Open sjlmg opened 11 months ago
I have solved this problem.
Could you please explain how this issue was resolved?
Hi,I also encountered the same problem.Could you please tell me how to fix it? Thanks in advance.
I'm very sorry for not replying before, but I remember it is an environment problem. Create a clean virtual environment and ensure the versions of cuda and pytorch. It is also possible to use a higher version of torch' than the version of this article.
Thanks for your prompt reply,that is really helpful
Thanks for your prompt reply,that is really helpful
Hello, may I ask what version you are using?Thank you.
Thanks for your prompt reply,that is really helpful
Sorry to bother you, my problem has been resolved^^
After I configured the environment, "AttributeError: 'tuple' object has no attribute 'ndim'" appeared when training on the WN18RR and FB15k-237 data sets. The error code is in line 107 of main.py (trainer.fit( model, datamodule)). Works fine when using CPU training.