Skip to content

Commit

Permalink
Tutorial 7: Correcting dl2021 reference
Browse files Browse the repository at this point in the history
  • Loading branch information
phlippe committed Dec 2, 2021
1 parent 5c0daea commit ce4b263
Showing 1 changed file with 2 additions and 2 deletions.
4 changes: 2 additions & 2 deletions docs/tutorial_notebooks/tutorial7/GNN_overview.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -502,7 +502,7 @@
"source": [
"## PyTorch Geometric\n",
"\n",
"We had mentioned before that implementing graph networks with adjacency matrix is simple and straight-forward but can be computationally expensive for large graphs. Many real-world graphs can reach over 200k nodes, for which adjacency matrix-based implementations fail. There are a lot of optimizations possible when implementing GNNs, and luckily, there exist packages that provide such layers. The most popular packages for PyTorch are [PyTorch Geometric](https://pytorch-geometric.readthedocs.io/en/latest/) and the [Deep Graph Library](https://www.dgl.ai/) (the latter being actually framework agnostic). Which one to use depends on the project you are planning to do and personal taste. In this tutorial, we will look at PyTorch Geometric as part of the PyTorch family. Similar to PyTorch Lightning, PyTorch Geometric is not installed by default on GoogleColab (and actually also not in our `dl2020` environment due to many dependencies that would be unnecessary for the practicals). Hence, let's import and/or install it below:"
"We had mentioned before that implementing graph networks with adjacency matrix is simple and straight-forward but can be computationally expensive for large graphs. Many real-world graphs can reach over 200k nodes, for which adjacency matrix-based implementations fail. There are a lot of optimizations possible when implementing GNNs, and luckily, there exist packages that provide such layers. The most popular packages for PyTorch are [PyTorch Geometric](https://pytorch-geometric.readthedocs.io/en/latest/) and the [Deep Graph Library](https://www.dgl.ai/) (the latter being actually framework agnostic). Which one to use depends on the project you are planning to do and personal taste. In this tutorial, we will look at PyTorch Geometric as part of the PyTorch family. Similar to PyTorch Lightning, PyTorch Geometric is not installed by default on GoogleColab (and actually also not in our `dl2021` environment due to many dependencies that would be unnecessary for the practicals). Hence, let's import and/or install it below:"
]
},
{
Expand Down Expand Up @@ -1361,7 +1361,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.9"
"version": "3.8.2"
}
},
"nbformat": 4,
Expand Down

0 comments on commit ce4b263

Please sign in to comment.