int8

Performs INT8 quantization of an ONNX model, and returns the ONNX ModelProto.

Functions

quantize

Applies INT8 quantization to an ONNX file using the compiler friendly heuristics.
quantize(onnx_path, calibration_method='entropy', calibration_data_reader=None, calibration_cache_path=None, op_types_to_quantize=None, op_types_to_exclude=None, nodes_to_quantize=None, nodes_to_exclude=None, use_external_data_format=True, intermediate_generated_files=[], verbose=False, trt_extra_plugin_lib_paths=None, high_precision_dtype='fp32', **kwargs)

Applies INT8 quantization to an ONNX file using the compiler friendly heuristics.

Quantization of [‘Add’, ‘AveragePool’, ‘BatchNormalization’, ‘Clip’, ‘Conv’, ‘ConvTranspose’, ‘Gemm’, ‘GlobalAveragePool’, ‘MatMul’, ‘MaxPool’, ‘Mul’] op types are supported.

Parameters:

  • onnx_path (str) –

  • calibration_method (str) –

  • calibration_data_reader (CalibrationDataReader) –

  • calibration_cache_path (str) –

  • op_types_to_quantize (List[str]) –

  • op_types_to_exclude (List[str]) –

  • nodes_to_quantize (List[str]) –

  • nodes_to_exclude (List[str]) –

  • use_external_data_format (bool) –

  • intermediate_generated_files (List[str]) –

  • verbose (bool) –

  • trt_extra_plugin_lib_paths (str) –

  • high_precision_dtype (str) –

Return type:

ModelProto