mirrors / dmlc--dgl

项目文件夹

文件

T

Lingfan Yu 74e13eea61 [Model] Update GAT model code (#622 )

* fix gat code to use latest edge softmax module

* avoid transpose

* update README

* use edge_softmax op

* mxnet edge softmax op

* mxnet gat

* update README

* fix unittest

* fix ci

* fix mxnet nn test; relax criteria for prod reducer

2019-06-08 21:41:38 -04:00

547 B

原始文件 永久链接 Blame 文件历史

Graph Attention Networks (GAT)

Paper link: https://arxiv.org/abs/1710.10903
Author's code repo: https://github.com/PetarV-/GAT.

Note that the original code is implemented with Tensorflow for the paper.

Dependencies

MXNet nightly build
requests

pip install mxnet --pre
pip install requests

Usage (make sure that DGLBACKEND is changed into mxnet)

DGLBACKEND=mxnet python3 train.py --dataset cora --gpu 0 --num-heads 8