pyg-nightly 2.7.0.dev20241111__tar.gz → 2.7.0.dev20241114__tar.gz

{pyg_nightly-2.7.0.dev20241111 → pyg_nightly-2.7.0.dev20241114}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: pyg-nightly
-Version: 2.7.0.dev20241111
+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.dev20241111 → pyg_nightly-2.7.0.dev20241114}/README.md

@@ -371,12 +371,12 @@ 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 `${CUDA}` should be replaced by either `cpu`, `cu118`, `cu121`, or `cu124` depending on your PyTorch installation.
@@ -387,23 +387,23 @@ where `${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.dev20241111 → pyg_nightly-2.7.0.dev20241114}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend="flit_core.buildapi"
 
 [project]
 name="pyg-nightly"
-version="2.7.0.dev20241111"
+version="2.7.0.dev20241114"
 authors=[
     {name="Matthias Fey", email="matthias@pyg.org"},
 ]

{pyg_nightly-2.7.0.dev20241111 → pyg_nightly-2.7.0.dev20241114}/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.dev20241111'
+__version__ = '2.7.0.dev20241114'
 
 __all__ = [
     'Index',

{pyg_nightly-2.7.0.dev20241111 → pyg_nightly-2.7.0.dev20241114}/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

{pyg_nightly-2.7.0.dev20241111 → pyg_nightly-2.7.0.dev20241114}/torch_geometric/data/data.py

@@ -659,7 +659,13 @@ class Data(BaseData, FeatureStore, GraphStore):
                 return value.get_dim_size()
             return int(value.max()) + 1
         elif 'index' in key or key == 'face':
-            return self.num_nodes
+            num_nodes = self.num_nodes
+            if num_nodes is None:
+                raise RuntimeError(f"Unable to infer 'num_nodes' from the "
+                                   f"attribute '{key}'. Please explicitly set "
+                                   f"'num_nodes' as an attribute of 'data' to "
+                                   f"prevent this error")
+            return num_nodes
         else:
             return 0
 

{pyg_nightly-2.7.0.dev20241111 → pyg_nightly-2.7.0.dev20241114}/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

pyg_nightly-2.7.0.dev20241114/torch_geometric/transforms/delaunay.py

@@ -0,0 +1,84 @@
+from typing import List
+
+import torch
+
+from torch_geometric.data import Data
+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 __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.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]], device=device)
+        else:
+            data = self._transform.forward(data)
+
+        return data

pyg_nightly-2.7.0.dev20241114/torch_geometric/transforms/face_to_edge.py

@@ -0,0 +1,61 @@
+import torch
+
+from torch_geometric.data import Data
+from torch_geometric.data.datapipes import functional_transform
+from torch_geometric.transforms import BaseTransform
+from torch_geometric.utils import to_undirected
+
+
+@functional_transform('face_to_edge')
+class FaceToEdge(BaseTransform):
+    r"""Converts mesh faces of shape :obj:`[3, num_faces]` or
+    :obj:`[4, num_faces]` to edge indices of shape :obj:`[2, num_edges]`
+    (functional name: :obj:`face_to_edge`).
+
+    This transform supports both 2D triangular faces, represented by a
+    tensor of shape :obj:`[3, num_faces]`, and 3D tetrahedral mesh faces,
+    represented by a tensor of shape :obj:`[4, num_faces]`. It will convert
+    these faces into edge indices, where each edge is defined by the indices
+    of its two endpoints.
+
+    Args:
+        remove_faces (bool, optional): If set to :obj:`False`, the face tensor
+            will not be removed.
+    """
+    def __init__(self, remove_faces: bool = True) -> None:
+        self.remove_faces = remove_faces
+
+    def forward(self, data: Data) -> Data:
+        if hasattr(data, 'face'):
+            assert data.face is not None
+            face = data.face
+
+            if face.size(0) not in [3, 4]:
+                raise RuntimeError(f"Expected 'face' tensor with shape "
+                                   f"[3, num_faces] or [4, num_faces] "
+                                   f"(got {list(face.size())})")
+
+            if face.size()[0] == 3:
+                edge_index = torch.cat([
+                    face[:2],
+                    face[1:],
+                    face[::2],
+                ], dim=1)
+            else:
+                assert face.size()[0] == 4
+                edge_index = torch.cat([
+                    face[:2],
+                    face[1:3],
+                    face[2:4],
+                    face[::2],
+                    face[1::2],
+                    face[::3],
+                ], dim=1)
+
+            edge_index = to_undirected(edge_index, num_nodes=data.num_nodes)
+
+            data.edge_index = edge_index
+            if self.remove_faces:
+                data.face = None
+
+        return data

{pyg_nightly-2.7.0.dev20241111 → pyg_nightly-2.7.0.dev20241114}/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

{pyg_nightly-2.7.0.dev20241111 → pyg_nightly-2.7.0.dev20241114}/torch_geometric/utils/_scatter.py

@@ -351,5 +351,5 @@ def group_cat(
     """
     assert len(tensors) == len(indices)
     index, perm = torch.cat(indices).sort(stable=True)
-    out = torch.cat(tensors, dim=0)[perm]
+    out = torch.cat(tensors, dim=dim).index_select(dim, perm)
     return (out, index) if return_index else out

{pyg_nightly-2.7.0.dev20241111 → pyg_nightly-2.7.0.dev20241114}/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]
 

{pyg_nightly-2.7.0.dev20241111 → pyg_nightly-2.7.0.dev20241114}/torch_geometric/visualization/graph.py

@@ -132,7 +132,7 @@ def _visualize_graph_via_networkx(
             xy=pos[src],
             xytext=pos[dst],
             arrowprops=dict(
-                arrowstyle="->",
+                arrowstyle="<-",
                 alpha=data['alpha'],
                 shrinkA=sqrt(node_size) / 2.0,
                 shrinkB=sqrt(node_size) / 2.0,

pyg_nightly-2.7.0.dev20241111/torch_geometric/transforms/delaunay.py

@@ -1,34 +0,0 @@
-import torch
-
-from torch_geometric.data import Data
-from torch_geometric.data.datapipes import functional_transform
-from torch_geometric.transforms import BaseTransform
-
-
-@functional_transform('delaunay')
-class Delaunay(BaseTransform):
-    r"""Computes the delaunay triangulation of a set of points
-    (functional name: :obj:`delaunay`).
-    """
-    def forward(self, data: Data) -> Data:
-        import scipy.spatial
-
-        assert data.pos is not None
-
-        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)
-        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)
-
-        return data

pyg_nightly-2.7.0.dev20241111/torch_geometric/transforms/face_to_edge.py

@@ -1,32 +0,0 @@
-import torch
-
-from torch_geometric.data import Data
-from torch_geometric.data.datapipes import functional_transform
-from torch_geometric.transforms import BaseTransform
-from torch_geometric.utils import to_undirected
-
-
-@functional_transform('face_to_edge')
-class FaceToEdge(BaseTransform):
-    r"""Converts mesh faces :obj:`[3, num_faces]` to edge indices
-    :obj:`[2, num_edges]` (functional name: :obj:`face_to_edge`).
-
-    Args:
-        remove_faces (bool, optional): If set to :obj:`False`, the face tensor
-            will not be removed.
-    """
-    def __init__(self, remove_faces: bool = True) -> None:
-        self.remove_faces = remove_faces
-
-    def forward(self, data: Data) -> Data:
-        if hasattr(data, 'face'):
-            assert data.face is not None
-            face = data.face
-            edge_index = torch.cat([face[:2], face[1:], face[::2]], dim=1)
-            edge_index = to_undirected(edge_index, num_nodes=data.num_nodes)
-
-            data.edge_index = edge_index
-            if self.remove_faces:
-                data.face = None
-
-        return data