-
Notifications
You must be signed in to change notification settings - Fork 123
First Order MAML? #63
Comments
Yes, I think that's correct! Additionally, you could set the |
Unless I'm missing something, you actually don't need to use As @Nithin-Holla points out, you can use |
hi @MurtyShikhar how did you end up implemented your fo MAML? hi @Nithin-Holla I tried setting |
@egrefen what is the official way to run first order MAML with higher? |
@Nithin-Holla can you confirm if I have understood you correctly or not. MAML to FoMAML can be done just by setting track_higher_grads = False, nothing else? |
@kamalojasv181 @egrefen whenever I set track_higher_grads=False I get my gradients are Non. I have this check:
in my train loop. Is this incorrect or is there something wrong? There should be gradients even if it's FO maml, no? What happens to you when you do: |
I think this is the solution: #102 to FO |
Hi,
Thanks for this very useful piece of software!
I was wondering if there's an easy way to implement first-order MAML with higher. I currently have an implementation of (full) MAML with higher, but wanted to compare it with just first order MAML.
EDIT: It appears that torch.autograd.grad(query_loss, fmodel.parameters()) would give the gradients corresponding to FOMAML and torch.autograd.grad(query_loss, fmodel.parameters(time=0)) can be used to get MAML gradient?
The text was updated successfully, but these errors were encountered: