Package org.tribuo.interop.onnx

Interface ExampleTransformer

All Superinterfaces:
com.oracle.labs.mlrg.olcut.config.Configurable, ProtoSerializable<org.tribuo.interop.onnx.protos.ExampleTransformerProto>, com.oracle.labs.mlrg.olcut.provenance.Provenancable<com.oracle.labs.mlrg.olcut.provenance.ConfiguredObjectProvenance>, Serializable
All Known Implementing Classes:
DenseTransformer, ImageTransformer
public interface ExampleTransformer extends com.oracle.labs.mlrg.olcut.config.Configurable, ProtoSerializable<org.tribuo.interop.onnx.protos.ExampleTransformerProto>, com.oracle.labs.mlrg.olcut.provenance.Provenancable<com.oracle.labs.mlrg.olcut.provenance.ConfiguredObjectProvenance>, Serializable
Transforms a SparseVector, extracting the features from it as a OnnxTensor.

This usually densifies the example, so can be a lot larger than the input example.

N.B. ONNX support is experimental, and may change without a major version bump.

  • Field Summary

    Fields inherited from interface org.tribuo.protos.ProtoSerializable

    DESERIALIZATION_METHOD_NAME, PROVENANCE_SERIALIZER

  • Method Summary

    Modifier and Type
    Method
    Description
    ai.onnxruntime.OnnxTensor
    transform(ai.onnxruntime.OrtEnvironment env, List<SparseVector> vectors)
    Converts a list of SparseVectors representing a batch of features into a OnnxTensor.
    ai.onnxruntime.OnnxTensor
    transform(ai.onnxruntime.OrtEnvironment env, SparseVector vector)
    Converts a SparseVector representing the features into a OnnxTensor.

    Methods inherited from interface com.oracle.labs.mlrg.olcut.config.Configurable

    postConfig

    Methods inherited from interface org.tribuo.protos.ProtoSerializable

    serialize

    Methods inherited from interface com.oracle.labs.mlrg.olcut.provenance.Provenancable

    getProvenance

  • Method Details

    • transform

      ai.onnxruntime.OnnxTensor transform(ai.onnxruntime.OrtEnvironment env, SparseVector vector) throws ai.onnxruntime.OrtException
      Converts a SparseVector representing the features into a OnnxTensor.

      It generates it as a single example minibatch.

      Parameters:
      env - The OrtEnvironment to create the tensor in.
      vector - The features to convert.
      Returns:
      A dense OnnxTensor representing this vector.
      Throws:
      ai.onnxruntime.OrtException - if the transformation failed.

    • transform

      ai.onnxruntime.OnnxTensor transform(ai.onnxruntime.OrtEnvironment env, List<SparseVector> vectors) throws ai.onnxruntime.OrtException
      Converts a list of SparseVectors representing a batch of features into a OnnxTensor.
      Parameters:
      env - The OrtEnvironment to create the tensor in.
      vectors - The batch of features to convert.
      Returns:
      A dense OnnxTensor representing this minibatch.
      Throws:
      ai.onnxruntime.OrtException - if the transformation failed.