org.apache.ignite.ml.inference.parser

Class TensorFlowGraphModelParser<I,O>

java.lang.Object

org.apache.ignite.ml.inference.parser.TensorFlowBaseModelParser<I,O>

org.apache.ignite.ml.inference.parser.TensorFlowGraphModelParser<I,O>

Type Parameters:

I - Type of model input.

O - Type of model output.

All Implemented Interfaces:

Serializable, ModelParser<I,O,Model<I,O>>

public class TensorFlowGraphModelParser<I,O>
extends TensorFlowBaseModelParser<I,O>

Implementation of TensorFlow model parser that accepts serialized graph definition.

See Also:

Serialized Form

Nested Class Summary

Nested classes/interfaces inherited from class org.apache.ignite.ml.inference.parser.TensorFlowBaseModelParser

TensorFlowBaseModelParser.InputTransformer<I>, TensorFlowBaseModelParser.OutputTransformer<O>

Constructor Summary

Constructors

Constructor and Description
TensorFlowGraphModelParser()

Method Summary

Modifier and Type	Method and Description
org.tensorflow.Session	parseModel(byte[] mdl) Parses model specified in serialized form as byte array.

Methods inherited from class org.apache.ignite.ml.inference.parser.TensorFlowBaseModelParser

parse, withInput, withOutput

Methods inherited from class java.lang.Object

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

Constructor Detail

TensorFlowGraphModelParser

public TensorFlowGraphModelParser()

Method Detail

parseModel

public org.tensorflow.Session parseModel(byte[] mdl)

Parses model specified in serialized form as byte array.

Specified by:

parseModel in class TensorFlowBaseModelParser<I,O>

Parameters:

mdl - Inference model in serialized form as byte array.

Returns:

TensorFlow session that encapsulates the TensorFlow graph parsed from serialized model.