Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

create_graph parameter is False hence first-order MAML? #63

Open
gunnxx opened this issue Sep 10, 2021 · 1 comment
Open

create_graph parameter is False hence first-order MAML? #63

gunnxx opened this issue Sep 10, 2021 · 1 comment

Comments

@gunnxx
Copy link

gunnxx commented Sep 10, 2021

Hi, I noticed that when using torch.autograd.grad, the implementation does not pass create_graph parameter which by default is False. See L#86 and L#116 of the Meta class. To compute higher-order derivatives, we need to set create_graph=True otherwise derivatives w.r.t fast_weights will not flow to the derivatives computation i.e. first-order only. Is it intentional to not set the create_graph parameter?
@BigWhitePolarBear
Copy link

It had been discussed in #32. Seems like the author have ignored this repository.....

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@gunnxx @BigWhitePolarBear