OpenKE

OpenKE copied to clipboard

PengxinWang

Any reason why we eliminate duplicates? Let us say we are scraping from a large internet DB. There could be relations that are strongly reinforced multiple times, other relations which...

allohvk

RT, 采用自定义数据集，更换不同opt、lr、loss函数，loss均不下降

mokeeqian

Benjamin-Loison

能详细解释一下corrupt_head函数吗

lvfeifei

Experiments 实验结果每个数据集每个模型的超参数是否可以提供一下，examples 里好像并不是很全，谢谢

CuteMing

是否可以仅使用train.txt训练得到embedding，而不用entity2id.txt以及relation2id.txt这两个文件？

2

如题

leapxcheng

Question about loss?

1

How much transE lost indicates that the training was effective，For example, there are 17,289 data in my training set, 8,320 entities and 26 relationships, and the loss is 0.416 after...

yemai666

Hello, when I was learning openke-pytorch, I encountered the following difficulties running on a Linux server “Input Files Path : ./benchmarks/FB15K237/ The toolkit is importing datasets. Process finished with exit...

zs1115

RuntimeError: unique_by_key: failed to synchronize: cudaErrorIllegalAddress: an illegal memory access was encountered

1

Has anyone else had this problem when run "python train_transe_FB15K237.py"?

XJL0930