Issues
- 17
Need help to understand the code
#5 opened by iamxpy - 1
- 3
我实在忍不住吐槽一句#I couldn't help wanting to talk
#26 opened by Smithol - 1
Is TreeGen better than regular transformers?
#25 opened by brando90 - 1
Which tensorflow version to make the code work?
#24 opened by bdqnghi - 5
Do you use CSTs or ASTs?
#22 opened by brando90 - 3
What does W_c[c1; ...; cM] notation in the paper mean for character embeddings?
#23 opened by brando90 - 1
vocabulary 的疑惑
#21 opened by boyang9602 - 8
train_trans.txt和train_tree.txt里面数据含义和作用是什么
#8 opened by yueml - 4
resolve_data.py可能存在的问题和一些疑惑
#18 opened by boyang9602 - 1
nlnum和copylst文件的含义
#20 opened by boyang9602 - 5
Why was TreeGen not trained with the standard warm up scheduler for Transformers?
#19 opened by brando90 - 4
How is the query vector masked and shifted so that the model does not cheat when predicting grammar rules?
#16 opened by brando90 - 1
Are the depth embedding used at every transformer block of TreeGen or only at the input?
#17 opened by brando90 - 7
- 1
How are general identifiers predicting e.g. functions from an available library? (besides the NL pointer net)
#15 opened by brando90 - 1
How is the target vector (program rules sequence) in TreeGen created during training?
#14 opened by brando90 - 6
Are the programs that TreeGen generate guaranteed to be syntactically correct?
#11 opened by brando90 - 1
What is missing from the repo?
#13 opened by brando90 - 1
- 7
Why use WordConv (separable convolution) in NL encoder and not the usual Feedforward NN (like original transformer)?
#10 opened by brando90 - 1
predict_HS-B.py 中的处理流程,和"J_*"形式的方法 的大致情况
#9 opened by yueml - 2
data generation scripts
#7 opened by lifengjin - 2
ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()
#6 opened by iamxpy - 4
Error while training
#4 opened by talk2kabir - 3
- 2
LICENSE
#1 opened by juancamilog