-
**Describe the bug**
Setup: FB15k237 (with inverse triples), Tesla V100, LCWA training loop
New GPUs have lots of VRAM - I'm testing on a V100 32GB.
Automatic memory optimization loop here
htt…
-
In main.py line 134-148,
```
for i, str2var in enumerate(train_batcher):
print("batch number:", i)
for j in range(str2var['e1'].shape[0]):
for k in range(str2var['…
-
-
我是KG的小白，我想问一下WN18 和WN18RR 是什么关系？为什么WN18RR的mean rank， hit@10 relatively low。这个是来做sparse graph的测试吗？
提前感谢～
best
-
Hello all,
firstly I would like to thank you for a clean implementation. Finally, we have clearn implementation of RDF2Vec to play with :)
I was wondering whether one use RDF2Vec in link predict…
-
Dear Tim,
thank you for the great work.
- I was wondering whether you could provide the best found hyperparameter settings of ConvE on WN18RR, FB15k-237, UMLS and Kinship.
- 209 number of th…
-
I am using the following parameters to train Transe to report an error. The error message is in the title。
--do_train
--cuda
--do_valid
--do_test
--data_path
D:\\KnowledgeGraphEmbedding\\data\\w…
-
This variable is used before it is defined.
[flake8](http://flake8.pycqa.org) testing of https://github.com/thunlp/OpenKE on Python 3.7.1
$ __flake8 . --count --select=E9,F63,F7,F82 --show-sourc…
-
Hello,
I was wondering where one could find the number of parameters of the ModE and HAKE on WN18RR, FB15k-237 and YAGO3-10.
Cheers
-
Hello,
I was wondering where the number of parameters of the InteractE on WN18RR, FB15k-237 and YAGO3-10 is reported somewhere.
Cheers