Problem when using it with dataset other than WikiSQL

[tornadozou]

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, table_data, TRAIN_ENTRY)
File
"/[email protected]#0/sqlnet/utils.py", line 146, in epoch_train
gt_where=gt_where_seq, gt_cond=gt_cond_seq, gt_sel=gt_sel_seq)
File
"/[email protected]#0/sqlnet/model/sqlnet.py", line 141, in forward
gt_where, gt_cond, reinforce=reinforce)
File "/opt/conda/envs/python2.7/lib/python2.7/site-packages/torch/nn/modules/module.py", line 489, in call
result = self.forward(*input, **kwargs)
File
"/[email protected]#0/sqlnet/model/modules/sqlnet_condition_predict.py", line 253, in forward
cond_str_score[b, :, :, num:] = -100
IndexError: too many indices for tensor of dimension 3

Can anyone help?

[guotong1988]

……

[guotong1988]

I also can not solve it.

[dhs007]

Does it work perfectly with wikisql datasets?