Class LabelTransformer

java.lang.Object
org.tribuo.interop.onnx.LabelTransformer
All Implemented Interfaces:
com.oracle.labs.mlrg.olcut.config.Configurable, com.oracle.labs.mlrg.olcut.provenance.Provenancable<com.oracle.labs.mlrg.olcut.provenance.ConfiguredObjectProvenance>, Serializable, OutputTransformer<Label>
public class LabelTransformer extends Object implements OutputTransformer<Label>
Can convert an OnnxValue into a Prediction or a Label.

Accepts both a tuple (tensor,sequence(map(long,float))) and a single tensor. The former is usually produced by scikit-learn or similar, the latter is produced by pytorch.

See Also:

  • Constructor Details

    • LabelTransformer

      public LabelTransformer()

  • Method Details

    • transformToPrediction

      public Prediction<Label> transformToPrediction(List<ai.onnxruntime.OnnxValue> tensor, ImmutableOutputInfo<Label> outputIDInfo, int numValidFeatures, Example<Label> example)
      Description copied from interface: OutputTransformer
      Converts a OnnxValue into a Prediction.
      Specified by:
      transformToPrediction in interface OutputTransformer<Label>
      Parameters:
      tensor - The value to convert.
      outputIDInfo - The output info to use to identify the outputs.
      numValidFeatures - The number of valid features used by the prediction.
      example - The example to insert into the prediction.
      Returns:
      A prediction object.

    • transformToOutput

      public Label transformToOutput(List<ai.onnxruntime.OnnxValue> tensor, ImmutableOutputInfo<Label> outputIDInfo)
      Description copied from interface: OutputTransformer
      Converts a OnnxValue into the specified output type.
      Specified by:
      transformToOutput in interface OutputTransformer<Label>
      Parameters:
      tensor - The value to convert.
      outputIDInfo - The output info to use to identify the outputs.
      Returns:
      A output.

    • transformToBatchPrediction

      public List<Prediction<Label>> transformToBatchPrediction(List<ai.onnxruntime.OnnxValue> tensor, ImmutableOutputInfo<Label> outputIDInfo, int[] numValidFeatures, List<Example<Label>> examples)
      Description copied from interface: OutputTransformer
      Converts a OnnxValue containing multiple outputs into a list of Predictions.
      Specified by:
      transformToBatchPrediction in interface OutputTransformer<Label>
      Parameters:
      tensor - The value to convert.
      outputIDInfo - The output info to use to identify the outputs.
      numValidFeatures - The number of valid features used by the prediction.
      examples - The example to insert into the prediction.
      Returns:
      A list of predictions.

    • transformToBatchOutput

      public List<Label> transformToBatchOutput(List<ai.onnxruntime.OnnxValue> tensor, ImmutableOutputInfo<Label> outputIDInfo)
      Description copied from interface: OutputTransformer
      Converts a OnnxValue containing multiple outputs into a list of Outputs.
      Specified by:
      transformToBatchOutput in interface OutputTransformer<Label>
      Parameters:
      tensor - The value to convert.
      outputIDInfo - The output info to use to identify the outputs.
      Returns:
      A list of outputs.

    • generatesProbabilities

      public boolean generatesProbabilities()
      Description copied from interface: OutputTransformer
      Does this OutputTransformer generate probabilities.
      Specified by:
      generatesProbabilities in interface OutputTransformer<Label>
      Returns:
      True if it produces a probability distribution in the Prediction.

    • toString

      public String toString()
      Overrides:
      toString in class Object

    • getProvenance

      public com.oracle.labs.mlrg.olcut.provenance.ConfiguredObjectProvenance getProvenance()
      Specified by:
      getProvenance in interface com.oracle.labs.mlrg.olcut.provenance.Provenancable<com.oracle.labs.mlrg.olcut.provenance.ConfiguredObjectProvenance>