Loading a tabular_learner without default directory

fastai
1

This seems silly, but is there a way to stop learn.load() from assuming my model is in /models?

2

any one help??

3

is there a way to stop learn.load() from assuming my model is in /models

Yes.

see the docs here

Load model from file along with opt (if available, and if with_opt)
file can be a Path object, a string or an opened file object. If a device is passed, the model is loaded on it, otherwise it’s loaded on the CPU.