Contents

dequantized(to:scale:zeroPoint:)

Converts a tensor you quantize to a 32-bit floating-point tensor.

Declaration

func dequantized(to type: MLCDataType, scale: MLCTensor, zeroPoint bias: MLCTensor) -> MLCTensor?

Parameters

  • type:

    The tensor data type.

  • scale:

    The scale the system uses when quantizing the data.

  • bias:

    The offset value the system uses when quantizing the data.

Return Value

A tensor the system dequantizes.

Discussion

See Also

Converting Tensors