Forest Gregg
Forest Gregg
is there a reason to not always use the slim option?
it's pretty hard to say, but your hardware seems like it should be more than enough for 40K records
do you know where in the process you get the memory error.
About 100K is probably when it makes sense to move to database. > Also 2.0.14 was giving slow performance .. Could you speak about what you were seeing with this?
you'll need to get more training data.
@abhijeetghotra, would it be possible to share the pairwise edges (the memmaped numpy array) that should be completely without any user-sensitive data.
cc @fjsj, perhaps relevant to your interests.
really interesting idea: https://twitter.com/mccastelle/status/1263272272787320840
https://arxiv.org/abs/1802.09478
thanks that's very helpful.