xiang song(charlie.song)
xiang song(charlie.song)
It seems like OOM. How large is your instance?
How many lines in your rel.list? For each relation, It will try to calculate (number of nodes * number of nodes) possible combinations, which is time consuming.
From you log, it seems the tcmalloc is trying to alloc 8GB memory (tcmalloc: large alloc 8589934592 bytes). What kinds of command you are running? Can you check how many...
Do you mean we have want to use dgl.heterograph({...}) when the {...} is a dict of 4M objects? How large is the graph?
Can you try downgrade the version of python and pytorch? In our testing env, we use python3.6 and pytorch 1.6
Yes, we need to make kge work with pytorch 1.7
emap_f and rmap_f is the entity id mapping file and relation id mapping file. Are you using raw_udd_{htr} ?
> Yes I used `raw_udd_{hrt}`. > > I just misread the documentation, the recommended delimiters are for the knowledge graph files. > > I just don't understand why the given...
Very nice work. Can you also upload some performance numbers (speed and MRR scores)? If you need some resources for multiGPU evaluation, we can help.
How did you install dglke? BTW, dglke may not work with Pytorch 1.8.0. Pytorch 1.7.0 is OK