Prediction settings

Overview

To score (predict) new data using a built model through the H2O Hydrogen Torch UI, H2O Hydrogen Torch requires the specification of certain settings refer as prediction settings. The predictions settings are a set of settings comprised of a certain dataset, prediction, and environment settings similar to those utilized when creating an experiment (model).

note

To learn how to deploy a built model through the H2O Hydrogen Torch UI, see H2O Hydrogen Torch UI.

The available settings for a particular prediction differ based on the problem type of the built model and the selected experience level. You can view the specific prediction settings of a particular problem type on the following pages:

• Image
  • Prediction settings: Image regression
  • Prediction settings: 3D image regression
  • Prediction settings: Image classification
  • Prediction settings: 3D image classification
  • Prediction settings: Image metric learning
  • Prediction settings: Image object detection
  • Prediction settings: Image semantic segmentation
  • Prediction settings: 3D image semantic segmentation
  • Prediction settings: Image instance segmentation
• Text
  • Prediction settings: Text regression
  • Prediction settings: Text classification
  • Prediction settings: Text sequence to sequence
  • Prediction settings: Text span prediction
  • Prediction settings: Text token classification
  • Prediction settings: Text metric learning
• Audio
  • Prediction settings: Audio regression
  • Prediction settings: Audio classification
• Speech
  • Prediction settings: Speech recognition

---

Feedback

• Submit and view feedback for this page
• Send feedback about H2O Hydrogen Torch to cloud-feedback@h2o.ai