Function arm_svdf_state_s16_s8¶

Function Documentation¶

arm_cmsis_nn_status arm_svdf_state_s16_s8(const cmsis_nn_context *input_ctx, const cmsis_nn_context *output_ctx, const cmsis_nn_svdf_params *svdf_params, const cmsis_nn_per_tensor_quant_params *input_quant_params, const cmsis_nn_per_tensor_quant_params *output_quant_params, const cmsis_nn_dims *input_dims, const int8_t *input_data, const cmsis_nn_dims *state_dims, int16_t *state_data, const cmsis_nn_dims *weights_feature_dims, const int8_t *weights_feature_data, const cmsis_nn_dims *weights_time_dims, const int16_t *weights_time_data, const cmsis_nn_dims *bias_dims, const int32_t *bias_data, const cmsis_nn_dims *output_dims, int8_t *output_data)¶

s8 SVDF function with 16 bit state tensor and 16 bit time weights

Parameters:

input_ctx – [in] Temporary scratch buffer The caller is expected to clear the buffer, if applicable, for security reasons.
output_ctx – [in] Temporary output scratch buffer The caller is expected to clear the buffer, if applicable, for security reasons.
svdf_params – [in] SVDF Parameters Range of svdf_params->input_offset : [-128, 127] Range of svdf_params->output_offset : [-128, 127]
input_quant_params – [in] Input quantization parameters
output_quant_params – [in] Output quantization parameters
input_dims – [in] Input tensor dimensions
input_data – [in] Pointer to input tensor
state_dims – [in] State tensor dimensions
state_data – [in] Pointer to state tensor
weights_feature_dims – [in] Weights (feature) tensor dimensions
weights_feature_data – [in] Pointer to the weights (feature) tensor
weights_time_dims – [in] Weights (time) tensor dimensions
weights_time_data – [in] Pointer to the weights (time) tensor
bias_dims – [in] Bias tensor dimensions
bias_data – [in] Pointer to bias tensor
output_dims – [in] Output tensor dimensions
output_data – [out] Pointer to the output tensor

Returns:

The function returns ARM_CMSIS_NN_SUCCESS