Custom Object Detection model with MLFlow tracking

diegosaenzmaqta
diegosaenzmaqta Dataiku DSS Core Designer, Dataiku DSS ML Practitioner, Dataiku DSS Adv Designer, Registered Posts: 1

I am trying to get the Yolov8 object detection model as a MLFlow python function to then automatically score and evaluate from the saved model. When I am setting mlflow_extension.set_run_inference_info and project.create_mlflow_pyfunc_model to "OTHER" prediction type, I cant use the mlflow_version.evaluate method on the selected saved model.

Any ideas how to set up the prediction type for this task?


Operating system used: Oracle Linux Server 8.8


Operating system used: Oracle Linux Server 8.8

Answers

  • HarizoR
    HarizoR Dataiker, Alpha Tester, Registered Posts: 138 Dataiker

    Hi,

    Unfortunately Dataiku does not have the ability to evaluate object detection models in its mlflow integration. You can use it for scoring, but not for evaluation reports.

    Best,

    Harizo

Setup Info
    Tags
      Help me…