SAM2 integration for segmentation tasks

Greetings.

I connected the ML Backend for segmentation to my project. Backend looks to be online, but I do not have any results in the project. I would like to ask for support to set everything up.

Here are the instructions I've used: https://github.com/HumanSignal/label-studio-ml-backend/tree/master/label_studio_ml/examples/segment_anything_2_image#running-from-source

Here is the labelling layout code:

[layout.xml](https://github.com/user-attachments/files/22533736/layout.xml)

Issues:
- There is no Auto-Detect functionality as it is in the official instruction video, and some of the tools are absent, too (https://www.youtube.com/watch?v=FTg8P8z4RgY)
- There is no visible segmentation feedback. The labelling process is completely manual.

Backend test request returns an empty response 200.

Here is the file structure of my project with the Backend:

Environment data:
OS: Windows 11
SW: PyCharm + Python 3.10
Label Studio Community Edition v1.12.0
Label Studio ML Backend v2.0.1dev0