Support for haiku models with non-trainable state
Open
- Dominant language
- Python
- Stars
- 272
- Forks
- 42
- PR merge metrics
- No merged PRs in 30d
Description
Hi!
congrats on this great library! I've started using it a few days ago and I love it!
Is there any way to use a haiku model with a non-trainable state (e.g. to use batch norm)?
I didn't find any nontrivial way, but maybe I'm missing something.
Thanks a lot for your help!
Contributor guide
Assessment
This issue has not been assessed yet.