TensorRT 8.5.3
nvinfer1::IInt8MinMaxCalibrator Class Reference

#include <NvInfer.h>

Inheritance diagram for nvinfer1::IInt8MinMaxCalibrator:
nvinfer1::IInt8Calibrator

Public Member Functions

CalibrationAlgoType getAlgorithm () noexcept override
 
virtual ~IInt8MinMaxCalibrator () noexcept=default
 
- Public Member Functions inherited from nvinfer1::IInt8Calibrator
virtual int32_t getBatchSize () const noexcept=0
 Get the batch size used for calibration batches. More...
 
virtual bool getBatch (void *bindings[], char const *names[], int32_t nbBindings) noexcept=0
 Get a batch of input for calibration. More...
 
virtual void const * readCalibrationCache (std::size_t &length) noexcept=0
 Load a calibration cache. More...
 
virtual void writeCalibrationCache (void const *ptr, std::size_t length) noexcept=0
 Save a calibration cache. More...
 
virtual ~IInt8Calibrator () noexcept=default
 

Detailed Description

MinMax Calibrator. It supports per activation tensor scaling.

Constructor & Destructor Documentation

◆ ~IInt8MinMaxCalibrator()

virtual nvinfer1::IInt8MinMaxCalibrator::~IInt8MinMaxCalibrator ( )
virtualdefaultnoexcept

Member Function Documentation

◆ getAlgorithm()

CalibrationAlgoType nvinfer1::IInt8MinMaxCalibrator::getAlgorithm ( )
inlineoverridevirtualnoexcept

Signal that this is the MinMax Calibrator.

Implements nvinfer1::IInt8Calibrator.


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