rml_op_pad_params

Parameters for the RML_OP_PAD operation.

Describes a data reorganization operator that inflates the input tensor with zeroes (or some other value) on the edges.

API

Graph Manipulation

Items

Name	Type	Description
input	rml_op	Operation that outputs tensor containing input data.
mode	rml_pad_mode	The padding mode to use.
value	float	The value with which to pad.
num_dims	size_t	The number of dimensions. Determines the size of the start_padding and end_padding arrays.
start_padding[RML_TENSOR_MAX_RANK]	uint32_t	An array of UINT containing the padding (number of pixels added) to the start of the corresponding axis. Padding defaults to 0 along the start and end of each axis.
end_padding[RML_TENSOR_MAX_RANK]	uint32_t	An array containing the padding (number of pixels added) to the end of the corresponding axis. Padding defaults to 0 along the start and end of each axis.