Sarthak Mittal

Results 6 comments of Sarthak Mittal

You are right! I should do it if it is the start of training, and otherwise not?

Ahh got it. Pushed the code for making the seed optional then instead, with default being not setting the seed.

So we generally have Trainer created --> MTDataPreproc ---> experiment manager ---> model creation ---> training Is there a particular reason why experiment manager is called after trainer creation and...

> @sarthmit did you try running a few runs to check if all of them resulted in the same plots with the same seeds? In addition to Sandeep's data across...

@Imperssonator I think both the lines are equivalent. Notice that since epsilon is drawn from a uniform distribution, you can equivalently replace epsilon by (1-epsilon), both of these expressions would...