GeneXus Cognitive API - Predict procedure

Makes a prediction using a custom model based on the input data.

Parameters

• in:&dataInput:: DataInput, GeneXusAI.Custom
  The input data item.

• in:&model :: Model, GeneXusAI.Custom
  The model information used to predict.

• in:&provider :: Provider, GeneXusAI.Configuration
  Provider settings.

• inout:&Messages :: Messages, GeneXus.Common
  A collection of warning and error messages returned by the task. You should check in your code if an error was returned. Refer to error codes and descriptions for more information.

• out:&DataOutput:: DataOutput, GeneXusAI.Custom
  Output data item.

Configuration

The following table resumes the configuration properties (access credentials) you must set in order to use this AI task.

Sample

After deploying your model (trained with the Mamaevs' Flowers Recognition dataset) and taking the following (unseen) image input, the table below shows the prediction made for each provider and the time it takes for processing it.

{
     "Label": "dandelion",
     "Confidence": 0.915
}

{
    "Label": "dandelion",
    "Confidence": 0.945
}

{
    "Label": "dandelion",
    "Confidence": 0.974
}

Notes

• If you want to get a set of possible candidates, use a predefined GeneXusAI task instead of the Predict procedure (e.g. use Classify procedure if your model was trained for predicting Labels, or DetectObjects for predicting Regions).

Scope

Availability

This procedure is available as of GeneXus 16 upgrade 6.

• As of GeneXus 16 upgrade 8
  -  Google Auto ML is available.

See also

• GeneXus Cognitive API - Train procedure
• HowTo: Build a custom model for GeneXus Cognitive API