Minjoon Seo
Minjoon Seo
Hi, It seems the issue is due to tensorflow incompatibility; I remember that 0.12 had issues. Could you try using 0.11? I cannot promise much about upgrading the code (for...
@webeng You are right that you can control those params to avoid OOM during training, but I think he is using pre-trained model and only testing. Looking at the error...
@rubby33 It is a trial-and-error thing, and I usually figure it out by looking at the memory usage and whether it gives OOM. 30k is a rough estimate.
Hi @rubby33 , I am a bit confused what the issue is.. could you please clarify? Thanks!
Hi, sorry for late response; apparently I was not watching for this repo (owned by AI2, not me) and I just realized it :( `basic` is for SQuAD, and `basic_cnn`...
Hi, I am unfamiliar with tf-serving but I am quite interested in it so will look into this!
Could you tell me what "mrc model" is?
Basically you want to set up a server which can take in question and output prediction, is that correct? As you pointed out, calling script every time will be costly....
@webeng Hmm, in fact, it seems the demo branch is not up to date.. It used to be like that, and we changed it later (current demo). @shmsw25 Could you...
Hi all, the demo branch has been updated. Now it can easily accept custom para/ques through http request.