Click or drag to resize

GraphQuantizedMatMulWithBiasAndRequantize Method

https://www.emgu.com/wiki/index.php/Emgu_TF
QuantizedMatMulWithBiasAndRequantize

Namespace:  Emgu.TF
Assembly:  Emgu.TF.Netstandard (in Emgu.TF.Netstandard.dll) Version: 2.6.0.1294
Syntax
public Operation QuantizedMatMulWithBiasAndRequantize(
	Output a,
	Output b,
	Output bias,
	Output min_a,
	Output max_a,
	Output min_b,
	Output max_b,
	Output min_freezed_output,
	Output max_freezed_output,
	Nullable<DataType> Toutput = null,
	bool transpose_a = false,
	bool transpose_b = false,
	string input_quant_mode = null,
	string opName = "QuantizedMatMulWithBiasAndRequantize"
)

Parameters

a
Type: Emgu.TFOutput
Input to the operation.
b
Type: Emgu.TFOutput
Input to the operation.
bias
Type: Emgu.TFOutput
Input to the operation.
min_a
Type: Emgu.TFOutput
Input to the operation.
max_a
Type: Emgu.TFOutput
Input to the operation.
min_b
Type: Emgu.TFOutput
Input to the operation.
max_b
Type: Emgu.TFOutput
Input to the operation.
min_freezed_output
Type: Emgu.TFOutput
Input to the operation.
max_freezed_output
Type: Emgu.TFOutput
Input to the operation.
Toutput (Optional)
Type: SystemNullableDataType
Toutput
transpose_a (Optional)
Type: SystemBoolean
transpose a
transpose_b (Optional)
Type: SystemBoolean
transpose b
input_quant_mode (Optional)
Type: SystemString
input quant mode
opName (Optional)
Type: SystemString
The name of the operation

Return Value

Type: Operation
The operation, where: [0] out(type: DtInvalid). [1] min_out(type: DtFloat). [2] max_out(type: DtFloat).
See Also