Function arm_hard_swish_precise_s8

Function Documentation

arm_cmsis_nn_status arm_hard_swish_precise_s8(const int8_t *input, const int32_t input_offset, const int32_t output_offset, const int32_t output_multiplier, const int32_t output_shift, const int32_t relu_q3, const int32_t relu_q6, const int32_t prescale, int8_t *output, const int32_t output_size)

S8 Hard-Swish activation function (precise version)

This version uses int32_t for intermediate computations to provide better accuracy. relu_q3, relu_q6 = round(3 / input_scale), round(6 / input_scale) prescale = min value to multiply input by to avoid overflow in intermediate computations M = ((input_scale**2) / (6.0 * output_scale)) * (1 << prescale) output_multiplier, output_shift = quantize_multiplier(M)

Parameters:

  • input – [in] Pointer to the input buffer

  • input_offset – [in] Input tensor zero offset

  • output_offset – [in] Output tensor zero offset

  • output_multiplier – [in] Output multiplier

  • output_shift – [in] Output shift

  • relu_q3 – [in] ReLU6 Q3 value

  • relu_q6 – [in] ReLU6 Q6 value

  • prescale – [in] Prescale to apply to input

  • output – [out] Pointer to the output buffer

  • output_size – [in] Number of elements in the tensor

Returns:

The function returns ARM_MATH_SUCCESS