Dzmitry Bahdanau
Dzmitry Bahdanau
While I am tinkering with my setup, could one of you try to run this experiment multiple (like 5) times, please?
I could not reproduce your issue. I have just trained 10 models, and they all worked fine. Can you please try running the experiment many times and tell me if...
I am sorry to hear the code doesn't work for you. For now all I can do is to give an extra info w.r.t the environment. I run the code...
I have looked at both `vocab.json` files, and the both seem to have `program_token_arity` keys in them. Can you please tell me what keys you have in your `vocab.json` file...
Right, there are two more. We will fix it at some point, but for now, please read the script, it is not very long. On 1 December 2015 at 08:20,...
Can you please paste the whole log of your installation attempt?
This looks really cool, I will check it Monday!
Thanks a lot, @jcjohnson ! Regarding the inconsistency between the original code and the Github code: can you please clarify which code was used to generate the widely used CLEVR...
Thanks Yushi for your fast response! Yes, indeed SimpleTOD evaluation code compares multi-values in the same way as yours. Do you think some other implementations (including ASSIST-DST and the links...
Thanks for your response! The original release I'm referring to is indeed https://github.com/jkkummerfeld/text2sql-data. Having read your response, my understanding now is that you only took 1 query per template when...