An Efemarai project groups together multiple datasets, models and operational domains that you use when working on a given ML problem. We recommend setting up a project per source code repository where you develop your ML solution.


This is how a project can be defined efemarai.yaml:

  name: Traffic Sign Detection
  description: Implement multiple models for detecting traffic signs.
  problem_type: ObjectDetection


  • name: unique name of the project

  • problem_type: type of machine learning problem the project represents. Supported problems:

    • Classification - predict image label

    • ObjectDetection - predict object bounding box

    • InstanceSegmentation - predict object mask

    • SemanticSegmentation - predict label of each pixel

    • ImageRegression - predict target values

    • Keypoints - predict location of keypoints

    • Custom - the most flexible way that allows for any internal representation

  • description (optional): free text description of the project