An extension of fastai for meta learning algorithms

fastai fastai dev
1

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.

Link: https://github.com/Atom-101/Meta.AI
Note that it isn’t pip installable yet. In order to use it, sys.path has to be modified.

1 Like
2

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.

2 Likes
3

Thanks.

I will add a demo notebook soon.

1 Like