-
Hi, thanks a lot for the wonderful repository and paper.
In the paper section B.3, it is mentioned that "We set the max length of input and inference as 256 and 64, respectively". However, on chec…
-
I have two questions on [Text-Code](https://github.com/microsoft/CodeXGLUE/tree/main/Text-Code/NL-code-search-Adv#result) readme:
1. Do you consider MRR of both validation and test dataset? The [da…
-
Can you provide some detail of the `PBSTM` and `Roborta (code)` method for the code-to-code translation task? Also, when do you plan to make your paper publicly available?
-
Hello, I read the paper and thanks a lot for the wonderful repos.
I follow the script to fine-tune the model (https://github.com/microsoft/CodeXGLUE/tree/main/Code-Text/code-to-text)
And I occur th…
-
Hi,
Thanks for your excellent work! it is really interesting.
Recently, I try to do some experiment on CodeSearchNet dataset. After preprocessing, I found the vocabulary is SO LARGE !!
I don't kn…
-
Hi, In the code to text generation task (https://github.com/microsoft/CodeXGLUE/tree/main/Code-Text/code-to-text), there are baselines called as, `Seq2Seq` and `Transformer`. I have a few questions re…
-
# 🐛 Bug
## Information
Model I am using (Bert, XLNet ...): CodeBERT
Language I am using the model on (English, Chinese ...): Code
The problem arises when using:
* [x] the official example…
-
Dear Shangchen Zhou,
for my research scope, I needed to infer the results produced by the single DeblurNet. I followed the procedure described ([here](https://github.com/sczhou/DAVANet/issues/1#issue…
-
Hi,
I would like build a code search engine model. The main purpose is that when I pass docstring, it should give me top-k associated code snippets as results.
I have a data in the form of (doc…
-
Thank You for CodeBERT! A quick question, wherein CodeSearchNet did you find a fixed set
of 999 distractor codes say If I wish to evaluate (MRR) for a model built (Code Search space)?