LuisaWerner

icon indicating a website link luisawerner.github.io

icon company INRIA icon location Grenoble, France icon location PhD candidate on neuro-symbolic integration based in Grenoble, France.

Results 1 comments of LuisaWerner

QuatE: GPU memory is not released per epoch

Thanks for your answer and sorry for my late reply! I use the default QuatE model from the pykeen library [here](https://pykeen.readthedocs.io/en/stable/api/pykeen.models.QuatE.html) It looks like this ``` QuatE( (loss): BCEWithLogitsLoss() (interaction):...