Simplified QAT Configuration File

Table 1 describes the fields in the retrain_config_caffe.proto file. Find the file in /amct_caffe/proto/retrain_config_caffe.proto under the AMCT installation directory.

**Table 1** retrain_config_caffe.proto
Parameter	Required/Optional	Type	Field	Description
AMCTRetrainConfig	-	-	-	Simplified QAT configuration of AMCT.
	Repeated	String	skip_layers	Layers to skip quantization. It is globally effective, which efficiently realizes the same functionality for extended features. If this field is set, you can skip the settings of the extended quant_skip_layers and xxx_skip_layers. If both skip_layers and quant_skip_layers are set, their union is used.
	Repeated	String	skip_layer_types	Types of layers to skip quantization. (Not supported currently.) It is globally effective, which efficiently realizes the same functionality for extended features. If this field is set, you can skip the settings of the extended quant_skip_types and xxx_skip_types. If both skip_layer_types and quant_skip_types are set, their union is used.
	Repeated	RetrainOverrideLayer	override_layer_configs	Layers to override. 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 initial upper and lower bounds from [–0.6, +0.6] to [–0.3, +0.3]. Parameter priority: Quantization scenario: override_layer_configs > override_layer_types > retrain_data_quant_config/retrain_weight_quant_config Sparsity scenario: override_layer_configs > override_layer_types > prune_config
	Repeated	RetrainOverrideLayerType	override_layer_types	Types of layers to override. 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 initial upper and lower bounds from [–0.6, +0.6] to [–0.3, +0.3]. Parameter priority: Quantization scenario: override_layer_configs > override_layer_types > retrain_data_quant_config/retrain_weight_quant_config Sparsity scenario: override_layer_configs > override_layer_types > prune_config
	Optional	UInt32	batch_num	Batch number for quantization.
	Required	RetrainDataQuantConfig	retrain_data_quant_config	Activation quantization configuration parameter for QAT. It is a global quantization configuration parameter. Parameter priority: override_layer_configs > override_layer_types > retrain_data_quant_config/retrain_weight_quant_config
	Required	RetrainWeightQuantConfig	retrain_weight_quant_config	Weight quantization configuration parameter for QAT. It is a global quantization configuration parameter. Parameter priority: override_layer_configs > override_layer_types > retrain_data_quant_config/retrain_weight_quant_config
	Repeated	String	quant_skip_layers	Layers to skip quantization. Applicable to quantization. If both skip_layers and quant_skip_layers are set, their union is used.
	Repeated	String	quant_skip_types	Types of layers to skip quantization. (Not supported currently.) Applicable to quantization. If both skip_layer_types and quant_skip_types are set, their union is used.
RetrainDataQuantConfig	-	-	-	Activation quantization configuration for QAT.
RetrainDataQuantConfig	-	ULQuantize	ulq_quantize	Activation quantization algorithm. Currently, only ULQ is supported.
ULQuantize	-	-	-	ULQ quantization algorithm configuration. For details about the algorithm, see ULQ Algorithm.
	Optional	ClipMaxMin	clip_max_min	Initial upper and lower bounds. IFMR is used for initialization by default.
	Optional	Boolean	fixed_min	Whether to fix the lower bound at 0. Set to true for ReLU or false for other algorithms.
ClipMaxMin	-	-	-	Initial upper and lower bounds.
	Required	Float	clip_max	Initial upper bound.
	Required	Float	clip_min	Initial lower bound.
RetrainWeightQuantConfig	-	-	-	Weight quantization configuration for QAT.
RetrainWeightQuantConfig	-	ARQRetrain	arq_retrain	Weight quantization algorithm. Currently, only ARQ is supported.
ARQRetrain	-	-	-	ARQ algorithm configuration. For details about the algorithm, see ARQ Algorithm.
ARQRetrain	Required	Boolean	channel_wise	Channel-wise ARQ enable.
RetrainOverrideLayer	-	-	-	Layer overriding configuration.
	Required	String	layer_name	Layer name.
	Required	RetrainDataQuantConfig	retrain_data_quant_config	Activation quantization configuration to override.
	Required	RetrainWeightQuantConfig	retrain_weight_quant_config	Weight quantization configuration to override.
RetrainOverrideLayerType	-	-	-	Type of the layer to override.
	Required	String	layer_type	Layer type.
	Required	RetrainDataQuantConfig	retrain_data_quant_config	Activation quantization configuration to override.
	Required	RetrainWeightQuantConfig	retrain_weight_quant_config	Weight quantization configuration to override.

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

# global quantize parameter
 retrain_data_quant_config: {
     ulq_quantize: {
         clip_max_min: {
             clip_max: 6.0
             clip_min: -6.0
         }
     }
 }

 retrain_weight_quant_config: {
     arq_retrain: {
         channel_wise: true
     }
 }

 skip_layers: "conv_1"

 override_layer_types : {
     layer_type: "InnerProduct"
     retrain_weight_quant_config: {
         arq_retrain: {
            channel_wise: false
         }
     }
 }

 override_layer_configs : {   
     layer_name: "fc_5"   
     retrain_weight_quant_config: {        
         arq_retrain: {   
            channel_wise: false
         }    
      }
}

Parent topic: Reference