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
Can you provide a GIAS data set that you divided when training GIAS? #13
Comments
Thanks for your attention. Actually, in the latest version of our paper, we use three times five-fold cross validations to make the results in the small datasets more convincing. I highly recommend you to do so as well, because the results seem quite unstable due to the small number of data. Hope this helps. |
Hello,author, could you provide the latest code, the code related to the three times five-fold cross validations?,or can you send me a copy of the latest code, my email is 1458546594@qq.com,thank you very much! |
Hello,author, could you provide the latest code, the code related to the three times five-fold cross validations?,or can you send me a copy of the latest code, my email is mustansar.fiaz@gmail.com Regards: |
For the five-fold cross validation pipeline, you can refer to this repo: https://github.com/McGregorWwww/UDTransNet For the three times experiment, you can just run the pipeline three times and average all the results. Note that this may not be necessary in your tasks, since we added this exp mainly to convince the reviewer. |
Hello author, can you provide a GIAS data set that you divided when training GIAS? My email is 1458546594@qq.com, if possible, I will be very grateful to you
The text was updated successfully, but these errors were encountered: