add yolov5 serverless function leveraging nvidia gpu

[tdhooghe]

Fixes #4851

This change enables leveraging an NVIDIA GPU when using a YOLOv5 serverless function.

Motivation and context

This change speeds up auto labeling with a YOLOv5 model.

How has this been tested?

Deploying the script using deploy_gpu.sh and checking if it uses the NVIDIA GPU with NVIDIA-SMI while auto-labeling.

Checklist

• I submit my changes into the develop branch
• I have added a description of my changes into CHANGELOG file
• I have updated the documentation accordingly
• I have added tests to cover my changes
• I have linked related issues (read github docs)
• I have increased versions of npm packages if it is necessary (cvat-canvas,
  cvat-core, cvat-data and cvat-ui)

License

• I submit my code changes under the same MIT License that covers the project.
  Feel free to contact the maintainers if that's a concern.

[azhavoro]

LGTM, worked for me

[azhavoro]

@tdhooghe Hi,
Thanks for the your contribution and could you add a line to the changelog about your change?

[bsekachev]

@tdhooghe

Thank you for the contribution, I will add a line to CONTRIBUTING.md later.

[tdhooghe]

Hi Boris, Apologies for my late response. I can still add a line in the changelog if you want? Kind regards, Thomas Op wo 12 okt. 2022 om 18:20 schreef Boris Sekachev ***@***.***

…

: @tdhooghe <https://github.com/tdhooghe> Thank you for the contribution, I will add a line to CONTRIBUTING.md later. — Reply to this email directly, view it on GitHub <#4960 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AOTQY2IV6C3MY6ZEMZZNNPTWC3QLZANCNFSM6AAAAAAQOFZZ4A> . You are receiving this because you were mentioned.Message ID: ***@***.***>

[bsekachev]

@tdhooghe
Would be great, thank you.