Filip Cornell
Filip Cornell
Sorry for my late reply. The analysis still runs fairly slow with the update. I will return with a timing on both!
Oh, now I feel a bit stupid. Of course, I see the `b` in front of the `b"Hello world!"` in the docs now. Perhaps there might be a value of...
Yes, I will have a look at it. I think further tests should also be built, I might have a look at that if I get the time.
Good point. I will make changes accordingly!
I can add here that the problem seems to be with the fact that `cdist` is being used, as described [here](https://github.com/pytorch/pytorch/issues/49928). However, it should be fixed; I am using `torch==1.7.1`,...
I seem to have fixed this problem now, by upgrading `torch` to 1.9.0.
Yes, did you upgrade to `torch` 1.9.0?
To further update; I realized I constrained my search to only using sLCWA runs, so the one above does not correspond to the run presented in the paper (Table 18)....
Hi there, Thank you for your reply! :D I will re-run the experiment in question with your comment in my mind and see if the fixes the results. If not,...
Hi again @mberr , If I add what you write, ```python3 config["pipeline"]["training_kwargs"]["callback_kwargs"] = { "prefix": "validation", "factory": dataset.validation, "additional_filter_triples": dataset.training, } ``` I get the error: ``` File "/home/users/filip/.conda/envs/kgexperiments/lib/python3.10/site-packages/pykeen/training/training_loop.py", line...