-
Uploading and downloading of large KGE files may take awhile. Some application feedback needs to be given to the user to report progress of either operation.
**Note:** s3 client `upload_fileobj `an…
-
here are a variety of iotm resources that were not used after a day of garbofarmin', along with how they should be used. some are more complicated to handle than others.
- clan VIP pool table (+5 f…
-
Hi,
As far as I understand from the documentation, the base KGE model object contains a TriplesFactory object. This can be called using `model.triples_factory` in pykeen 1.4.0. However, using the …
-
Thanks for publishing this great repo!
I'm trying to use the pretrained KGE models in this repo to create embeddings for unseen objects and predicates but I'm having trouble figuring out how to do …
-
I was wondering whether (1) it is possible to use pretrained models and (2) do you plan to include any other KGE approaches published after 2018 ?
Cheers
-
I noticed someone else mentioned this in another issue (https://github.com/awslabs/dgl-ke/issues/178), but I haven't seen it resolved.
I'm running dglke_predict on trained embeddings and having iss…
-
KGX currently reads entire knowledge graphs into RAM. This places an obvious limit on the size of knowledge graphs which can be processed by a given memory-bound machine.
Several KGX operations may…
-
Dear LibKGE team,
thank you for this great library! My intention was to use it to train the embedding of some KGs but I did not manage to complete the training of the toy example because of a poten…
-
@AdrianKs found today that the downloads_all.sh script does not work for some datasets, as it downloads an HTML file instead of the actual tar.gz file with the data. I confirmed this behavior as well.…
-
Hi, Thanks very much for your excellent job!
I'm now using my own algorithm on a large knowledge graph dataset, I've been obsessed with computation time. Since you don't support any function API, i…