YoloV8 serverless support

[hardikdava]

Motivation and context

Yolov8 object detection support added.

This pr is for #6471.

How has this been tested?

sh ./serverless/deploy_cpu.sh serverless/pytorch/ultralytics/yolov8

and

sh ./serverless/deploy_gpu.sh serverless/pytorch/ultralytics/yolov8

Checklist

• I submit my changes into the develop branch
• I have added a description of my changes into the CHANGELOG file
• I have updated the documentation accordingly
• I have added tests to cover my changes
• I have linked related issues (see GitHub docs)

License

Please check license since ultralytics is released under different license and so is yolov5

[codecov]

Codecov Report

Merging #6472 (c30b971) into develop (0c8a46e) will decrease coverage by 0.02%.
The diff coverage is n/a.

❗ Current head c30b971 differs from pull request most recent head 35538eb. Consider uploading reports for the commit 35538eb to get more accurate results

@@             Coverage Diff             @@
##           develop    #6472      +/-   ##
===========================================
- Coverage    81.68%   81.67%   -0.02%     
===========================================
  Files          334      334              
  Lines        38446    38446              
  Branches      3540     3540              
===========================================
- Hits         31406    31402       -4     
- Misses        7040     7044       +4     

Components	Coverage Δ
cvat-ui	75.07% <ø> (-0.02%)	⬇️
cvat-server	87.80% <ø> (-0.01%)	⬇️

[nmanovic]

@hardikdava , thank you for the contribution!

[nmanovic]

@hardikdava , could you please fix pylint warnings?

Also function-gpu.yml doesn't have pip install supervision. It leads to a problem.

[nmanovic]

@hardikdava , could you please update ‎site/content/en/docs/manual/advanced/ai-tools.md as well? Please add information about YOLO v8

[hardikdava]

@hardikdava , could you please fix pylint warnings?

Also function-gpu.yml doesn't have pip install supervision. It leads to a problem.

Done. Added pip install supervision

@hardikdava , could you please update ‎site/content/en/docs/manual/advanced/ai-tools.md as well? Please add information about YOLO v8

Done. Added information about YoloV8 in ai-tools.md

@nmanovic I have added the changes you asked.

[hardikdava]

is there any update on the merging?

[bsekachev]

Hi @hardikdava

Thank you for the contribution.
But, unfortunately we can't use YOLO v5/v8 from ultralytics in our product, because of recent change of their license to AGPL which is not compatible with MIT.