From 33c8abb9f457cfe8f51f1a41ac4a5417ade01460 Mon Sep 17 00:00:00 2001 From: Tong He Date: Thu, 22 Sep 2022 13:54:13 +0800 Subject: [PATCH] [Doc] Update Readme for example Hilander (#4587) The example was updated in https://github.com/dmlc/dgl/pull/3972 but the README file was not. This PR updates it to reflect the correct environment requirement. Co-authored-by: Minjie Wang --- examples/pytorch/hilander/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/examples/pytorch/hilander/README.md b/examples/pytorch/hilander/README.md index a98b09aef313..bd889530019f 100644 --- a/examples/pytorch/hilander/README.md +++ b/examples/pytorch/hilander/README.md @@ -5,13 +5,13 @@ This folder contains the official code for [Learning Hierarchical Graph Neural N ## Setup -We use python 3.7. The CUDA version needs to be 10.2. Besides DGL (>=0.5.2), we depend on several packages. To install dependencies using conda: +We use python 3.7. The CUDA version needs to be 10.2. Besides DGL (>=0.8), we depend on several packages. To install dependencies using conda: ```bash conda create -n Hilander # create env conda activate Hilander # activate env conda install pytorch==1.7.0 torchvision==0.8.0 cudatoolkit=10.2 -c pytorch # install pytorch 1.7 version conda install -y cudatoolkit=10.2 faiss-gpu=1.6.5 -c pytorch # install faiss gpu version matching cuda 10.2 -pip install dgl-cu102 # install dgl for cuda 10.2 +pip install dgl-cu102 dglgo -f https://data.dgl.ai/wheels/repo.html # install the latest dgl for cuda 10.2 pip install tqdm # install tqdm git clone https://github.com/yjxiong/clustering-benchmark.git # install clustering-benchmark for evaluation cd clustering-benchmark