Piotr Skalski

@dokooh looks like after refinement, you lost all makes. I will add a [fix](https://github.com/roboflow/multimodal-maestro/pull/20) for that edge case. As a workaround try skipping `maestro.refine_marks` step.

The `maestro` project has pivoted in the direction of a VLM fine-tuning toolkit. As a result, I am closing legacy issues.

Cool! I'll keep that in mind. We had a call with @PawelPeczek-Roboflow. We agreed on PromptCreator and ResultProcessor structure. Those can encapsulate a lot of the logic you just described....

we are changing the profile of the project, making these old ideas obsolete

Looks awesome! will ad it!

Hi @KTXKIKI, @capjamesg and @tfriedel 👋🏻 Work on datasets has had a lower priority in Supervision for some time, but it seems we can increase this priority in the coming...

Hi @6yuhao6 👋🏻 ! Is that question only about this specific image or in general?

Yes. That's exactly the reason. We could still apply some post processing - try to cat to area of one mask from the other.

Hi @emSko 👋🏻 Could you accept CLA? Without this, we won't be able to merge your PR.

Let's split the work on this PR into three parts: - [x] Implementation of `rle_to_mask` and `mask_to_rle`. Please write valid docstrings in Google format for both methods. For example, take...