chshin10/epinet

Cannot reach the performance of pre-trained model using default code setting

Opened this issue · 1 comments

Hi,

I found that using the default code and settings. After 6 days of training, the accuracy on validation set is still worse than the provided pre-trained model. Did you exclude some special training settings or strategies in the provided code?

Thank you!

Hi,

We've also had a lot of trouble reproducing the results presented in the paper. Any updates on this?