I came accross this warning in the higher PyTorch library
# Crucially in our testing procedure here, we do *not* fine-tune
# the model during testing for simplicity.
# Most research papers using MAML for this task do an extra
# stage of fine-tuning here that should be added if you are
# adapting this code for research.
which I found confusing. Does someone know what this means?
Thoughts:
Since maml already has it's fine-tuning step (it's adaptation step) I'm unsure what this means.
Does this mean that people change the meta-learned weights (slow weights) on the validation set again? Isn't that just making the data set larger in overall effect? Or something else?
original question on github repo: https://github.com/facebookresearch/higher/issues/120
