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

Use other libs #8

Open
ductm104 opened this issue Aug 19, 2021 · 4 comments
Open

Use other libs #8

ductm104 opened this issue Aug 19, 2021 · 4 comments

Comments

@ductm104
Copy link

Hi, I see that your requirements.txt file only contains tensorflow based libraries.

How can I use other libs like pytorch?

Can you provide an example to use torch instead of tf. I just checked maml_torch but it doesn't work.

@ebadrian
Copy link
Owner

Hello!
The requirements has been updated and now has the higher (second order optimization library required by maml_torch). The maml_torch baseline should now work with the conda environment.
Everything you need to know to use torch models instead of TF is inside this baseline. More specifically, you only need to implement the torch data wrapper in order to use any torch models you want.
Let me know how it goes!

@ductm104
Copy link
Author

Hi @ebadrian ,

I have another question about how to get exactly the total number of meta class in meta training phase.

@ebadrian
Copy link
Owner

ebadrian commented Sep 2, 2021

Hi!
We plan to release this feature soon, I'll keep you updated.

@ductm104
Copy link
Author

Hi @ebadrian , are there any updates on this problem? Because I cannot use 'batch' mode with CE Loss if total_meta_class is not known.

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

2 participants