Class ImageTransformer<T extends Output<T>>

java.lang.Object

org.tribuo.interop.tensorflow.ImageTransformer<T>

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<T>

public class ImageTransformer<T extends Output<T>>
extends Object
implements ExampleTransformer<T>

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.

See Also:

• Serialized Form

Constructor Summary

Constructors

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

Method Summary

Modifier and Type	Method	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()
org.tensorflow.Tensor<?>	transform(List<Example<T>> examples, ImmutableFeatureMap featureIDMap)	Transform implicitly pads unseen values with zero.
org.tensorflow.Tensor<?>	transform(List<SparseVector> vectors)	Converts a list of SparseVectors representing a batch of features into a Tensor.
org.tensorflow.Tensor<?>	transform(Example<T> example, ImmutableFeatureMap featureIDMap)	Transform implicitly pads unseen values with zero.
org.tensorflow.Tensor<?>	transform(SparseVector vector)	Converts a SparseVector representing the features into a Tensor.

Methods inherited from class java.lang.Object

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

Constructor Details

ImageTransformer

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

Method Details

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 org.tensorflow.Tensor<?> transform(Example<T> example,
 ImmutableFeatureMap featureIDMap)

Transform implicitly pads unseen values with zero.

Specified by:

transform in interface ExampleTransformer<T extends Output<T>>

Parameters:

example - The example to transform.

featureIDMap - The feature id mapping to use.

Returns:

A 3d tensor, (width, height, channels) for this example.

transform

public org.tensorflow.Tensor<?> transform(List<Example<T>> examples,
 ImmutableFeatureMap featureIDMap)

Transform implicitly pads unseen values with zero.

Converts a batch of examples into a Tensor.

Specified by:

transform in interface ExampleTransformer<T extends Output<T>>

Parameters:

examples - The examples to transform.

featureIDMap - The feature id mapping to use.

Returns:

A 4d tensor, (batch-id, width, height, channels) for this example.

transform

public org.tensorflow.Tensor<?> transform(SparseVector vector)

Description copied from interface: ExampleTransformer

Converts a SparseVector representing the features into a Tensor.

It generates it as a single example minibatch.

Specified by:

transform in interface ExampleTransformer<T extends Output<T>>

Parameters:

vector - The features to convert.

Returns:

A dense Tensor representing this vector.

transform

public org.tensorflow.Tensor<?> transform(List<SparseVector> vectors)

Description copied from interface: ExampleTransformer

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

Specified by:

transform in interface ExampleTransformer<T extends Output<T>>

Parameters:

vectors - The batch of features to convert.

Returns:

A dense Tensor representing this minibatch.

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<T extends Output<T>>