **kwargs)  # type: ignore

torch_geometric/data/feature_store.py

@@ -74,13 +74,6 @@ class TensorAttr(CastMixin):
         r"""Whether the :obj:`TensorAttr` has no unset fields."""
         return all([self.is_set(key) for key in self.__dataclass_fields__])
 
-    def fully_specify(self) -> 'TensorAttr':
-        r"""Sets all :obj:`UNSET` fields to :obj:`None`."""
-        for key in self.__dataclass_fields__:
-            if not self.is_set(key):
-                setattr(self, key, None)
-        return self
-
     def update(self, attr: 'TensorAttr') -> 'TensorAttr':
         r"""Updates an :class:`TensorAttr` with set attributes from another
         :class:`TensorAttr`.
@@ -230,10 +223,11 @@ class AttrView(CastMixin):
 
             store[group_name, attr_name]()
         """
-        # Set all UNSET values to None:
-        out = copy.copy(self)
-        out._attr.fully_specify()
-        return out._store.get_tensor(out._attr)
+        attr = copy.copy(self._attr)
+        for key in attr.__dataclass_fields__:  # Set all UNSET values to None.
+            if not attr.is_set(key):
+                setattr(attr, key, None)
+        return self._store.get_tensor(attr)
 
     def __copy__(self) -> 'AttrView':
         out = self.__class__.__new__(self.__class__)
@@ -479,9 +473,7 @@ class FeatureStore(ABC):
         # CastMixin will handle the case of key being a tuple or TensorAttr
         # object:
         key = self._tensor_attr_cls.cast(key)
-        # We need to fully-specify the key for __setitem__ as it does not make
-        # sense to work with a view here:
-        key.fully_specify()
+        assert key.is_fully_specified()
         self.put_tensor(value, key)
 
     def __getitem__(self, key: TensorAttr) -> Any:
@@ -503,13 +495,16 @@ class FeatureStore(ABC):
         # If the view is not fully-specified, return a :class:`AttrView`:
         return self.view(attr)
 
-    def __delitem__(self, key: TensorAttr):
+    def __delitem__(self, attr: TensorAttr):
         r"""Supports :obj:`del store[tensor_attr]`."""
         # CastMixin will handle the case of key being a tuple or TensorAttr
         # object:
-        key = self._tensor_attr_cls.cast(key)
-        key.fully_specify()
-        self.remove_tensor(key)
+        attr = self._tensor_attr_cls.cast(attr)
+        attr = copy.copy(attr)
+        for key in attr.__dataclass_fields__:  # Set all UNSET values to None.
+            if not attr.is_set(key):
+                setattr(attr, key, None)
+        self.remove_tensor(attr)
 
     def __iter__(self):
         raise NotImplementedError

torch_geometric/transforms/delaunay.py

@@ -1,3 +1,5 @@
+from typing import List
+
 import torch
 
 from torch_geometric.data import Data
@@ -5,30 +7,78 @@ from torch_geometric.data.datapipes import functional_transform
 from torch_geometric.transforms import BaseTransform
 
 
+class _QhullTransform(BaseTransform):
+    r"""Q-hull implementation of delaunay triangulation."""
+    def forward(self, data: Data) -> Data:
+        assert data.pos is not None
+        import scipy.spatial
+
+        pos = data.pos.cpu().numpy()
+        tri = scipy.spatial.Delaunay(pos, qhull_options='QJ')
+        face = torch.from_numpy(tri.simplices)
+
+        data.face = face.t().contiguous().to(data.pos.device, torch.long)
+        return data
+
+
+class _ShullTransform(BaseTransform):
+    r"""Sweep-hull implementation of delaunay triangulation."""
+    def forward(self, data: Data) -> Data:
+        assert data.pos is not None
+        from torch_delaunay.functional import shull2d
+
+        face = shull2d(data.pos.cpu())
+        data.face = face.t().contiguous().to(data.pos.device)
+        return data
+
+
+class _SequentialTransform(BaseTransform):
+    r"""Runs the first successful transformation.
+
+    All intermediate exceptions are suppressed except the last.
+    """
+    def __init__(self, transforms: List[BaseTransform]) -> None:
+        assert len(transforms) > 0
+        self.transforms = transforms
+
+    def forward(self, data: Data) -> Data:
+        for i, transform in enumerate(self.transforms):
+            try:
+                return transform.forward(data)
+            except ImportError as e:
+                if i == len(self.transforms) - 1:
+                    raise e
+        return data
+
+
 @functional_transform('delaunay')
 class Delaunay(BaseTransform):
     r"""Computes the delaunay triangulation of a set of points
     (functional name: :obj:`delaunay`).
+
+    .. hint::
+        Consider installing the
+        `torch_delaunay <https://github.com/ybubnov/torch_delaunay>`_ package
+        to speed up computation.
     """
-    def forward(self, data: Data) -> Data:
-        import scipy.spatial
+    def __init__(self) -> None:
+        self._transform = _SequentialTransform([
+            _ShullTransform(),
+            _QhullTransform(),
+        ])
 
+    def forward(self, data: Data) -> Data:
         assert data.pos is not None
+        device = data.pos.device
 
         if data.pos.size(0) < 2:
-            data.edge_index = torch.tensor([], dtype=torch.long,
-                                           device=data.pos.device).view(2, 0)
-        if data.pos.size(0) == 2:
-            data.edge_index = torch.tensor([[0, 1], [1, 0]], dtype=torch.long,
-                                           device=data.pos.device)
+            data.edge_index = torch.empty(2, 0, dtype=torch.long,
+                                          device=device)
+        elif data.pos.size(0) == 2:
+            data.edge_index = torch.tensor([[0, 1], [1, 0]], device=device)
         elif data.pos.size(0) == 3:
-            data.face = torch.tensor([[0], [1], [2]], dtype=torch.long,
-                                     device=data.pos.device)
-        if data.pos.size(0) > 3:
-            pos = data.pos.cpu().numpy()
-            tri = scipy.spatial.Delaunay(pos, qhull_options='QJ')
-            face = torch.from_numpy(tri.simplices)
-
-            data.face = face.t().contiguous().to(data.pos.device, torch.long)
+            data.face = torch.tensor([[0], [1], [2]], device=device)
+        else:
+            data = self._transform.forward(data)
 
         return data

torch_geometric/typing.py

@@ -15,6 +15,7 @@ WITH_PT22 = WITH_PT20 and int(torch.__version__.split('.')[1]) >= 2
 WITH_PT23 = WITH_PT20 and int(torch.__version__.split('.')[1]) >= 3
 WITH_PT24 = WITH_PT20 and int(torch.__version__.split('.')[1]) >= 4
 WITH_PT25 = WITH_PT20 and int(torch.__version__.split('.')[1]) >= 5
+WITH_PT26 = WITH_PT20 and int(torch.__version__.split('.')[1]) >= 6
 WITH_PT111 = WITH_PT20 or int(torch.__version__.split('.')[1]) >= 11
 WITH_PT112 = WITH_PT20 or int(torch.__version__.split('.')[1]) >= 12
 WITH_PT113 = WITH_PT20 or int(torch.__version__.split('.')[1]) >= 13

torch_geometric/utils/_subgraph.py

@@ -346,10 +346,12 @@ def k_hop_subgraph(
 
     subsets = [node_idx]
 
+    preserved_edge_mask = torch.zeros_like(edge_mask)
     for _ in range(num_hops):
         node_mask.fill_(False)
         node_mask[subsets[-1]] = True
         torch.index_select(node_mask, 0, row, out=edge_mask)
+        preserved_edge_mask |= edge_mask
         subsets.append(col[edge_mask])
 
     subset, inv = torch.cat(subsets).unique(return_inverse=True)
@@ -360,6 +362,8 @@ def k_hop_subgraph(
 
     if not directed:
         edge_mask = node_mask[row] & node_mask[col]
+    else:
+        edge_mask = preserved_edge_mask
 
     edge_index = edge_index[:, edge_mask]