Template Class Int8Calibrator¶
Defined in File ptq.h
Inheritance Relationships¶
Base Type¶
private Algorithm
Class Documentation¶
-
template<typename Algorithm, typename DataLoaderUniquePtr>
class 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
-
inline 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 Torch-TensorRT
- 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)
- inline int getBatchSize () const noexceptoverride
Get the Batch Size for the next batch (always 1 due to issues with TRT and explicit batch)
- Returns
int
- inline bool getBatch (void *bindings[], const char *names[], int nbBindings) noexceptoverride
Get the next Batch.
- 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
- Returns
true - There is a new batch for the calibrator to consume
false - There is not a new batch for the calibrator to consume
- inline const void * readCalibrationCache (size_t &length) noexceptoverride
Read calibration cache.
How to read from the calibration cache, only enabled if use_cache is set
- Parameters
length –
- Returns
const void* - Pointer to cache data
- inline void writeCalibrationCache (const void *cache, size_t length) noexceptoverride
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
-
inline 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 CompileSpec
- Returns
nvinfer1::IInt8Calibrator*
