27/** Perform a NCHW -> NHWC or NHWC -> NCHW conversion for Fully Connected 2D weights.
28 *
29 * For NCHW -> NHWC, FACTOR_1 will be equal to the product of the first two dimensions of FullyConnectedLayer's input and FACTOR_2 will represent the number of channels of that tensor.
30 * For NHWC -> NCHW, FACTOR_1 and FACTOR_2 will hold the same values, but swapped.
31 *
32 * @attention Data type can be passed using the -DDATA_TYPE compile flag, e.g. -DDATA_TYPE=float
33 * @attention Original input tensor width*height and depth should be given as a preprocessor argument using -DFACTOR_1=size and -DFACTOR_2=size for NCHW and vice versa for NHWC. e.g. -DFACTOR_1=256 and -DFACTOR_2=128
34 *
35 * @param[in] src_ptr Pointer to the source image. Supported data types: All.
36 * @param[in] src_stride_x Stride of the source image in X dimension (in bytes)
37 * @param[in] src_step_x src_stride_x * number of elements along X processed per workitem(in bytes)
38 * @param[in] src_stride_y Stride of the source image in Y dimension (in bytes)
39 * @param[in] src_step_y src_stride_y * number of elements along Y processed per workitem(in bytes)
40 * @param[in] src_offset_first_element_in_bytes The offset of the first element in the source image
41 * @param[out] dst_ptr Pointer to the destination image. Supported data types: same as @p src_ptr
42 * @param[in] dst_stride_x Stride of the destination image in X dimension (in bytes)
43 * @param[in] dst_step_x dst_stride_x * number of elements along X processed per workitem(in bytes)
44 * @param[in] dst_stride_y Stride of the destination image in Y dimension (in bytes)
45 * @param[in] dst_step_y dst_stride_y * number of elements along Y processed per workitem(in bytes)
46 * @param[in] dst_offset_first_element_in_bytes The offset of the first element in the destination image