Results 347 comments of Luke Wood

I could really use this - @insin and plan to accept soon?

> Sorry for the long wait, since end user could easily miss the preprocess API with pytorch format, how about we include the preprocess as part of the model, and...

We can't change the behavior on this. This is potentially confusing though, so a warning would be great!

Notes from triage: The error message can be improved here - as the issue is with the `standardize` argument, not the layer

@AdityaKane2001 feel free to send a PR for this!

thanks an advance for any tips or guidance!

I'm not sure we'll be supporting the earlier YOLOs, such as v3

is there ever a case where users would want to use v3 over v7?

> I think that we are a little bit loosing the scope of Keras-cv manifesto in this thread. > > The main goal here is to share reusable subcomponents to...

Thanks for your efforts @atuleu ! one comment, other than that LGTM