rml_op_reduce_params

Parameters for reduce operation:

• RML_OP_REDUCE_AVG

• RML_OP_REDUCE_L1

• RML_OP_REDUCE_L2

• RML_OP_REDUCE_MUL

• RML_OP_REDUCE_LOGN_ADD

• RML_OP_REDUCE_LOGN_ADD_EXP

• RML_OP_REDUCE_MAX

• RML_OP_REDUCE_MIN

• RML_OP_REDUCE_ADD_SQUARE

API

Graph Manipulation

Items

Name	Type	Description
input	rml_op	Operation that outputs tensor containing the input data.
keep_dims	rml_bool	If keepdims is true, the reduced dimensions are retained with length 1.
num_axes	size_t	Number of axes to reduce.
axes[RML_TENSOR_MAX_RANK]	const int32_t*	List of integers indicating the dimensions to reduce. Negative value means counting dimensions from the back. Accepted range is [-R, R-1] where R = rank(data).