When creating a job, you will have an option to create either a manual job or an auto-annotation job. If you select auto-annotation, the entire job will be labeled automatically by a model, and you will have the option to edit the annotations after auto-annotaiton is complete.

​
Autolabel Playground

When you select the autolabel option, you will see a popup where you will have the option to adjust and decide on an optimal model configuration before kicking off the autolabelling process. You can:
  • Add labels that you wish to be used during the autolabelling process
  • Adjust the description for each label. It is recommended to always have something, even something simple, for the description, in order to help with model performance.
  • Adjust label confidnece levels before and after prediction, to find the optimal confidence level for each label
Autolabel Playground
It is recommended to test out the model runs on multiple different images in the job (the reshuffle button will give you 5 new random iamges from the job to test with). Once you have decided on an ideal configuration, you may save it and that configuration (labels, confidence levels, descriptions) will be used across all frames in the job during the autolabelling process.

​
Autolabelling Process

Once you press “Create,” the auto-labelling process starts in the background. You can navigate away to complete other tasks while the selected model generates the appropriate annotations in accordance with the confidence score provided per label. While we are confident on the performance of our flows and incorporated models, these annotations are best subject to review, for predictions are only as good as the confidence score and descriptions that are provided to labels of interest. It is always best to have a human review and adjust the automatically generated annotations in order to ensure quality.