Reproducing predictions in fastai v1

fastai
1

It seems that my predictions get worse after loading a model compared to predicting directly after training (this could be variance though)

Assuming I have the same databunch object, is it enough to:

  • create the same learner
  • load weights
  • call learn.model.eval()

and then predict?

And I’m a little confused by the fact that:
learn.model.eval()
returns the layers of the model, it should still set the model in eval model mode with just that line, right?

2

pytorch function model.eval() returns the model, so that’s why you see something. You can make it disappear with a ; at the end of your line.
Be careful to load the same validation set if you’re using it to validate.

1 Like
3

Great!

Yes, I now save and load the validation indices to make sure I’m using the same split

Merry Christmas and thank you for everything you do around this project!