Skip to content

GitLab

Unverified Commit 6b0d42db authored by Junki Ishikawa's avatar Junki Ishikawa Committed by GitHub
Browse files

Fix typo (#2235) 


Co-authored-by: default avatarChao Ma <mctt90@gmail.com>
parent 36daf66f
Hide whitespace changes
Inline Side-by-side
Showing with 3 additions and 3 deletions
python/dgl/nn/pytorch/conv/gatconv.py
View file @ 6b0d42db
...@@ -33,7 +33,7 @@ class GATConv(nn.Module): ...@@ -33,7 +33,7 @@ class GATConv(nn.Module):
---------- ----------
in_feats : int, or pair of ints in_feats : int, or pair of ints
Input feature size; i.e, the number of dimensions of :math:`h_i^{(l)}`. Input feature size; i.e, the number of dimensions of :math:`h_i^{(l)}`.
ATConv can be applied on homogeneous graph and unidirectional GATConv can be applied on homogeneous graph and unidirectional
`bipartite graph <https://docs.dgl.ai/generated/dgl.bipartite.html?highlight=bipartite>`__. `bipartite graph <https://docs.dgl.ai/generated/dgl.bipartite.html?highlight=bipartite>`__.
If the layer is to be applied to a unidirectional bipartite graph, ``in_feats`` If the layer is to be applied to a unidirectional bipartite graph, ``in_feats``
specifies the input feature size on both the source and destination nodes. If specifies the input feature size on both the source and destination nodes. If
......
python/dgl/nn/pytorch/conv/nnconv.py
View file @ 6b0d42db
...@@ -28,7 +28,7 @@ class NNConv(nn.Module): ...@@ -28,7 +28,7 @@ class NNConv(nn.Module):
---------- ----------
in_feats : int in_feats : int
Input feature size; i.e, the number of dimensions of :math:`h_j^{(l)}`. Input feature size; i.e, the number of dimensions of :math:`h_j^{(l)}`.
NN can be applied on homogeneous graph and unidirectional NNConv can be applied on homogeneous graph and unidirectional
`bipartite graph <https://docs.dgl.ai/generated/dgl.bipartite.html?highlight=bipartite>`__. `bipartite graph <https://docs.dgl.ai/generated/dgl.bipartite.html?highlight=bipartite>`__.
If the layer is to be applied on a unidirectional bipartite graph, ``in_feats`` If the layer is to be applied on a unidirectional bipartite graph, ``in_feats``
specifies the input feature size on both the source and destination nodes. If specifies the input feature size on both the source and destination nodes. If
......
python/dgl/nn/pytorch/conv/sageconv.py
View file @ 6b0d42db
...@@ -30,7 +30,7 @@ class SAGEConv(nn.Module): ...@@ -30,7 +30,7 @@ class SAGEConv(nn.Module):
in_feats : int, or pair of ints in_feats : int, or pair of ints
Input feature size; i.e, the number of dimensions of :math:`h_i^{(l)}`. Input feature size; i.e, the number of dimensions of :math:`h_i^{(l)}`.
GATConv can be applied on homogeneous graph and unidirectional SAGEConv can be applied on homogeneous graph and unidirectional
`bipartite graph <https://docs.dgl.ai/generated/dgl.bipartite.html?highlight=bipartite>`__. `bipartite graph <https://docs.dgl.ai/generated/dgl.bipartite.html?highlight=bipartite>`__.
If the layer applies on a unidirectional bipartite graph, ``in_feats`` If the layer applies on a unidirectional bipartite graph, ``in_feats``
specifies the input feature size on both the source and destination nodes. If specifies the input feature size on both the source and destination nodes. If
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment