Issues
- 0
批处理
#21 opened by therateful - 0
RuntimeError: cublas runtime error : the GPU program failed to execute at C:/w/1/s/tmp_conda_3.7_044431/conda/conda-bld/pytorch_1556686009173/work/aten/src/THC/THCBlas.cu:259
#19 opened by Hdligence - 1
pytorch版本确定是1.1.0吗?我按照环境要求安装了依赖,但是运行程序就报错显示RuntimeError: cublas runtime error : the GPU program failed to execute at C:/w/1/s/tmp_conda_3.7_044431/conda/conda-bld/pytorch_1556686009173/work/aten/src/THC/THCBlas.cu:259
#20 opened by Hdligence - 1
拓扑图构建
#18 opened by GitHubmalajava - 1
use model with different data set
#17 opened by Mopsfrosch - 2
关于数据集Flickr和BlogCatalog在模型GCN和GAT上的复现
#16 opened by lizhou21 - 0
- 2
这个可以用于异构图吗?
#13 opened by Heath0 - 1
训练为什么不用验证集
#14 opened by lizhou21 - 1
test results
#12 opened by xuhaiyun43 - 2
About dataset
#11 opened by Neoyanghc - 3
Code issues
#10 opened by xnuohz - 2
I want to know if the authors have any experimental results on Cora and PubMed datasets. I spend a lot of time adjusting parameters to modify your code, but it is still difficult to get ideal results, even worse than the results of GCN on Cora and PubMed. Secondly, this paper does not use validation dataset, and outputs the best results on the test dataset. Is it reasonable?
#9 opened by njuyuan - 3
- 5
About the feature graph construction
#7 opened by ZJJTSL - 3
About baseline performance
#6 opened by LiFXe - 3
About the attention implementation
#5 opened by agave233 - 1
nsadj和nfadj的shape为什么是一样的呢?
#4 opened by wumingyao - 1
About the ACC of baseline
#3 opened by lilybud - 1
- 2
About F-score
#1 opened by GNN-zl