org.tribuo.interop.onnx

Class ImageTransformer

java.lang.Object

org.tribuo.interop.onnx.ImageTransformer

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, ExampleTransformer

public class ImageTransformer
extends Object
implements ExampleTransformer

Image transformer. Assumes the feature id numbers are linearised ids of the form [0,0,0] = 0, [1,0,0] = 1, ..., [i,0,0] = i, [0,1,0] = i+1, ..., [i,j,0] = i*j, ... [0,0,1] = (i*j)+1, ..., [i,j,k] = i*j*k.

ONNX expects images in the format [channels,height,width].

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
ImageTransformer(int channels, int height, int width)

Method Summary

Modifier and Type	Method and Description
com.oracle.labs.mlrg.olcut.provenance.ConfiguredObjectProvenance	getProvenance()
void	postConfig() Used by the OLCUT configuration system, and should not be called by external code.
String	toString()
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 class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Constructor Detail

ImageTransformer

public ImageTransformer(int channels,
                        int height,
                        int width)

Method Detail

postConfig

public void postConfig()

Used by the OLCUT configuration system, and should not be called by external code.

Specified by:

postConfig in interface com.oracle.labs.mlrg.olcut.config.Configurable

transform

public ai.onnxruntime.OnnxTensor transform(ai.onnxruntime.OrtEnvironment env,
                                           SparseVector vector)
                                    throws ai.onnxruntime.OrtException

Description copied from interface: ExampleTransformer

Converts a SparseVector representing the features into a OnnxTensor.

It generates it as a single example minibatch.

Specified by:

transform in interface ExampleTransformer

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

public ai.onnxruntime.OnnxTensor transform(ai.onnxruntime.OrtEnvironment env,
                                           List<SparseVector> vectors)
                                    throws ai.onnxruntime.OrtException

Description copied from interface: ExampleTransformer

Converts a list of SparseVectors representing a batch of features into a OnnxTensor.

Specified by:

transform in interface ExampleTransformer

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.

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>