An extension of fastai for meta learning algorithms

I am working on a mini-library on top of fastai for meta learning. Few shot learning algorithms often require complicated gradient updates which require a lot of code. I am trying to reduce the hassle in using these algorithms.

Key features:

  • Supports MAML, Meta-SGD and Reptile algorithms currently.
  • Native support for all torchvision resnet models. Also allows use of pretrained imagenet weights.
  • Functional versions of nn.Conv2d, nn.Batchnorm2d, nn.Linear and nn.Sequential to allow users to easily create their own models for few shot learning.
  • Support for fastai’s callback system.

It is still a work in progress and any feedback is appreciated, especially from people with experience in this domain.

Note that it isn’t pip installable yet. In order to use it, sys.path has to be modified.

1 Like

Now added to the unofficial fastai extensions repository :slight_smile:

You might want to add a short introduction explaining clearly what meta-learning is and why people would want to use it plus a small demo notebook so that people can play with the concept.



I will add a demo notebook soon.

1 Like