quantized(to:scale:bias:axis:)
Converts a 32-bit floating-point tensor with the scale and bias you specify.
Declaration
func quantized(to type: MLCDataType, scale: MLCTensor, bias: MLCTensor, axis: Int) -> MLCTensor?Parameters
- type:
The tensor data type.
- scale:
The scale to apply for quantizing.
- bias:
The offset value that maps to float zero.
- axis:
The dimension on which to apply per-channel quantization.
Return Value
A tensor the system quantizes.