Aritra Roy Gosthipaty

I am thinking of the following: - Have a boolean flag in the `save_pretrained_keras` model named `is_tf_module` which by default is `False` - If the `is_tf_module` is `True` we switch...

Hey @merveenoyan Thanks for the quick reply. I have tried downgrading and it works. But I do not think this can be a permanent solution to the problem. There are...

I am willing to work on this as well.

Sure!

> Somehow I can't assign to you through user name... I think we need to comment on the issue to be assigned?

I feel like this is a _very_ important feature to welcome. Some really relatable pointers: - Pre-training the model (foundational model or any model for that matter) is really tricky....

Hey folks, I took a look at the paper and the code. These are my thoughts: - @AdityaKane2001 rightly pointed out > in their official implementation ([here](https://github.com/facebookresearch/msn/blob/4388dc1eadbe3042b85d3296d41b9b207656e043/src/data_manager.py#L95-L105)) they have simply...

I understand! Can we have a label for `GSoC` so that we point out which issues are already taken? @AdityaKane2001 all the very best for your contributions!

I would like to work on this!

Hey @tanzhenyu I got around reading the contriution guideline and the API design document. I was unable to find a guide to contribute a model inside of `keras_cv`. My main...