Function arm_depthwise_conv_3x3_s8¶
Defined in File arm_nnfunctions.h
Function Documentation¶
-
arm_cmsis_nn_status arm_depthwise_conv_3x3_s8(const cmsis_nn_context *ctx, const cmsis_nn_dw_conv_params *dw_conv_params, const cmsis_nn_per_channel_quant_params *quant_params, const cmsis_nn_dims *input_dims, const int8_t *input_data, const cmsis_nn_dims *filter_dims, const int8_t *filter_data, const cmsis_nn_dims *bias_dims, const int32_t *bias_data, const cmsis_nn_dims *output_dims, int8_t *output_data)¶
Optimized s8 depthwise convolution function for 3x3 kernel size with some constraints on the input arguments(documented below). Refer arm_depthwise_conv_s8() for function argument details.
Supported framework : TensorFlow Lite Micro
The following constrains on the arguments apply
Number of input channel equals number of output channels
Filter height and width equals 3
Padding along x is either 0 or 1.
- Returns:
The function returns one of the following
ARM_CMSIS_NN_ARG_ERROR- Unsupported dimension of tensorsUnsupported pad size along the x axis
ARM_CMSIS_NN_SUCCESS- Successful operation