Simplified Configuration File

The following table lists the simplified configuration file. The file is stored in the /amct_tensorflow/proto/calibration_config_ascend_tf.proto directory in the installation directory.

**Table 1** Description of the calibration_config_ascend_tf.proto parameter
Message	Required	Type	Parameter	Description
AMCTConfig	-	-	-	Simplified PTQ configuration of AMCT.
	optional	bool	activation_offset	Whether to quantize activations with offset. It is a global configuration parameter. true: with offset. Activations are asymmetrically quantized. false: without offset. Activations are symmetrically quantized.
	repeated	string	skip_layers	Layers to skip quantization.
	repeated	string	skip_layer_types	Types of layers to skip quantization.
	optional	CalibrationConfig	common_config	Common quantization configuration, which is a global parameter. Use this configuration if a layer is not overridden by override_layer_types or override_layer_configs. Parameter priority: override_layer_configs > override_layer_types > common_config
	repeated	OverrideLayerType	override_layer_types	Certain types of layers to override the quantization configurations. It is used to determine which layers are to be differentiatedly quantized. By using this parameter, you can perform differentiated quantization on some layers to change the quantization factor search step from 0.01 to 0.02. Parameter priority: override_layer_configs > override_layer_types > common_config
	repeated	OverrideLayer	override_layer_configs	Layer to override the quantization configurations. It is used to determine which layers are to be differentiatedly quantized. By using this parameter, you can perform differentiated quantization on some layers to change the quantization factor search step from 0.01 to 0.02. Parameter priority: override_layer_configs > override_layer_types > common_config
	optional	bool	do_fusion	BN fusion switch. Defaults to true, indicating BN fusion enabled.
	repeated	string	skip_fusion_layers	Layers to skip BN fusion.
OverrideLayerType	-	-	-	Quantization configuration overriding by layer type.
	required	string	layer_type	Quantizable layer type.
	required	CalibrationConfig	calibration_config	Quantization configuration to apply.
OverrideLayer	-	-	-	Quantization configuration overriding by layer.
	required	string	layer_name	Layer to override.
	required	CalibrationConfig	calibration_config	Quantization configuration to override.
CalibrationConfig	-	-	-	Calibration-based quantization configuration.
	-	ARQuantize	arq_quantize	Weight quantization algorithm. arq_quantize: ARQ algorithm configuration.
	-	FMRQuantize	ifmr_quantize	Activation quantization algorithm. ifmr_quantize: IFMR quantization algorithm configuration. Currently, only the IFMR algorithm is supported.
ARQuantize	-	-	-	ARQ algorithm configuration. For details about the algorithm, see ARQ Algorithm.
ARQuantize	optional	bool	channel_wise	Whether to use different quantization factors for each channel.
FMRQuantize	-	-	-	FMR quantization algorithm. For details about the algorithm, see ifmr: IFMR algorithm for activation quantization.
	optional	float	search_range_start	Quantization factor search start.
	optional	float	search_range_end	Quantization factor search end.
	optional	float	search_step	Quantization factor search step.
	optional	float	max_percentile	Upper bound for searching for the largest.
	optional	float	min_percentile	Lower bound for searching for the smallest.
	optional	bool	asymmetric	Whether to perform symmetric quantization. It is used to select the layer-wise quantization algorithm. true: asymmetric quantization false: symmetric quantization If this parameter is set for override_layer_configs, override_layer_types, and common_config, or if the activation_offset parameter is set, the priority is as follows: override_layer_configs>override_layer_types>common_config>activation_offset

The following is an example of the simplified configuration file (quant.cfg) for distillation:

# global quantize parameter
activation_offset : true
skip_layers : "Opname"
skip_layer_types:"Optype"
do_fusion: true
skip_fusion_layers : "Opname"
common_config : {
    arq_quantize : {
        channel_wise : true
    }
    ifmr_quantize : {
        search_range_start : 0.7
        search_range_end : 1.3
        search_step : 0.01
        max_percentile : 0.999999
        min_percentile : 0.999999
        asymmetric : true
    }
}
 
override_layer_types : {
    layer_type : "Optype"
    calibration_config : {
        arq_quantize : {
            channel_wise : false
        }
        ifmr_quantize : {
            search_range_start : 0.8
            search_range_end : 1.2
            search_step : 0.02
            max_percentile : 0.999999
            min_percentile : 0.999999
            asymmetric : true
        }
    }
}
 
override_layer_configs : {
    layer_name : "Opname"
    calibration_config : {
        arq_quantize : {
            channel_wise : true
        }
        ifmr_quantize : {
            search_range_start : 0.8
            search_range_end : 1.2
            search_step : 0.02
            max_percentile : 0.999999
            min_percentile : 0.999999
            asymmetric : true
        }
    }
}

Parent topic: See Also