learnables / learn2learn

A PyTorch Library for Meta-learning Research
http://learn2learn.net
MIT License
2.62k stars 350 forks source link

How to augment support set in l2l? #316

Closed brando90 closed 2 years ago

brando90 commented 2 years ago

I noticed the rethinking few shot learning paper here https://github.com/WangYueFt/rfs/issues/34 augments their support set.

How can I do this in l2l?

seba-1511 commented 2 years ago

Instantiate the transforms and apply them to the support before processing it with your feature extractor (eg, in the fast_adapt function).