You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hey, I think there is an issue here in the code where the switch statement. It checks if t is greater the 1 however t is 1. because there is t = self.iterations + 1 above. For me this was returning d_t on the first step and causing the loss to diverge instantly. I set the value to 2 and everything works now. I am using this optimizer with tensorflow and not Keras so maybe that is messing something up too...
Hey, I think there is an issue here in the code where the switch statement. It checks if t is greater the 1 however t is 1. because there is
t = self.iterations + 1
above. For me this was returning d_t on the first step and causing the loss to diverge instantly. I set the value to 2 and everything works now. I am using this optimizer with tensorflow and not Keras so maybe that is messing something up too...https://github.com/rooa/eve/blob/master/eve/optim/eve.py#L67
The text was updated successfully, but these errors were encountered: