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.

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

Asking about inner and outer loop #64

Open
tranquangchung opened this issue Nov 15, 2021 · 0 comments
Open

Asking about inner and outer loop #64

tranquangchung opened this issue Nov 15, 2021 · 0 comments

Comments

@tranquangchung
Copy link

image

As I know, support set is training data and query set is testing data. And the query set uses for evaluating performance of model. However, in this code I realize that

In Line 138 loss_q.backward() 

=> using query set (testing data) to update gradient.

  1. You can explain in more detail here
  2. Why not use loss of support set to update gradient, more specifically, loss.backward() (line 85 and 114)

Thanks

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant