start_epoch called before parsing the argument

Open rashadkp opened this issue 1 year ago • 2 comments

https://github.com/ClementPinard/FlowNetPytorch/blob/60c72a9c054e6e525eca5cc129ccafc11758d88f/main.py#L91C1-L91C7

in the line 91 ,it should be : n_iter = int(args.start_epoch)

Mar 18 '24 11:03 rashadkp

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 :thinking:

We could probably do better by inferring the n_iter from args.start_epoch and dataset size (like len(train_set) * args.start_epoch )

Mar 18 '24 13:03 ClementPinard

Should be solved with last commits. Please check it out ! :sunglasses:

Mar 24 '24 21:03 ClementPinard