deepAPI lack of ScheduledOptim

“ScheduledOptim” is not defined in modules.Whether the content is missing？

Jul 16 '21 12:07 zhenghuanghe

It seems that the code you are running is inconsistent with the Github repository.

Can you double-check?

Jul 18 '21 01:07 guxd

I downloaded the latest version and download dataset from google drive. When I running train.py.There are still some problems when I running train.py. $%X5XS_~}2(7@{4(HOXIQK2J$ It seems that the data type is not matching.I change my environment python=3.6 and Pytorch=0.4.1 as the README.md.The problem is not solved. Can you give me the current environment？

Dec 03 '21 12:12 zhenghuanghe

Can you print the size and content of inputs before calling inputs = self.word_embedder(inputs) in modules.py? Can you check whether they are word indices or sequence lengths?

Dec 03 '21 12:12 guxd

the type of inputs is int32

Dec 03 '21 12:12 zhenghuanghe

How about brutally casting the inputs to long such asinputs = inputs.long()?

Dec 03 '21 13:12 guxd

$ZCQ{9HZ1C_ M3WPY}LBPI$P$ Thanks your help! There are so many place has this problem .I chang the data type from int32 to long in train.py line 114 .It can work now. $EQ9$% V0YJL{{ )~%_1ENXS$

But I don't know if it will have an unpredictable effect on the result.Because the source code your share don‘t need to change the tensor type in your environment.

Dec 03 '21 13:12 zhenghuanghe

It can be OK. It might be caused by the Line 53-54 in data_loader.py. Can you try to change the argument np.int to np.long?

Dec 03 '21 13:12 guxd

I chang np.int to np.long but result is same .

Dec 03 '21 14:12 zhenghuanghe

Dear author,I change the np.int to np.int64 and the problem was solved. My problem might be caused by numpy version. When I train the model,I find that it needs nearly 22 hours to train an epoch.It takes too much time.Is it normal to consume such a long time? My GPU is GTX2060 and use default configuration in config.py,GPU usage is not high during training.

Dec 08 '21 11:12 zhenghuanghe

Thanks for reporting this solution. Yes, it is normal to cost such a long time for training an epoch.

Dec 08 '21 13:12 guxd

My result is Avg recall BLEU 28.139705, avg precision BLEU 28.139705, F1 28.139705. There seems to be something wrong with my training. Can you provide a trained model ？

Dec 09 '21 12:12 zhenghuanghe