Matan
Matan
@0bserver07 @guxd could you share the raw method names\descriptions?
I changed the reload param to 500:  and the subfolder for models/JointEmbeddingModel/ contains the matching 500-epoch files:  Is there something i forgot?
@guxd any news? I am very eager to re-create the papers results, they are very impressive 😄
@guxd thanks for the response. actually, i used `python codesearcher.py --mode repr_code`, `python norm_code_repr.py` threw the error `'data/use.codevecs.h5' doesnt exist because it doest not exist. the file use.codvecs.normalized.h5 already existed...
@guxd i have renamed it and ran run norm_code_repr.py. Now, the results from the top of the issue are: For the query: iterate through a hashmap I got the responses:...
@guxd should i re-train the model? if so, should i edit something special in configs.py (in addition to turning reload from 500 to 0)? Are there any updates in the...
@guxd i re-trained the model. Here are the results i now got for `convert an inputstream to a string` ``` ('public static String chomp ( final String str , final...