Package org.tribuo.interop.tensorflow
Class TensorFlowFrozenExternalModel<T extends Output<T>>
java.lang.Object
org.tribuo.Model<T>
org.tribuo.interop.ExternalModel<T,TensorMap,org.tensorflow.Tensor>
org.tribuo.interop.tensorflow.TensorFlowFrozenExternalModel<T>
- All Implemented Interfaces:
com.oracle.labs.mlrg.olcut.provenance.Provenancable<ModelProvenance>
,Closeable
,Serializable
,AutoCloseable
,ProtoSerializable<org.tribuo.protos.core.ModelProto>
public final class TensorFlowFrozenExternalModel<T extends Output<T>>
extends ExternalModel<T,TensorMap,org.tensorflow.Tensor>
implements Closeable
A Tribuo wrapper around a TensorFlow frozen model.
The model's serialVersionUID is set to the major Tensorflow version number times 100.
N.B. TensorFlow support is experimental and may change without a major version bump.
- See Also:
-
Field Summary
Modifier and TypeFieldDescriptionstatic final int
Protobuf serialization version.Fields inherited from class org.tribuo.interop.ExternalModel
DEFAULT_BATCH_SIZE, featureBackwardMapping, featureForwardMapping
Fields inherited from class org.tribuo.Model
ALL_OUTPUTS, BIAS_FEATURE, featureIDMap, generatesProbabilities, name, outputIDInfo, provenance, provenanceOutput
Fields inherited from interface org.tribuo.protos.ProtoSerializable
DESERIALIZATION_METHOD_NAME, PROVENANCE_SERIALIZER
-
Method Summary
Modifier and TypeMethodDescriptionvoid
close()
protected TensorMap
convertFeatures
(SparseVector input) Converts from a SparseVector using the external model's indices into the ingestion format for the external model.protected TensorMap
convertFeaturesList
(List<SparseVector> input) Converts from a list of SparseVector using the external model's indices into the ingestion format for the external model.protected List<Prediction<T>>
convertOutput
(org.tensorflow.Tensor output, int[] numValidFeatures, List<Example<T>> examples) Converts a tensor into a prediction.protected Prediction<T>
convertOutput
(org.tensorflow.Tensor output, int numValidFeatures, Example<T> example) Converts a tensor into a prediction.copy
(String newName, ModelProvenance newProvenance) Copies a model, replacing its provenance and name with the supplied values.static <T extends Output<T>>
TensorFlowFrozenExternalModel<T>createTensorflowModel
(OutputFactory<T> factory, Map<String, Integer> featureMapping, Map<T, Integer> outputMapping, String outputName, FeatureConverter featureConverter, OutputConverter<T> outputConverter, String filename) Creates a TensorflowFrozenExternalModel by loading in a frozen graph.static TensorFlowFrozenExternalModel<?>
deserializeFromProto
(int version, String className, com.google.protobuf.Any message) Deserialization factory.protected org.tensorflow.Tensor
externalPrediction
(TensorMap input) Runs the session to make a prediction.getTopFeatures
(int n) Gets the topn
features associated with this model.org.tribuo.protos.core.ModelProto
Serializes this object to a protobuf.Methods inherited from class org.tribuo.interop.ExternalModel
createFeatureMap, createOutputInfo, getBatchSize, getExcuse, innerPredict, predict, setBatchSize, validateFeatureMapping
Methods inherited from class org.tribuo.Model
castModel, copy, createDataCarrier, deserialize, deserializeFromFile, deserializeFromStream, generatesProbabilities, getExcuses, getFeatureIDMap, getName, getOutputIDInfo, getProvenance, predict, predict, serializeToFile, serializeToStream, setName, toString, validate
-
Field Details
-
CURRENT_VERSION
public static final int CURRENT_VERSIONProtobuf serialization version.- See Also:
-
-
Method Details
-
deserializeFromProto
public static TensorFlowFrozenExternalModel<?> deserializeFromProto(int version, String className, com.google.protobuf.Any message) throws com.google.protobuf.InvalidProtocolBufferException Deserialization factory.- Parameters:
version
- The serialized object version.className
- The class name.message
- The serialized data.- Returns:
- The deserialized object.
- Throws:
com.google.protobuf.InvalidProtocolBufferException
- If the protobuf could not be parsed from themessage
.
-
convertFeatures
Description copied from class:ExternalModel
Converts from a SparseVector using the external model's indices into the ingestion format for the external model.- Specified by:
convertFeatures
in classExternalModel<T extends Output<T>,
TensorMap, org.tensorflow.Tensor> - Parameters:
input
- The features using external indices.- Returns:
- The ingestion format for the external model.
-
convertFeaturesList
Description copied from class:ExternalModel
Converts from a list of SparseVector using the external model's indices into the ingestion format for the external model.- Specified by:
convertFeaturesList
in classExternalModel<T extends Output<T>,
TensorMap, org.tensorflow.Tensor> - Parameters:
input
- The features using external indices.- Returns:
- The ingestion format for the external model.
-
externalPrediction
Runs the session to make a prediction.Closes the input tensor after the prediction has been made.
- Specified by:
externalPrediction
in classExternalModel<T extends Output<T>,
TensorMap, org.tensorflow.Tensor> - Parameters:
input
- The input in the external model's format.- Returns:
- A tensor representing the output.
-
convertOutput
protected Prediction<T> convertOutput(org.tensorflow.Tensor output, int numValidFeatures, Example<T> example) Converts a tensor into a prediction. Closes the output tensor after it's been converted.- Specified by:
convertOutput
in classExternalModel<T extends Output<T>,
TensorMap, org.tensorflow.Tensor> - Parameters:
output
- The output of the external model.numValidFeatures
- The number of valid features in the input.example
- The input example, used to construct the Prediction.- Returns:
- A
Prediction
representing this tensor output.
-
convertOutput
protected List<Prediction<T>> convertOutput(org.tensorflow.Tensor output, int[] numValidFeatures, List<Example<T>> examples) Converts a tensor into a prediction. Closes the output tensor after it's been converted.- Specified by:
convertOutput
in classExternalModel<T extends Output<T>,
TensorMap, org.tensorflow.Tensor> - Parameters:
output
- The output of the external model.numValidFeatures
- An array with the number of valid features in each example.examples
- The input examples, used to construct the Predictions.- Returns:
- A list of
Prediction
representing this tensor output.
-
getTopFeatures
Description copied from class:Model
Gets the topn
features associated with this model.If the model does not produce per output feature lists, it returns a map with a single element with key Model.ALL_OUTPUTS.
If the model cannot describe it's top features then it returns
Collections.emptyMap()
.- Specified by:
getTopFeatures
in classModel<T extends Output<T>>
- Parameters:
n
- the number of features to return. If this value is less than 0, all features should be returned for each class, unless the model cannot score it's features.- Returns:
- a map from string outputs to an ordered list of pairs of feature names and weights associated with that feature in the model
-
copy
Description copied from class:Model
Copies a model, replacing its provenance and name with the supplied values.Used to provide the provenance removal functionality.
-
close
public void close()- Specified by:
close
in interfaceAutoCloseable
- Specified by:
close
in interfaceCloseable
-
serialize
public org.tribuo.protos.core.ModelProto serialize()Description copied from interface:ProtoSerializable
Serializes this object to a protobuf. -
createTensorflowModel
public static <T extends Output<T>> TensorFlowFrozenExternalModel<T> createTensorflowModel(OutputFactory<T> factory, Map<String, Integer> featureMapping, Map<T, Integer> outputMapping, String outputName, FeatureConverter featureConverter, OutputConverter<T> outputConverter, String filename) Creates a TensorflowFrozenExternalModel by loading in a frozen graph.- Type Parameters:
T
- The type of the output.- Parameters:
factory
- The output factory.featureMapping
- The feature mapping between Tribuo's names and the TF integer ids.outputMapping
- The output mapping between Tribuo's names and the TF integer ids.outputName
- The name of the output tensor.featureConverter
- The feature transformation function.outputConverter
- The output transformation function.filename
- The filename to load the graph from.- Returns:
- The TF model wrapped in a Tribuo ExternalModel.
-