From 7baef8d4cad13297fa2d08b5ac0f19f06bb708e3 Mon Sep 17 00:00:00 2001 From: David Mack Date: Mon, 7 Jan 2019 15:47:29 -0800 Subject: [PATCH] tidier --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 81745de..37c1762 100644 --- a/README.md +++ b/README.md @@ -14,7 +14,7 @@ Here we present a "Graph network with attention read and write", a simple networ We present this network both as a novel system in of itself, but more importantly as the basis for further investigation into effective neural graph computation. -See the [full network description](https://medium.com/octavian-ai/finding-shortest-paths-with-graph-networks-807c5bbfc9c8). +Read our [extensive article about this architecture](https://medium.com/octavian-ai/finding-shortest-paths-with-graph-networks-807c5bbfc9c8). Download the [pre-compiled YAML dataset](https://storage.googleapis.com/octavian-static/download/clevr-graph/StationShortestCount.zip) or the [fully-compiled TFRecords dataset](https://storage.googleapis.com/octavian-static/download/mac-graph/StationShortestCount.zip). Data is expected to live in input_data/processed/StationShortestCount/.