utils

Machine-readable model

• quantize_multiplierfunctionConvert a floating point multiplier into a fixed-point multiplier and shift.
• compute_fused_activation_rangefunctionCompute the activation min and max values based on the fused activation function.
• compute_padding_with_offsetfunctionComputes a single padding value (top/left) for one dimension with offset.
• compute_paddingfunctionComputes a single padding value (top/left) for one dimension.
• reduce_multiplier_q31_to_q15functionReduce a multiplier value for int16 quantization.

function

quantize_multiplier

Python

Convert a floating point multiplier into a fixed-point multiplier and shift.

helia_aot/air/utils.py:8

quantize_multiplier(real_multiplier: float) -> tuple[int, int]

Convert a floating point multiplier into a fixed-point multiplier and shift.

Given a real multiplier, this function computes a pair (quantized_multiplier, shift) such that the fixed-point multiplication approximates the real multiplier:

real_multiplier ~ quantized_multiplier / (2^(31 - shift))

This is typically used in quantized inference to convert floating-point scaling factors to fixed-point representation.

The CMSIS-NN arm_nn_divide_by_power_of_two function only supports exponent values in [0, 31], so the resulting shift is clamped to [-31, 30]. When the real multiplier is so small that the shift would fall below -31 the contribution is negligible and the multiplier is flushed to zero.

Parameters

Parameters of quantize_multiplier

Name	Type	Default	Description
real_multiplier	float	Required	The floating-point multiplier.

Returns

Returns of quantize_multiplier

Value	Type	Description
tuple	tuple[int, int]	(quantized_multiplier, shift)

function

compute_fused_activation_range

Python

Compute the activation min and max values based on the fused activation function.

helia_aot/air/utils.py:68

compute_fused_activation_range(
    activation_function: AirActivationType,
    output_zero_point: int = 0,
    output_scale: float = 1.0,
    qmin: int = -128,
    qmax: int = 127,
) -> tuple[int, int]

Compute the activation min and max values based on the fused activation function.

Parameters

Parameters of compute_fused_activation_range

Name	Type	Default	Description
activation_function	litert.ActivationFunctionType	Required	The activation function type.
output_zero_point	int	0	The zero point for the output tensor. Defaults to 0.
output_scale	float	1.0	The scale for the output tensor. Defaults to 1.0.
qmin	int	-128	Minimum quantized value. Defaults to -128.
qmax	int	127	Maximum quantized value. Defaults to 127.

Returns

Returns of compute_fused_activation_range

Type	Description
tuple[int, int]	tuple[int, int]: The activation min and max values.

function

compute_padding_with_offset

Python

Computes a single padding value (top/left) for one dimension with offset.

helia_aot/air/utils.py:111

compute_padding_with_offset(
    in_size: int,
    filter_size: int,
    stride: int,
    dilation_rate: int = 1,
    padding_type: int = AirPaddingType.SAME,
) -> tuple[int, int]

Computes a single padding value (top/left) for one dimension with offset.

Parameters

Parameters of compute_padding_with_offset

Name	Type	Default	Description
in_size	int	Required	Input dimension (height or width).
filter_size	int	Required	Kernel dimension (height or width).
stride	int	Required	Stride for that dimension.
dilation_rate	int	1	Dilation rate for that dimension (default is 1).
padding_type	int	AirPaddingType.SAME	0 for SAME padding, 1 for VALID padding (default is SAME).

Returns

Returns of compute_padding_with_offset

Value	Type	Description
int	tuple[int, int]	The computed top or left padding value.

function

compute_padding

Python

Computes a single padding value (top/left) for one dimension.

helia_aot/air/utils.py:140

compute_padding(
    in_size: int,
    filter_size: int,
    stride: int,
    dilation_rate: int = 1,
    padding_type: int = AirPaddingType.SAME,
) -> int

Computes a single padding value (top/left) for one dimension.

Parameters

Parameters of compute_padding

Name	Type	Default	Description
in_size	int	Required	Input dimension (height or width).
filter_size	int	Required	Kernel dimension (height or width).
stride	int	Required	Stride for that dimension.
dilation_rate	int	1	Dilation rate for that dimension (default is 1).
padding_type	int	AirPaddingType.SAME	0 for SAME padding, 1 for VALID padding (default is SAME).

Returns

Returns of compute_padding

Value	Type	Description
int	int	The computed top or left padding value.

function

reduce_multiplier_q31_to_q15

Python

Reduce a multiplier value for int16 quantization.

helia_aot/air/utils.py:185

reduce_multiplier_q31_to_q15(multiplier: int) -> int

Reduce a multiplier value for int16 quantization.

Certain CMSIS functions for int16 quantized models require the multiplier to be reduced from Q31 format to Q15 format. This function performs that reduction.

Parameters

Parameters of reduce_multiplier_q31_to_q15

Name	Type	Default	Description
multiplier	int	Required	The original multiplier value.

Returns

Returns of reduce_multiplier_q31_to_q15

Value	Type	Description
int	int	The reduced multiplier value.