huaxiuyao / c-mixup Goto Github PK

Hello.
First of all, thank you for source.

Is there a reason why scheduler.step() is missing in the train() function of algorithm.py when "is_mixup" is True?

Hi,

Thanks for your impressive work, but I can not reproduce the results in your paper with your source codes on some datasets, like Crime, Skillcraft, and so on. What I have done is just repeat the experiments with the provided parameters on seed 0,1,2. Since you have 3 runs on each dataset, could you provide the seed numbers and the parameters on each seed?

Thank you very much and look forward to your reply.