tensorflow::serving::ClassifierInterface Class Reference

#include <classifier.h>

Public Member Functions
virtual Status	Classify (const ClassificationRequest &request, ClassificationResult *result)=0

Detailed Description

Model-type agnostic interface for performing classification.

Specific implementations will exist for different model types (e.g. TensorFlow SavedModel) that can convert the request into a model specific input and know how to convert the output into a generic ClassificationResult.

Definition at line 31 of file classifier.h.

Member Function Documentation

Classify()

virtual Status tensorflow::serving::ClassifierInterface::Classify ( const ClassificationRequest &  request, ClassificationResult *  result  )

pure virtual

Given a ClassificationRequest, populates the ClassificationResult with the result.

Parameters

request	Input request specifying the model/signature to query along with the data payload.
result	The output classifications that will get populated.

Returns

A status object indicating success or failure.

---

The documentation for this class was generated from the following file:

• tensorflow_serving/apis/classifier.h