Why do we need to save -> unfreeze -> lr_find -> fit_one_cycle -> save again?

I’m at lesson 3 now and there is one thing that I can’t get my head around. I’m afraid that if I don’t overcome this issue, I can’t understand anything ahead.

Why do we need to fit_one_cycle at 4 epochs, then save, then unfreeze, then find the learning rate (lr_find), then fit_one_cycle again?

What is the purpose of unfreeze? And why after unfreeze and fit_one_cycle again, we usually have a better result?

Why the fit_one_cycle doesn’t do all these things for us?

Why not just



I know there is a post about this here Why do we need to unfreeze the learner everytime before retarining even if learn.fit_one_cycle() works fine without learn.unfreeze()
But reading it makes me confused even more.

Thank you.

Hi hoangtrinhj hope you are well!
Go back and watch the videos 1-3 but especially focus at these points:
Go back and watch lesson 1 video - especially from 1:16:00
Go back and watch lesson 3 video - especially from 1:19:00

Watch them till you understand, :smiley:

I would make my own notes! to help remember :smiley:

Cheers mrfabulous1 :smiley::smiley: