Dynamic-Clip-Attention

Dynamic-Clip-Attention copied to clipboard

No such file or directory: './data/raw_data/WikiQA/wikiQA-train.txt.labeled' 请问这个文件是怎么处理的

Sure0520

tjyjy

the size of training set?

1

hi, I recheck the size of training set, there are 1227 questions and it's different with the statistic you reported in the paper. Should it be 1227 or I made...

knimet

SyntaxError: positional argument follows keyword argument

1

F:\Anaconda3\python.exe E:/Dynamic-Clip-Attention-master/preprocess.py File "E:/Dynamic-Clip-Attention-master/preprocess.py", line 116 Util.generate_vocab(file_list=["./data/trecqa/train-all.txt","./data/trecqa/clean-dev.txt","./data/trecqa/clean-test.txt"],output_file="./data/trecqa/vocab_trec.txt","trecqa") ^ SyntaxError: positional argument follows keyword argument Process finished with exit code 1

tjyjy

F:\Anaconda3\python.exe E:/Dynamic-Clip-Attention-master/main.py F:\Anaconda3\lib\site-packages\h5py\__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`. from ._conv import...

tjyjy

Merge Exception

2

Hi, There is an Exception during running the model, how could you solve this problem? Traceback (most recent call last): File "main.py", line 176, in main(args) File "main.py", line 103,...

zhanghaoie

If you are trying to run this model and getting NaN loss after a few iterations. Try the following: - Gradient clipping of Adam optimiser - In the SoftAlignment layer,...

imeckr

The model you introduced in your published paper seems different from the model in your code? Can you explain it more concretely? Only the Aggregation Layer (CNN layer), which you...

hexingwei

how to produce the result published in your paper?

2

Hi, I have tried the command given in the readme but it is not giving the result published in your paper. Do you achieve that with a different config that...

wailoktam