Template Class Int8Calibrator

Inheritance Relationships

Base Type

  • private Algorithm

Class Documentation

template<typename Algorithm , typename DataLoaderUniquePtr >
class trtorch::ptq :: Int8Calibrator : private Algorithm

Generic Int8Calibrator implementation based on a specified TensorRT calibration algorithm and a LibTorch DataLoader.

Template Parameters
  • Algorithm : class nvinfer1::IInt8Calibrator (Default: nvinfer1::IInt8EntropyCalibrator2) - Algorithm to use

  • DataLoaderUniquePtr : std::unique_ptr<torch::data::DataLoader> - DataLoader type

Public Functions

Int8Calibrator ( DataLoaderUniquePtr dataloader , const std::string & cache_file_path , bool use_cache )

Construct a new Int8Calibrator object.

Using the provided DataLoader, construct a calibrator that can be used for PTQ with TRTorch

Parameters
  • dataloader : std::unqiue_ptr<torch::data::DataLoader> - A unique pointer to the DataLoader, should be what is returned from the make_data_loader factory

  • cache_file_path : const std::string& - A path to store / find the calibration cache

  • use_cache : : bool - Whether to use the cache (if it exists)

int getBatchSize ( ) const override

Get the Batch Size for the next batch (always 1 due to issues with TRT and explicit batch)

Return

int

bool getBatch ( void * bindings [], const char * names [], int nbBindings ) override

Get the next Batch.

Return

true - There is a new batch for the calibrator to consume

Return

false - There is not a new batch for the calibrator to consume

Parameters
  • bindings : void*[] - An array of binding pointers (fed in from TensorRT calibrator), these buffers should be filed with batch data for each input

  • names : const char*[] - Names of bindings

  • nbBindings : int - Number of bindings

const void * readCalibrationCache ( size_t & length ) override

Read calibration cache.

How to read from the calibration cache, only enabled if use_cache is set

Return

const void* - Pointer to cache data

Parameters
  • length :

void writeCalibrationCache ( const void * cache , size_t length ) override

Write calibration cache.

Write a the calibration cache provided by TensorRT to a specified file

Parameters
  • cache : const void* - cache data

  • length : size_t - length of cache

operator nvinfer1::IInt8Calibrator* ( )

operator to cast to nvinfer1::IInt8Calibrator*

Convience function to convert to a IInt8Calibrator* to easily be assigned to the ptq_calibrator field in ExtraInfo

Return

nvinfer1::IInt8Calibrator*