Click or drag to resize

GraphXlaDequantize Method

https://www.emgu.com/wiki/index.php/Emgu_TF
Takes the packed uint32 input and unpacks the input to uint8 to do

Namespace:  Emgu.TF
Assembly:  Emgu.TF.Netstandard (in Emgu.TF.Netstandard.dll) Version: 2.6.0.1294
Syntax
public Operation XlaDequantize(
	Output input,
	float min_range,
	float max_range,
	string mode,
	bool transpose_output,
	string opName = "XlaDequantize"
)

Parameters

input
Type: Emgu.TFOutput
Input to the operation: Input tensors whose types is uint32, shape is [d0, ..., dn].
min_range
Type: SystemSingle
The minimum scalar value possibly produced for the input.
max_range
Type: SystemSingle
The maximum scalar value possibly produced for the input.
mode
Type: SystemString
String to determine the dequantize mode in {"MIN_COMBINED", "MIN_FIRST", "SCALED"}.
transpose_output
Type: SystemBoolean
Boolean to determine if output is transposed. transpose_output is faster when input is large and rank of input is higher than 1.
opName (Optional)
Type: SystemString
The name of the operation

Return Value

Type: Operation
The operation, where: [0] output(type: DtBfloat16): Output tensors whose types is bloat16. If transpose_output is true, output shape is [dn * 4, dn-1, ..., d1, d0]. If transpose_output is false, output shape is [d0,..., dn * 4].
See Also