Public Attributes | List of all members
mkldnn_lrn_desc_t Struct Reference

#include <mkldnn_types.h>

Collaboration diagram for mkldnn_lrn_desc_t:
Collaboration graph

Public Attributes

mkldnn_primitive_kind_t primitive_kind
mkldnn_prop_kind_t prop_kind
mkldnn_alg_kind_t alg_kind
mkldnn_memory_desc_t data_desc
mkldnn_memory_desc_t diff_data_desc
int local_size
float lrn_alpha
float lrn_beta
float lrn_k

Detailed Description

A descriptor of a Local Response Normalization (LRN) operation.

Member Data Documentation

mkldnn_alg_kind_t mkldnn_lrn_desc_t::alg_kind

LRN algorithm. Possible values: mkldnn_lrn_within_channel and mkldnn_lrn_across_channels.

mkldnn_memory_desc_t mkldnn_lrn_desc_t::data_desc

Source and destination memory descriptor.

mkldnn_memory_desc_t mkldnn_lrn_desc_t::diff_data_desc

Source and destination gradient memory descriptor.

int mkldnn_lrn_desc_t::local_size

The number of channels to sum over (for cross-channel LRN) or the side length of the square region to sum over (for within-channel LRN).

float mkldnn_lrn_desc_t::lrn_alpha

LRN alpha parameter.

float mkldnn_lrn_desc_t::lrn_beta

LRN beta parameter.

float mkldnn_lrn_desc_t::lrn_k

LRN k parameter.

mkldnn_primitive_kind_t mkldnn_lrn_desc_t::primitive_kind

The kind of primitive. Used for self-identifying the primitive descriptor. Must be mkldnn_lrn.

mkldnn_prop_kind_t mkldnn_lrn_desc_t::prop_kind

The kind of propagation. Possible values: mkldnn_forward_training, mkldnn_forward_inference, mkldnn_backward, and mkldnn_backward_data.

The documentation for this struct was generated from the following file: