Generally would follow this documentation (https://opencv.github.io/cvat/docs/administration/advanced/installation_automatic_annotation/)
In the CVAT directory, run:
-
Stop all containers first, if any.
docker compose down -
Start CVAT together with the plugin use for AI automatic annotation assistant.
docker compose -f docker-compose.yml -f components serverless/docker-compose.serverless.yml up -d -
Install
nuctl*wget https://github.com/nuclio/nuclio/releases/download/<version>/nuctl-<version>-linux-amd64 -
After downloading the nuclio, give it a proper permission and do a softlink.*
sudo chmod +x nuctl-<version>-linux-amd64 sudo ln -sf $(pwd)/nuctl-<version>-linux-amd64 /usr/local/bin/nuctl -
Build the docker image and run the container. After it is done, you can use the model right away in the CVAT.
./serverless/deploy_cpu.sh path/to/this/folder/
Note: * is a one time step.
-
function.yaml: Declare the model so it can be understand by CVAT. It includes setup the docker environment. -
main.py: Contain the handle function that will serve as the endpoint used by CVAT to run detection. -
custom-yolov8n.pt: Your custom yolov8 model.