Record Files

A record file is a serialized data structure file based on Protobuf. It records the scale and offset factors for quantization. You can generate a compressed model file by using the record file, quantization configuration file, and original network model file.

Record Prototype Definition

The Protobuf prototype of the record file is defined as follows:

message SingleLayerRecord {
    optional float scale_d = 1;
    optional int32 offset_d = 2;
    repeated float scale_w = 3;
    repeated int32 offset_w = 4;
    repeated uint32 shift_bit = 5;
    optional uint32 channels = 6;
    optional uint32 height = 7;
    optional uint32 width = 8;
    optional bool skip_fusion = 9 [default = false];
}
message ScaleOffsetRecord {
    message MapFiledEntry {
        optional string key = 1;
        optional SingleLayerRecord value = 2;
    }
    repeated MapFiledEntry record = 1;
}

The parameters are described as follows.

Message	Required	Type	Parameter	Description
ScaleOffsetRecord	-	-	-	Map structure. The discrete map structure is used to ensure compatibility.
ScaleOffsetRecord	repeated	MapFiledEntry	record	Quantization factor record per layer, consisting of two members: key: layer name. value: quantization factors defined by SingleLayerRecord.
SingleLayerRecord	-	-	-	Quantization factors.
	optional	float	scale_d	Scale factor for activation quantization. Only unified activation quantization is supported.
	optional	int32	offset_d	Offset factor for activation quantization; only unified activation quantization is supported.
	repeated	float	scale_w	Scale factor for weight quantization. Two quantization modes are supported: scalar (uniformly quantizing the weight of the current layer) and vector (quantizing the weight of the current layer channel-wise). Channel-wise quantization applies only to the Conv2D, DepthwiseConv2dNative, and Conv2DBackpropInput layers.
	repeated	int32	offset_w	Offset factor for weight quantization. Similar to scale_w, it also supports scalar and vector modes and the dimension configuration must be the same as that of scale_w. Currently, weight quantization with offset is not supported, and offset_w must be 0.
	repeated	uint32	shift_bit	Shift factor. Reserved for the convert_model API.
	optional	uint32	channels	Size of the input channel dimension. AMCT does not support network-wide infer_shape. Therefore, you must configure the input shape information of the current layer.
	optional	uint32	height	Size of the input height dimension. AMCT does not support network-wide infer_shape. Therefore, you must configure the input shape information of the current layer.
	optional	uint32	width	Size of the input width dimension. AMCT does not support network-wide infer_shape. Therefore, you must configure the input shape information of the current layer.
	optional	bool	skip_fusion	Whether to skip Conv+BN+Scale+Bias, Deconv+BN+Scale+Bias, BN+Scale+Conv, and FC+BN+Scale+Bias fusion at the current layer. Defaults to false, which indicates performing the preceding fusion types.

Beware that the Protobuf protocol does not report an error if you have updated optional fields more than once. As such, the most recent settings are used.

Record Files

The format of a generated record file is record.txt. Configure the following parameters for general quantization layers: scale_d, offset_d, scale_w, offset_w, channels, height, width, and shift_bit. The scale_w and offset_w parameters are unavailable for AVE Pooling since the layer has no weight. Here is an example of a quantization factor record file:

record {
    key: "conv1"
    value: {
        scale_d: 0.01424
        offset_d: -128
        scale_w: 0.43213
        scale_w: 0.78163
        scale_w: 1.03213
        offset_w: 0
        offset_w: 0
        offset_w: 0
        shift_bit: 1
        shift_bit: 1
        shift_bit: 1
        channels:3
        height: 144
        width: 144
        skip_fusion: true
    }
}
record {
    key: "pool1"
    value: {
        scale_d: 0.532532
        offset_d: 13
        channels:256
        height: 32
        width: 32
    }
}
record {
    key: "fc1"
    value: {
        scale_d: 0.37532
        offset_d: -67
        scale_w: 0.876221
        offset_w: 0
        shift_bit: 1
        channels:1024
        height: 1
        width: 1
    }
}

Parent topic: See Also