`neural_compressor.adaptor.ox_utils.quantizer`

Quantizer for onnx models.

Module Contents

Classes

Quantizer class.

class neural_compressor.adaptor.ox_utils.quantizer.Quantizer(model, q_config, mode, static, quantization_params, op_types_to_quantize, fallback_list=['fp32'], reduce_range=None, add_qdq_pair_to_weight=False, optypes_to_exclude_output_quant=[], dedicated_qdq_pair=False, backend='CPUExecutionProvider')[source]: Quantizer class.