search

cvat-ai / cvat

Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.
https://cvat.ai
MIT License
11.88k stars 2.9k forks source link

using yolo for assisted labeling #7935

Open williamhoole opened 1 month ago

williamhoole commented 1 month ago

Actions before raising this issue

Is your feature request related to a problem? Please describe.

I am not that experienced with CVAT but i see you are able to do assisted labeling with a pre-trained model. However the process of getting this to work is pretty complex and i havent gotten it to work. I would like to use either a yolov5 or yolov8 model from ultralytics to assist during my annotation process. I have the weights locally on my computer and wold like to import it to cvat. Is it possible to do this online? or will i have to download cvat with all its docker containers and get that to running... followed by the nucli server etc. could someone assist on how to do this in a more simpler way? Since Yolo is probably the most common object detection framework.

Describe the solution you'd like

No response

Describe alternatives you've considered

No response

Additional context

No response

davy-blavette commented 1 month ago

It seems to me that CVAT doesn't offer Yolov5 or Yolov8 for reasons of license incompatibility, but it is possible to use them locally if you set the serveless correctly.

O-J1 commented 12 hours ago

It seems to me that CVAT doesn't offer Yolov5 or Yolov8 for reasons of license incompatibility, but it is possible to use them locally if you set the serveless correctly.

Do you happen to have or know of any guidance on this?