-
我目前的知识图谱实体在1500万个左右,在运用transE进行训练时显示oom错误,即使batch size设置为1,也会出现oom错误,请问怎么解决呢?
Traceback (most recent call last):
File "train_transe_WN18_adv_sigmoidloss.py", line 52, in
trainer.run()
Fil…
-
Using the default config file present in `/configs/c-rgcn/lp-WN18.yaml` after changing the weight initialisation as suggested in #12, I get the following error.
```INFO - R-GCN Link Prediction - R…
-
Dear authors,
I met this problem when I ran the MKG task. I tried to solve it in the data_module file, but I failed. Have you ever met the same problem?
warnings.warn(
Namespace(accelerator=None,…
-
Hello!
Thank you for a nice study and a nice repository! :D I am currently trying to re-use some of your hyperparameters from the study, e.g., those for `Complex` for the `YAGO3-10` dataset. Howev…
-
非常感谢作者们扎实的工作,我现在想要尝试用您提供的代码跑WN18和FB15K-237这两个数据集,不知道这个可否实现呢?因为我注意到您的代码中有这些针对于DB15K和MKG-W的专有json文件,不知道这些文件可否通过代码生成在其他数据集上呢?(例如WN18和FB15K-237)
![image](https://github.com/zjukg/MyGO/assets/91859784/cf8…
-
### Metadata
- Authors: Avishek Joey Bose, huan ling, Yanshuai Cao
- Organization: Borealis AI & University of Toronto
- Conference: ACL 2018
- Paper: http://aclweb.org/anthology/P18-1094
- Blog:…
-
### Describe the bug
Calling `CosineAnnealingWarmRestart` as an option in `pykeen.pipeline.pipeline` results in the following error:
```
CosineAnnealingWarmRestarts.__init__() got an unexpected …
-
作者,您好,最近做实验的时候用了gitHub给的网盘中提供的IMG数据集,但是发现实体数目对应不上,以WN18RR为例,实体的数目应该有**40943**个,但是WN18-IMG对应的文件夹只有**7801**个,请问是不是有的实体没有对应的图片,然后处理的时候需要过滤掉没有图片的实体呢,这样做有没有什么影响,期待您的回复,谢谢
-
Hi,
I have a question regarding the `create_inverse_triple` argument when loading a TripleFactory,
such as:
```python
train = TriplesFactory.from_path(data_path / 'train.txt', create_inverse_…
-
您好,我从提供的Google Drive中下载了wn18-images,发现只有7,801个实体有图片文件夹,不知道是不是没有上传完整呢?