nvinfer1::IInt8Calibrator Class Reference

Application-implemented interface for calibration. More...

Inheritance diagram for nvinfer1::IInt8Calibrator:

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

Detailed Description

Application-implemented interface for calibration.

Calibration is a step performed by the builder when deciding suitable scale factors for 8-bit inference.

It must also provide a method for retrieving representative images which the calibration process can use to examine the distribution of activations. It may optionally implement a method for caching the calibration result for reuse on subsequent runs.

Constructor & Destructor Documentation

~IInt8Calibrator()

virtual nvinfer1::IInt8Calibrator::~IInt8Calibrator ( )

inlinevirtual

Member Function Documentation

getBatchSize()

virtual int32_t nvinfer1::IInt8Calibrator::getBatchSize ( ) const

pure virtual

Get the batch size used for calibration batches.

Returns

The batch size.

Implemented in sample::anonymous_namespace{sampleEngines.cpp}::RndInt8Calibrator.

getBatch()

virtual bool nvinfer1::IInt8Calibrator::getBatch ( void *  bindings[], const char *  names[], int32_t  nbBindings  )

pure virtual

Get a batch of input for calibration.

The batch size of the input must match the batch size returned by getBatchSize().

Parameters

bindings	An array of pointers to device memory that must be updated to point to device memory containing each network input data.
names	The names of the network input for each pointer in the binding array.
nbBindings	The number of pointers in the bindings array.

Returns

False if there are no more batches for calibration.

See also

getBatchSize()

readCalibrationCache()

virtual const void* nvinfer1::IInt8Calibrator::readCalibrationCache ( std::size_t &  length )

pure virtual

Load a calibration cache.

Calibration is potentially expensive, so it can be useful to generate the calibration data once, then use it on subsequent builds of the network. The cache includes the regression cutoff and quantile values used to generate it, and will not be used if these do not batch the settings of the current calibrator. However, the network should also be recalibrated if its structure changes, or the input data set changes, and it is the responsibility of the application to ensure this.

Parameters

length

The length of the cached data, that should be set by the called function. If there is no data, this should be zero.

Returns

A pointer to the cache, or nullptr if there is no data.

writeCalibrationCache()

virtual void nvinfer1::IInt8Calibrator::writeCalibrationCache ( const void *  ptr, std::size_t  length  )

pure virtual

Save a calibration cache.

Parameters

ptr	A pointer to the data to cache.
length	The length in bytes of the data to cache.

See also

readCalibrationCache()

getAlgorithm()

virtual CalibrationAlgoType nvinfer1::IInt8Calibrator::getAlgorithm ( )

pure virtual

Get the algorithm used by this calibrator.

Returns

The algorithm used by the calibrator.

Implemented in nvinfer1::IInt8LegacyCalibrator, nvinfer1::IInt8MinMaxCalibrator, nvinfer1::IInt8EntropyCalibrator2, and nvinfer1::IInt8EntropyCalibrator.

---

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

• NvInfer.h