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
Is it possible to use l2l's meta-train to do standard supervised learning? #301
Comments
Yes, you can access the underlying dataset of a TaskDataset with |
then pass that to a standard dataloader? Thanks again for your really nice framework :) Hope to contribute in a more meaningful way soon I hope! |
Correct, that gives you a standard PyTorch dataset. |
amazing! Your library is so nicely designed. Kudos. |
decided to do it slightly differently but I it seems right:
|
Actually do:
|
@seba-1511 I'm confused, what is the type of |
hmmm... this doesn't seem to be the right type:
|
perhaps its this:
|
I think this is better:
|
@seba-1511 is this really needed? |
e.g. I don't want to do episodic meta-learning but I want to use the data in the meta-train set and sample it randomly. Is that possible? Just normal SL but on the meta-train set.
The text was updated successfully, but these errors were encountered: