nrf_edgeai_output_dequantize_neuton_q8_f32()

void nrf_edgeai_output_dequantize_neuton_q8_f32

(

nrf_edgeai_model_t *

p_model

)

Dequantize Neuton model outputs to 32-bit floating point.

These functions convert the output values from quantized format (8-bit or 16-bit) to 32-bit floating point format, using the scaling parameters defined in the model context.

Parameters

[in,out]

p_model

Pointer to model context nrf_edgeai_model_t

Note

• Use nrf_edgeai_output_dequantize_neuton_q8_f32() for 8-bit quantized models.
• Use nrf_edgeai_output_dequantize_neuton_q16_f32() for 16-bit quantized models.