Data Split
Page the user sees when they enter Model Playground
This page essentially gives an overview of the various splits already tried when a user enters the model building phase after data annotation and quality control steps.

Different parameters of the created splits on this page

  • Split name
  • Problem - This is the type of model you want to use for the model building phase. It includes: Attribute prediction, Label class prediction, Object detection, Image tag prediction, Instance segmentation, Semantic segmentation.
  • Creation date
  • Created by - This helps to track which user is experimenting with a particular model.
  • Images - This value gives an idea of the number of images (Total, Train, Test, Validation) that were used for a particular set of experiments/model types.
  • Experiments - Total number of experiments a user has carried out for a model type.

Actions you can perform on this page

  • Open - This takes you to the main Model Playground Dashboard where you can compare and create new model building experiments.
  • Split info - This links you to the split results page in Model Playground.
  • Delete - Delete a particular split