# Stride value in convolution

Hi，there
I am just wanna port OpenVX to our board ，and found the convolution layer only has the argument：

typedef struct _vx_nn_convolution_params_t
{
vx_size padding_x;                 /*!< \brief Number of elements added at each side in the x dimension of the input. */
vx_size padding_y;                 /*!< \brief Number of elements added at each side in the y dimension of the input. */
vx_enum overflow_policy;         /*!< \brief A <tt> VX_TYPE_ENUM</tt> of the <tt> vx_convert_policy_e</tt> enumeration. */
vx_enum rounding_policy;         /*!< \brief A <tt> VX_TYPE_ENUM</tt> of the <tt> vx_round_policy_e</tt> enumeration. */
vx_enum down_scale_size_rounding; /*!< \brief Rounding method for calculating output dimensions. See <tt>\ref vx_nn_rounding_type_e</tt> */
vx_size dilation_x;            /*!< \brief "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;            /*!< \brief "inflate" the kernel by inserting zeros between the kernel elements in the y direction. The value is the number of zeros to insert.*/
} vx_nn_convolution_params_t;


and in my models the cnn has the stride value ， so how can I input the stride value ？

it confuses me too. default to 1?

well, I read the specification more carefully
this time. Stride is caculated inversely according to input size and output size. Stride is skip value