tensorflow::serving::RegressorInterface

This is an abstract class.

#include <regressor.h>

Model agnostic interface for performing regression.

Summary

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 RegressionResult.

Constructors and Destructors

~RegressorInterface()

Public functions

Regress(const RegressionRequest & request, RegressionResult *result)=0
virtual Status
Given a RegressionRequest, populates the RegressionResult with the result.

Public functions

Regress

virtual Status Regress(
  const RegressionRequest & request,
  RegressionResult *result
)=0

Given a RegressionRequest, populates the RegressionResult with the result.

Details
Parameters
request
Input request specifying the model/signature to query along with the data payload.
result
The output regression results that will get populated.
Returns
A status object indicating success or failure.

~RegressorInterface

virtual  ~RegressorInterface()=default