some questions about own dataset

[check-777]

Thanks for your nice works!If I want to use another datasets from "mulan"，such as emotion ,how can i convert it to datasets paper used ?I saw the words in the top of the preprocess.py "../data/reuters/train_inputs.txt -train_tgt ../data/reuters/train_labels.txt”, but i don't know the detail of the train_inputs.txt or train_labels.txt.Can you give an example of such type.Thank!

[untiltheday-lin]

I have the same problem. Have you solved it?

[jacklanchantin]

I don't have access to the raw data anymore as my home directory was removed from the university servers. I believe preprocess.py expects a train_input.txt file where each line is a sample and a train_label.txt file where each line contains the sequence of labels.

Alternatively, you can write your own prepocessing file to match the .pt pytorch object files that are currently used.