I run decode ,then has a error

[fiser321]

(env-0.12.0) root@op-System-Product-Name:/home/github/deep-text-corrector# cat predict.sh
python correct_text.py --test_path ./test.txt --config DefaultMovieDialogConfig --data_reader_type MovieDialogReader --model_path ./movie_dialog_model --decode

may I run "python correct_text.py --train_path ./movie_dialog_train.txt --test_path ./test.txt --config DefaultMovieDialogConfig --data_reader_type MovieDialogReader --model_path ./movie_dialog_model --decode"????

add -train_path ./movie_dialog_train.txt
????

[vishalshar]

You could try splitting (Train-Test-Validate) dialog data from 'movie_lines.txt'
http://www.cs.cornell.edu/%7Ecristian/Cornell_Movie-Dialogs_Corpus.html

[ourway]

Could someone please explain what's the meaning of split? Split to 3 equal n sized parts?
@vishalshar

[vishalshar]

Yes you can do n equal splits or 60-20-20 (train-test-validate)