Using the output variable (output_ts) of the data

[ghost]

Hi,

I want to use the output variable which stores the aspect, sentiment pairs of the input sentence. I think it is the output_ts variable in work.py

I actually want to use it in a different .py file so I import the work.py like a module and I try to use output_ts there. The error I encounter is that work.py doesn't have an attribute named "output_ts". So I tried to return output_ts after the predict function inside work.py but that also didn't work. Is there a way to solve this issue?

[lixin4ever]

Hi,

I am very busy recently. Maybe we can discuss your issues after Feb 2.

[ghost]

Hello,

yes sure I will be waiting!

[lixin4ever]

Hi,

I want to use the output variable which stores the aspect, sentiment pairs of the input sentence. I think it is the output_ts variable in work.py

I actually want to use it in a different .py file so I import the work.py like a module and I try to use output_ts there. The error I encounter is that work.py doesn't have an attribute named "output_ts". So I tried to return output_ts after the predict function inside work.py but that also didn't work. Is there a way to solve this issue?

Work.py does NOT have an attribute called output_ts. You should set output_ts as (additional) return value of the predict function and then import the predict function (in another.py) from work.py. Every time you need to obtain the output_ts, just call the predict function in another.py.

This issue is more like a python issue, for the problems not related to our model, please google first and try to solve them by YOURSELF.

[ghost]

what should I put for args model tokenizer while calling predict in another.py?

[lixin4ever]

Basically, you need to write several lines of code to load the fine-tuned model and the tokenizer from the specified paths.

Just follow the procedure of the function main() in work.py.