SQLNet

SQLNet copied to clipboard

Problem when using it with dataset other than WikiSQL

3

while i m running the train.py file with a dataset other than WikiSQL. i meet the error as follow: Traceback (most recent call last): File "train.py", line 128, in sql_data,...

tornadozou

I am getting error in the following line:- loss += self.CE(sel_score, sel_truth_var) Error:- RuntimeError: Assertion `cur_target >= 0 && cur_target < n_classes' failed. at c:\new-builder_3\win-wheel\pytorch\aten\src\thnn\generic/ClassNLLCriterion.c:93

deepanshib

Hi @xiaojunxu Could you upload your tokenizatoin script? The reason is that I found there are some difference in "question" and "query_tok" sometimes. For example, at 25th data in `dev_tok.jsonl`,...

whwang299

Could you explain the differences between cond_num_lstm and cond_num_name_enc?

trangkum

Hi xiaojunxu, I don't find how to predict the number of conditions in your paper.

trangkum

Help!! Don't have Cuda

1

Hi, This package uses gpu (cuda) for processing which is not available in my server. Can you please guide me how to use it without gpu. P.S. working on a...

Manas0706

Trained model

2

Hello! I am studying SQLNet and first I would like to congratulate you for the great work you have done in this paper. I got your code from https://github.com/xiaojunxu/SQLNet but...

riquebueno

You can try pure character-level embedding without word embedding to get the result of https://arxiv.org/abs/1801.00076

guotong1988

get the result of https://arxiv.org/abs/1801.00076 The reason and inspiration to use bi-directional attention is from the machine comprehension task. In the SQuAD [Rajpurkar et al. 2016] machine comprehension task, we...

guotong1988

用文本分类模型来做AGG的预测，一共就MIN MAX COUNT等几类 Thank you @xiaojunxu

guotong1988