Function arm_fully_connected_fp16

Function Documentation

arm_cmsis_nn_status arm_fully_connected_fp16(const cmsis_nn_context *ctx, const cmsis_nn_fc_params *fc_params, const cmsis_nn_dims *input_dims, const float16_t *input, const cmsis_nn_dims *filter_dims, const float16_t *kernel, const cmsis_nn_dims *bias_dims, const float16_t *bias, const cmsis_nn_dims *output_dims, float16_t *output, const float16_t out_activation_min, const float16_t out_activation_max)

Fully-connected layer function for float16.

  1. Supported framework: TensorFlow Lite Micro

Parameters:

  • ctx – [in] Function context (e.g. temporary buffer). Check the function definition file to see if an additional buffer is required. Optional function arm_fully_connected_fp16_get_buffer_size() provides the buffer size if an additional buffer is required. The caller is expected to clear the buffer, if applicable, for security reasons.

  • fc_params – [in] Pointer to the fully-connected layer parameters

  • input_dims – [in] Pointer to the input tensor dimensions

  • input – [in] Pointer to the input tensor

  • filter_dims – [in] Pointer to the kernel tensor dimensions

  • kernel – [in] Pointer to the kernel tensor

  • bias_dims – [in] Pointer to the bias tensor dimensions

  • bias – [in] Pointer to the bias tensor

  • output_dims – [in] Pointer to the output tensor dimensions

  • output – [out] Pointer to the output tensor

  • out_activation_min – [in] Minimum value to clamp the output to

  • out_activation_max – [in] Maximum value to clamp the output to

Returns:

The function returns ARM_CMSIS_NN_SUCCESS