start_epoch called before parsing the argument
rashadkp opened this issue · comments
in the line 91 ,it should be : n_iter = int(args.start_epoch)
Actually, it should be 0, n_iter is only here for tensorflow purpose. I am surprised this does not make the code crash, since the variable start_epoch is not defined 🤔
We could probably do better by inferring the n_iter from args.start_epoch and dataset size (like len(train_set) * args.start_epoch )
Should be solved with last commits. Please check it out ! 😎