# Predictor

Predictor is used to predict/define/categorize images in a dataset using a previously trained model.

Min confidence determines what minimum precision is sufficient to accept a given prediction and create an appropriate classification category or label for an image based on it.

Prediction mode settings determine which elements in the dataset will be checked by the predictor:

  • Run predictor on all images from the dataset
  • Run predictor on all images from the dataset and replace old labels
  • Run predictor only on images without annotations. The rest of the images will stay unchanged.

Model determines which of the previously trained detection or classification models is selected for prediction.

Once started, as with the conversion, the predictor will run in the background, taking longer or shorter depending on the size of the dataset. When finished, you will receive a completion message and clicking on it will take you to the dataset with the new classifications or annotations.