Removed unnecessary colons and fixed typos in the documentation

CHANGELOG.md

@@ -12,6 +12,7 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/).
 - Added support for graph-level outputs in `to_hetero` ([#4582](https://github.com/pyg-team/pytorch_geometric/pull/4582))
 - Added `CHANGELOG.md` ([#4581](https://github.com/pyg-team/pytorch_geometric/pull/4581))
 ### Changed
+- Removed unnecessary colons and fixed typos in the documentation ([#4616](https://github.com/pyg-team/pytorch_geometric/pull/4616))
 - The `bias` argument in `TAGConv` is now actually applied ([#4597](https://github.com/pyg-team/pytorch_geometric/pull/4597))
 - Fixed subclass behaviour of `process` and `download` in `Datsaet` ([#4586](https://github.com/pyg-team/pytorch_geometric/pull/4586))
 ### Removed

torch_geometric/data/lightning_datamodule.py

@@ -103,10 +103,10 @@ class LightningDataset(LightningDataModule):
             trainer.fit(model, datamodule)
 
     Args:
-        train_dataset: (Dataset) The training dataset.
-        val_dataset: (Dataset, optional) The validation dataset.
+        train_dataset (Dataset): The training dataset.
+        val_dataset (Dataset, optional): The validation dataset.
             (default: :obj:`None`)
-        test_dataset: (Dataset, optional) The test dataset.
+        test_dataset (Dataset, optional): The test dataset.
             (default: :obj:`None`)
         batch_size (int, optional): How many samples per batch to load.
             (default: :obj:`1`)

torch_geometric/datasets/tu_dataset.py

@@ -50,7 +50,7 @@ class TUDataset(InMemoryDataset):
         use_edge_attr (bool, optional): If :obj:`True`, the dataset will
             contain additional continuous edge attributes (if present).
             (default: :obj:`False`)
-        cleaned: (bool, optional): If :obj:`True`, the dataset will
+        cleaned (bool, optional): If :obj:`True`, the dataset will
             contain only non-isomorphic graphs. (default: :obj:`False`)
 
     Stats:

torch_geometric/nn/conv/cluster_gcn_conv.py

@@ -25,7 +25,7 @@ class ClusterGCNConv(MessagePassing):
         in_channels (int): Size of each input sample, or :obj:`-1` to derive
             the size from the first input(s) to the forward method.
         out_channels (int): Size of each output sample.
-        diag_lambda: (float, optional): Diagonal enhancement value
+        diag_lambda (float, optional): Diagonal enhancement value
             :math:`\lambda`. (default: :obj:`0.`)
         add_self_loops (bool, optional): If set to :obj:`False`, will not add
             self-loops to the input graph. (default: :obj:`True`)

torch_geometric/nn/conv/han_conv.py

@@ -109,13 +109,13 @@ def forward(
         Args:
             x_dict (Dict[str, Tensor]): A dictionary holding input node
                 features  for each individual node type.
-            edge_index_dict: (Dict[str, Union[Tensor, SparseTensor]]): A
+            edge_index_dict (Dict[str, Union[Tensor, SparseTensor]]): A
                 dictionary holding graph connectivity information for each
                 individual edge type, either as a :obj:`torch.LongTensor` of
                 shape :obj:`[2, num_edges]` or a
                 :obj:`torch_sparse.SparseTensor`.
 
-        :rtype: :obj:`Dict[str, Optional[Tensor]]` - The ouput node embeddings
+        :rtype: :obj:`Dict[str, Optional[Tensor]]` - The output node embeddings
             for each node type.
             In case a node type does not receive any message, its output will
             be set to :obj:`None`.

torch_geometric/nn/conv/hgt_conv.py

@@ -121,13 +121,13 @@ def forward(
         Args:
             x_dict (Dict[str, Tensor]): A dictionary holding input node
                 features  for each individual node type.
-            edge_index_dict: (Dict[str, Union[Tensor, SparseTensor]]): A
+            edge_index_dict (Dict[str, Union[Tensor, SparseTensor]]): A
                 dictionary holding graph connectivity information for each
                 individual edge type, either as a :obj:`torch.LongTensor` of
                 shape :obj:`[2, num_edges]` or a
                 :obj:`torch_sparse.SparseTensor`.
 
-        :rtype: :obj:`Dict[str, Optional[Tensor]]` - The ouput node embeddings
+        :rtype: :obj:`Dict[str, Optional[Tensor]]` - The output node embeddings
             for each node type.
             In case a node type does not receive any message, its output will
             be set to :obj:`None`.

torch_geometric/nn/conv/pna_conv.py

@@ -55,7 +55,7 @@ class PNAConv(MessagePassing):
         aggregators (list of str): Set of aggregation function identifiers,
             namely :obj:`"sum"`, :obj:`"mean"`, :obj:`"min"`, :obj:`"max"`,
             :obj:`"var"` and :obj:`"std"`.
-        scalers: (list of str): Set of scaling function identifiers, namely
+        scalers (list of str): Set of scaling function identifiers, namely
             :obj:`"identity"`, :obj:`"amplification"`,
             :obj:`"attenuation"`, :obj:`"linear"` and
             :obj:`"inverse_linear"`.

torch_geometric/nn/conv/point_transformer_conv.py

@@ -44,13 +44,13 @@ class PointTransformerConv(MessagePassing):
             A tuple corresponds to the sizes of source and target
             dimensionalities.
         out_channels (int): Size of each output sample.
-        pos_nn : (torch.nn.Module, optional): A neural network
+        pos_nn (torch.nn.Module, optional): A neural network
             :math:`h_\mathbf{\Theta}` which maps relative spatial coordinates
             :obj:`pos_j - pos_i` of shape :obj:`[-1, 3]` to shape
             :obj:`[-1, out_channels]`.
             Will default to a :class:`torch.nn.Linear` transformation if not
             further specified. (default: :obj:`None`)
-        attn_nn : (torch.nn.Module, optional): A neural network
+        attn_nn (torch.nn.Module, optional): A neural network
             :math:`\gamma_\mathbf{\Theta}` which maps transformed
             node features of shape :obj:`[-1, out_channels]`
             to shape :obj:`[-1, out_channels]`. (default: :obj:`None`)

torch_geometric/nn/fx.py

@@ -60,7 +60,7 @@ class Transformer(object):
             In case :obj:`input_map` is not further specified, will try to
             automatically determine the correct type of input arguments.
             (default: :obj:`None`)
-        debug: (bool, optional): If set to :obj:`True`, will perform
+        debug (bool, optional): If set to :obj:`True`, will perform
             transformation in debug mode. (default: :obj:`False`)
     """
     def __init__(

torch_geometric/nn/models/deepgcn.py

@@ -40,7 +40,7 @@ class DeepGCNLayer(torch.nn.Module):
         block (string, optional): The skip connection operation to use
             (:obj:`"res+"`, :obj:`"res"`, :obj:`"dense"` or :obj:`"plain"`).
             (default: :obj:`"res+"`)
-        dropout: (float, optional): Whether to apply or dropout.
+        dropout (float, optional): Whether to apply or dropout.
             (default: :obj:`0.`)
         ckpt_grad (bool, optional): If set to :obj:`True`, will checkpoint this
             part of the model. Checkpointing works by trading compute for

torch_geometric/nn/models/dimenet.py

@@ -269,20 +269,20 @@ class DimeNet(torch.nn.Module):
         num_bilinear (int): Size of the bilinear layer tensor.
         num_spherical (int): Number of spherical harmonics.
         num_radial (int): Number of radial basis functions.
-        cutoff: (float, optional): Cutoff distance for interatomic
+        cutoff (float, optional): Cutoff distance for interatomic
             interactions. (default: :obj:`5.0`)
         max_num_neighbors (int, optional): The maximum number of neighbors to
             collect for each node within the :attr:`cutoff` distance.
             (default: :obj:`32`)
         envelope_exponent (int, optional): Shape of the smooth cutoff.
             (default: :obj:`5`)
-        num_before_skip: (int, optional): Number of residual layers in the
+        num_before_skip (int, optional): Number of residual layers in the
             interaction blocks before the skip connection. (default: :obj:`1`)
-        num_after_skip: (int, optional): Number of residual layers in the
+        num_after_skip (int, optional): Number of residual layers in the
             interaction blocks after the skip connection. (default: :obj:`2`)
-        num_output_layers: (int, optional): Number of linear layers for the
+        num_output_layers (int, optional): Number of linear layers for the
             output blocks. (default: :obj:`3`)
-        act: (Callable, optional): The activation funtion.
+        act (Callable, optional): The activation function.
             (default: :obj:`swish`)
     """
 

torch_geometric/nn/to_hetero_transformer.py

@@ -104,7 +104,7 @@ def forward(self, x, edge_index):
             In case :obj:`input_map` is not further specified, will try to
             automatically determine the correct type of input arguments.
             (default: :obj:`None`)
-        debug: (bool, optional): If set to :obj:`True`, will perform
+        debug (bool, optional): If set to :obj:`True`, will perform
             transformation in debug mode. (default: :obj:`False`)
     """
     transformer = ToHeteroTransformer(module, metadata, aggr, input_map, debug)

torch_geometric/nn/to_hetero_with_bases_transformer.py

@@ -125,7 +125,7 @@ def forward(self, x, edge_index):
             In case :obj:`input_map` is not further specified, will try to
             automatically determine the correct type of input arguments.
             (default: :obj:`None`)
-        debug: (bool, optional): If set to :obj:`True`, will perform
+        debug (bool, optional): If set to :obj:`True`, will perform
             transformation in debug mode. (default: :obj:`False`)
     """
     transformer = ToHeteroWithBasesTransformer(module, metadata, num_bases,

torch_geometric/transforms/add_self_loops.py

@@ -14,7 +14,7 @@ class AddSelfLoops(BaseTransform):
     (functional name: :obj:`add_self_loops`).
 
     Args:
-        attr: (str, optional): The name of the attribute of edge weights
+        attr (str, optional): The name of the attribute of edge weights
             or multi-dimensional edge features to pass to
             :meth:`torch_geometric.utils.add_self_loops`.
             (default: :obj:`"edge_weight"`)

torch_geometric/transforms/to_sparse_tensor.py

@@ -23,7 +23,7 @@ class ToSparseTensor(BaseTransform):
         :obj:`data.edge_index` for now.
 
     Args:
-        attr: (str, optional): The name of the attribute to add as a value to
+        attr (str, optional): The name of the attribute to add as a value to
             the :class:`~torch_sparse.SparseTensor` object (if present).
             (default: :obj:`edge_weight`)
         remove_edge_index (bool, optional): If set to :obj:`False`, the

torch_geometric/utils/subgraph.py

@@ -147,7 +147,7 @@ def k_hop_subgraph(node_idx, num_hops, edge_index, relabel_nodes=False,
     Args:
         node_idx (int, list, tuple or :obj:`torch.Tensor`): The central
             node(s).
-        num_hops: (int): The number of hops :math:`k`.
+        num_hops (int): The number of hops :math:`k`.
         edge_index (LongTensor): The edge indices.
         relabel_nodes (bool, optional): If set to :obj:`True`, the resulting
             :obj:`edge_index` will be relabeled to hold consecutive indices