Skip to content
Permalink
Browse files

Fix typos

  • Loading branch information...
dongkwan-kim committed Aug 9, 2019
1 parent 4cafaa1 commit a03b309e870a7dc134a044ce75787380cb1501d9
@@ -5,7 +5,7 @@ If you are interested in contributing to PyTorch Geometric, your contributions w
1. You want to implement a new feature:
- In general, we accept any features as long as they fit the scope of this package. If you are unsure about this or need help on the design/implementation of your feature, post about it in an issue.
2. You want to fix a bug:
- Feel free to send a Pull Request any time you encounter a bug. Please provide a clear and concise decription of what the bug was. If you are unsure about if this is a bug at all or how to fix, post about it in an issue.
- Feel free to send a Pull Request any time you encounter a bug. Please provide a clear and concise description of what the bug was. If you are unsure about if this is a bug at all or how to fix, post about it in an issue.

Once you finish implementing a feature or bug-fix, please send a Pull Request to https://github.com/rusty1s/pytorch_geometric.

@@ -3,6 +3,6 @@ External Resources

* Matthias Fey and Jan E. Lenssen: **Fast Graph Representation Learning with PyTorch Geometric** [`Paper <https://arxiv.org/abs/1903.02428>`_, `Slides (3.3MB) <http://rusty1s.github.io/pyg_slides.pdf>`_, `Poster (2.3MB) <http://rusty1s.github.io/pyg_poster.pdf>`_, `Notebook <http://htmlpreview.github.io/?https://github.com/rusty1s/rusty1s.github.io/blob/master/pyg_notebook.html>`_]

* Soumith Chintala: **Automatic Differentation, PyTorch and Graph Neural Networks** [`Talk (starting from 26:15) <http://www.ipam.ucla.edu/abstract/?tid=15592&pcode=GLWS4>`_]
* Soumith Chintala: **Automatic Differentiation, PyTorch and Graph Neural Networks** [`Talk (starting from 26:15) <http://www.ipam.ucla.edu/abstract/?tid=15592&pcode=GLWS4>`_]

* Steeve Huang: **Hands-on Graph Neural Networks with PyTorch & PyTorch Geometric** [`Tutorial <https://towardsdatascience.com/hands-on-graph-neural-networks-with-pytorch-pytorch-geometric-359487e221a8>`_, `Code <https://github.com/khuangaf/Pytorch-Geometric-YooChoose>`_]
@@ -24,7 +24,7 @@ class ShapeNet(InMemoryDataset):
:obj:`"Guitar"`, :obj:`"Knife"`, :obj:`"Lamp"`, :obj:`"Laptop"`,
:obj:`"Motorbike"`, :obj:`"Mug"`, :obj:`"Pistol"`, :obj:`"Rocket"`,
:obj:`"Skateboard"`, :obj:`"Table"`).
Can be explicitely set to :obj:`None` to load all categories.
Can be explicitly set to :obj:`None` to load all categories.
(default: :obj:`None`)
train (bool, optional): If :obj:`True`, loads the training dataset,
otherwise the test dataset. (default: :obj:`True`)
@@ -32,7 +32,7 @@ class ARMAConv(torch.nn.Module):
(default: :obj:`1`).
num_layers (int, optional): Number of layers :math:`T`.
(default: :obj:`1`)
act (callable, optional): Activiation function :math:`\sigma`.
act (callable, optional): Activation function :math:`\sigma`.
(default: :meth:`torch.nn.functional.ReLU`)
shared_weights (int, optional): If set to :obj:`True` the layers in
each stack will share the same parameters. (default: :obj:`False`)
@@ -9,7 +9,7 @@

class GCNConv(MessagePassing):
r"""The graph convolutional operator from the `"Semi-supervised
Classfication with Graph Convolutional Networks"
Classification with Graph Convolutional Networks"
<https://arxiv.org/abs/1609.02907>`_ paper
.. math::
@@ -30,13 +30,13 @@ class RENet(torch.nn.Module):
Args:
num_nodes (int): The number of nodes in the knowledge graph.
num_rel (int): The number of relations in the knowledge graph.
num_rels (int): The number of relations in the knowledge graph.
hidden_channels (int): Hidden size of node and relation embeddings.
seq_len (int): The sequence length of past events.
num_layers (int, optional): The number of recurrent layers.
(default: :obj:`1`)
dropout (int): If non-zero, introduces a dropout layer before the final
prediction. (default: :obj:`0`)
dropout (float): If non-zero, introduces a dropout layer before the final
prediction. (default: :obj:`0.`)
bias (bool, optional): If set to :obj:`False`, all layers will not
learn an additive bias. (default: :obj:`True`)
"""
@@ -47,7 +47,7 @@ def __init__(self,
hidden_channels,
seq_len,
num_layers=1,
dropout=0,
dropout=0.,
bias=True):
super(RENet, self).__init__()

@@ -15,7 +15,7 @@ class RandomScale(object):
for three-dimensional positions.
Args:
scale (tuple): scaling factor interval, e.g. :obj:`(a, b)`, then scale
scales (tuple): scaling factor interval, e.g. :obj:`(a, b)`, then scale
is randomly sampled from the range
:math:`a \leq \mathrm{scale} \leq b`.
"""
@@ -11,7 +11,7 @@ def filter_adj(row, col, edge_attr, mask):
def dropout_adj(edge_index, edge_attr=None, p=0.5, force_undirected=False,
num_nodes=None, training=True):
r"""Randomly drops edges from the adjacency matrix
:obj:`(edge_index, edge_attr)` with propability :obj:`p` using samples from
:obj:`(edge_index, edge_attr)` with probability :obj:`p` using samples from
a Bernoulli distribution.
Args:

0 comments on commit a03b309

Please sign in to comment.
You can’t perform that action at this time.