polygraphy.backend.trt.calibrator Namespace Reference

Functions
def	Calibrator (data_loader, cache=None, BaseClass=trt.IInt8MinMaxCalibrator, batch_size=None)

Variables
	data_loader
	_cache
	device_buffers
	batch_size
	data_loader_iter
	num_batches
	cache_contents
	has_cached_scales

Function Documentation

Calibrator()

def polygraphy.backend.trt.calibrator.Calibrator	(		data_loader,
			cache = None,
			BaseClass = trt.IInt8MinMaxCalibrator,
			batch_size = None
	)

Supplies calibration data to TensorRT to calibrate the network for INT8 inference.

Args:
    data_loader (Generator -> OrderedDict[str, numpy.ndarray]):
        A generator or iterable that yields a dictionary that maps input names to input NumPy buffers.

        In case you don't know details about the inputs ahead of time, you can access the
        `input_metadata` property in your data loader, which will be set to an `TensorMetadata` instance.
        Note that this does not work for generators or lists.

        The number of calibration batches is controlled by the number of items supplied
        by the data loader.


    cache (Union[str, file-like]):
            Path or file-like object to save/load the calibration cache.
            By default, the calibration cache is not saved.
    BaseClass (type):
            The type of calibrator to inherit from.
            Defaults to trt.IInt8MinMaxCalibrator.
    batch_size (int):
            [DEPRECATED] The size of each batch provided by the data loader.

Variable Documentation

data_loader

polygraphy.backend.trt.calibrator.data_loader

_cache

polygraphy.backend.trt.calibrator._cache

private

device_buffers

polygraphy.backend.trt.calibrator.device_buffers

batch_size

polygraphy.backend.trt.calibrator.batch_size

data_loader_iter

polygraphy.backend.trt.calibrator.data_loader_iter

num_batches

polygraphy.backend.trt.calibrator.num_batches

cache_contents

polygraphy.backend.trt.calibrator.cache_contents

has_cached_scales

polygraphy.backend.trt.calibrator.has_cached_scales