Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

About process_train.py #2

Closed
tomtang110 opened this issue Jul 5, 2019 · 3 comments
Closed

About process_train.py #2

tomtang110 opened this issue Jul 5, 2019 · 3 comments

Comments

@tomtang110
Copy link

Hi ming

If you load the hotpot_dev_fullwiki_v1.json in your process_train.py, there is an error occuring.
屏幕快照 2019-07-05 17 49 01

@Sleepychord
Copy link
Contributor

Hi, " hotpot_dev_fullwiki_v1.json" is not training data but validation data. This file is to process training data. Do not change the filename in the code.

@tomtang110
Copy link
Author

Hi
I have run your code and evaluate it, but the result is weird, I am sure that I use the eval() function in hotpot_dev_fullwiki_v1.json. Could tell me what function you use to eval()?
屏幕快照 2019-07-08 13 44 40

@Sleepychord
Copy link
Contributor

Sleepychord commented Jul 9, 2019

I think this problem can be solved by reading the evaluation codes, which is offered by HotpotQA dataset. It looks not relevant to CogQA. I am not sure about the exact reason.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants