From 80262da3cc75d0e1b7937c76196b505649f5937e Mon Sep 17 00:00:00 2001 From: Zecheng Zhang Date: Tue, 6 Apr 2021 22:01:37 -0700 Subject: [PATCH] Update docs and README --- README.md | 2 +- docs/source/notes/introduction.rst | 4 ++-- tests/README.md | 7 +++++++ 3 files changed, 10 insertions(+), 3 deletions(-) create mode 100644 tests/README.md diff --git a/README.md b/README.md index 4ae13df..17739df 100644 --- a/README.md +++ b/README.md @@ -2,7 +2,7 @@ [![PyPI](https://img.shields.io/pypi/v/deepsnap.svg?color=brightgreen)](https://pypi.org/project/deepsnap/) [![License](https://img.shields.io/badge/license-MIT-blue.svg)](https://github.com/snap-stanford/deepsnap/blob/master/LICENSE) [![Build Status](https://travis-ci.org/snap-stanford/deepsnap.svg?branch=master)](https://travis-ci.org/github/snap-stanford/deepsnap) [![Downloads](https://pepy.tech/badge/deepsnap)](https://pepy.tech/project/deepsnap) [![Repo size](https://img.shields.io/github/repo-size/snap-stanford/deepsnap?color=yellow)](https://github.com/snap-stanford/deepsnap/archive/refs/heads/master.zip) -**[Documentation](https://snap.stanford.edu/deepsnap/)** | **[Examples](https://github.com/snap-stanford/deepsnap/tree/master/examples)** +**[Documentation](https://snap.stanford.edu/deepsnap/)** | **[Examples](https://github.com/snap-stanford/deepsnap/tree/master/examples)** | **[Colab Notebooks](http://snap.stanford.edu/deepsnap/notes/colab.html)** DeepSNAP is a Python library to assist efficient deep learning on graphs. DeepSNAP features in its support for flexible graph manipulation, standard pipeline, heterogeneous graphs and simple API. diff --git a/docs/source/notes/introduction.rst b/docs/source/notes/introduction.rst index 197b732..0cf1ea8 100644 --- a/docs/source/notes/introduction.rst +++ b/docs/source/notes/introduction.rst @@ -404,8 +404,8 @@ Dataset splitting for heterogeneous graph encompasses the following additional d of object in its corresponding :attr:`task`, having :attr:`edge_split_mode` set to `approximate` could give the user some performance gain. -Heterogeneous GNN in DeepSNAP ------------------------------ +DeepSNAP Heterogeneous GNN +-------------------------- The Heterogeneous GNN layer is a PyTorch :class:`nn.Module` that supports easy creation of heterogeneous GNN, building on top of PyTorch Geometric. Users can easily specify the message passing model for each message type. The message passing models are straightforward adaptation of Pytorch Geometric homogeneous models (such as GraphSAGE, GCN, GIN). In future release, we will provide even easier utilities to create such heterogeneous message passing models. diff --git a/tests/README.md b/tests/README.md new file mode 100644 index 0000000..255766e --- /dev/null +++ b/tests/README.md @@ -0,0 +1,7 @@ +## Tests + +To test, `nose` is required. + +```sh +pip install nose +``` \ No newline at end of file