Hi everyone,
I was wondering what happens when I change the path of a learner when doing transfer learning. To be more specific, I want to change the path of the language model learner in the IMDB notebook so that I can more easily access the model’s output files.
In the documentation the following is written: “If path is provided, all the model files created will be saved in path / model_dir ; if not, then they will be saved in data.path / model_dir .”
Is this the only thing it does or will changing the path also affect from where the learner tries to load the pre-trained weights (i.e. ~/.fastai/models/)?
Thanks in advance for your answers!
Stefan