accuracy_based_auto_calibration

import amct_onnx as amct
from amct_onnx.common.auto_calibration import AutoCalibrationEvaluatorBase

# You need to implement the AutoCalibrationEvaluator's calibration(), evaluate() and metric_eval() funcs
class AutoCalibrationEvaluator(AutoCalibrationEvaluatorBase):
    """ subclass of AutoCalibrationEvaluatorBase"""
    def __init__(self, target_loss, batch_num):
        super(AutoCalibrationEvaluator, self).__init__()
        self.target_loss = target_loss
        self.batch_num = batch_num

    def calibration(self, model_file):
        """ implement the calibration function of AutoCalibrationEvaluatorBase
            calibration() need to finish the calibration inference procedure
            so the inference batch num need to >= the batch_num pass to create_quant_config
        """
        onnx_forward(onnx_model=model_file, batch_size=32, iterations=self.batch_num)

    def evaluate(self, model_file):
        """ implement the evaluate function of AutoCalibrationEvaluatorBase
            params: model_file in .onnx
            return: the accuracy of input model on the eval dataset, or other metric which
                    can describe the 'accuracy' of model
        """
        top1, top5 = onnx_forward(onnx_model=model_file, batch_size=32, iterations=5)
        return top1

    def metric_eval(self, original_metric, new_metric):
        """ implement the metric_eval function of AutoCalibrationEvaluatorBase
            params: original_metric: the returned accuracy of evaluate() on non quantized model
                    new_metric: the returned accuracy of evaluate() on fake quant model
            return:
                   [0]: whether the accuracy loss between non quantized model and fake quant model
                        can satisfy the requirement
                   [1]: the accuracy loss between non quantized model and fake quant model
        """
        loss = original_metric - new_metric
        if loss * 100 < self.target_loss:
            return True, loss
        return False, loss
   ...
 
    config_json_file = os.path.join(TMP, 'config.json')
    skip_layers = []
    batch_num = 1
    model_file = "mobilenet_v2.onnx"
    amct.create_quant_config(
        config_file=config_json_file, model_file=model_file, skip_layers=skip_layers, batch_num=batch_num,
        activation_offset=True, config_defination=None)

    # 1. step1 create quant config json file
    scale_offset_record_file = os.path.join(TMP, 'scale_offset_record.txt')
    result_path = os.path.join(PATH, 'results/mobilenet_v2')

    # 2. step2 construct the instance of AutoCalibrationEvaluator
    evaluator = AutoCalibrationEvaluator(target_loss=0.5, batch_num=batch_num)

    # 3. step3 using the accuracy_based_auto_calibration to quantized the model
    amct.accuracy_based_auto_calibration(
        model_file=model_file,
        model_evaluator=evaluator,
        config_file=config_json_file,
        record_file=scale_offset_record_file,
        save_dir=result_path,
        strategy='BinarySearch',
        sensitivity='CosineSimilarity'
    )