Questions tagged [meta-learning]

18 questions
0
votes
0 answers

Failing to compute gradient in PyTorch

I've been reading this research paper- https://arxiv.org/abs/1908.00413, and trying to implement the code from GitHub- https://github.com/hoyeoplee/MeLU, however, I run into a runtime error while training the model. Can anyone suggest the possible…
0
votes
0 answers

How does one use the mean and std from training in Batch Norm?

I wanted to use the means, stds from training rather than batch stats since it seems if I use batch statistics my model diverges (as outline here When should one call .eval() and .train() when doing MAML with the PyTorch higher library?). How does…
Charlie Parker
  • 5,884
  • 57
  • 198
  • 323
0
votes
2 answers

How to use have batch norm not forget batch statistics it just used in Pytorch?

I am in an unusual setting where I should not use running statistics (as that would be considered cheating e.g. meta-learning). However, I often run a forward pass on a set of points (5 in fact) and then I want to evaluate only on 1 point using the…
Charlie Parker
  • 5,884
  • 57
  • 198
  • 323
1
2