_vx_nn_convolution_params_t Struct Reference

_vx_nn_convolution_params_t Struct Reference#

MIVisionX: _vx_nn_convolution_params_t Struct Reference
_vx_nn_convolution_params_t Struct Reference

Input parameters for a convolution operation. More...

#include <docs-6.3.0/amd_openvx/openvx/include/VX/vx_khr_nn.h>

Data Fields

vx_size padding_x
 Number of elements added at each side in the x dimension of the input.
 
vx_size padding_y
 Number of elements added at each side in the y dimension of the input.
 
vx_enum overflow_policy
 A VX_TYPE_ENUM of the vx_convert_policy_e enumeration.
 
vx_enum rounding_policy
 A VX_TYPE_ENUM of the vx_round_policy_e enumeration.
 
vx_enum down_scale_size_rounding
 Rounding method for calculating output dimensions. See vx_nn_rounding_type_e
 
vx_size dilation_x
 “inflate” the kernel by inserting zeros between the kernel elements in the x direction. The value is the number of zeros to insert.
 
vx_size dilation_y
 “inflate” the kernel by inserting zeros between the kernel elements in the y direction. The value is the number of zeros to insert.
 

Detailed Description

Input parameters for a convolution operation.


The documentation for this struct was generated from the following file: