kge
kge copied to clipboard
uma-pi1
LibKGE - A knowledge graph embedding library for reproducible research
I'm not very familiar with this way of running programs through yaml configuration files, is there any convenient way to debug programs? I would appreciate that if someone has a...
Hi I have a model from which I am trying to get scores from a large number of triples. To speed up the process I would like to get these...
I was following the example on the tensor scoring in the readme file ```python import torch from kge.model import KgeModel from kge.util.io import load_checkpoint checkpoint = load_checkpoint('fb15k-237-rescal.pt') model = KgeModel.create_from(checkpoint)...
In frequency based sampling, we are using `_multinomial_alias_setup` and `_multinomial_alias_draw`. However, these methods were removed as of torch 1.8. Therefore, frequency based sampling does not work anymore with any newer...
Currently, logs for the training job are not written to kge.log if we resume from checkpoint. By default on model.create_from() we use a tmp file for logging. This small change...