mxnet
Functions
Collaboration diagram for LRN:

Functions

mkldnn_status_t MKLDNN_API mkldnn_lrn_forward_desc_init (mkldnn_lrn_desc_t *lrn_desc, mkldnn_prop_kind_t prop_kind, mkldnn_alg_kind_t alg_kind, const mkldnn_memory_desc_t *data_desc, mkldnn_dim_t local_size, float alpha, float beta, float k)
 
mkldnn_status_t MKLDNN_API mkldnn_lrn_backward_desc_init (mkldnn_lrn_desc_t *lrn_desc, mkldnn_alg_kind_t alg_kind, const mkldnn_memory_desc_t *diff_data_desc, const mkldnn_memory_desc_t *data_desc, mkldnn_dim_t local_size, float alpha, float beta, float k)
 

Detailed Description

A primitive to perform local response normalization (LRN) across or within channels.

See also
mkldnn_primitive_desc_query and mkldnn_primitive_desc_query_pd
dev_guide_lrn in developer guide
cpp_api_lrn in cpp_api

Function Documentation

mkldnn_status_t MKLDNN_API mkldnn_lrn_backward_desc_init ( mkldnn_lrn_desc_t lrn_desc,
mkldnn_alg_kind_t  alg_kind,
const mkldnn_memory_desc_t diff_data_desc,
const mkldnn_memory_desc_t data_desc,
mkldnn_dim_t  local_size,
float  alpha,
float  beta,
float  k 
)

Initializes an lrn_desc for backward propagation using alg_kind, memory descriptors data_desc and diff_data_desc, and regularization parameters local_size, alpha, beta, and k.

Inputs:

Outputs:

mkldnn_status_t MKLDNN_API mkldnn_lrn_forward_desc_init ( mkldnn_lrn_desc_t lrn_desc,
mkldnn_prop_kind_t  prop_kind,
mkldnn_alg_kind_t  alg_kind,
const mkldnn_memory_desc_t data_desc,
mkldnn_dim_t  local_size,
float  alpha,
float  beta,
float  k 
)

Initializes an lrn_desc for forward propagation using prop_kind (possible values are mkldnn_forward_training and mkldnn_forward_inference), alg_kind, memory descriptor data_desc, and regularization parameters local_size, alpha, beta, and k.

Inputs:

Outputs: