How to evaluate model on test set?

Hi, I’m new to fastai, is there a simple way to evaluate a model on test set ?

I found this thread but the code seems valid for fastaiv1 and it does not provide any simple solution.

PS: How come we have to struggle to have a solution to such a basic question for such a popular framework ?

is there a simple way to evaluate a model on test set ?

Essentially this is like your deployed-runtime-mode.
Use get_preds() as suggested in this answer in your other thread
and also described for Batch Prediction

Now I just want to check you are familiar with fastai context for these terms, watch Lesson 4 at 45:11 where Jeremy advises “perhaps the most important idea in machine learning is the idea of having separate training, validation and test data sets…”

1 Like