Public Attributes | List of all members
dnnl_lrn_desc_t Struct Reference

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

#include <dnnl_types.h>

Collaboration diagram for dnnl_lrn_desc_t:
Collaboration graph

Public Attributes

dnnl_primitive_kind_t primitive_kind
dnnl_prop_kind_t prop_kind
dnnl_alg_kind_t alg_kind
dnnl_memory_desc_t data_desc
 Source and destination memory descriptor. More...
dnnl_memory_desc_t diff_data_desc
 Source and destination gradient memory descriptor. More...
dnnl_dim_t local_size
float lrn_alpha
 LRN alpha parameter. More...
float lrn_beta
 LRN beta parameter. More...
float lrn_k
 LRN k parameter. More...

Detailed Description

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

Member Data Documentation

dnnl_alg_kind_t dnnl_lrn_desc_t::alg_kind

LRN algorithm. Possible values: dnnl_lrn_within_channel and dnnl_lrn_across_channels.

dnnl_memory_desc_t dnnl_lrn_desc_t::data_desc

Source and destination memory descriptor.

dnnl_memory_desc_t dnnl_lrn_desc_t::diff_data_desc

Source and destination gradient memory descriptor.

dnnl_dim_t dnnl_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 dnnl_lrn_desc_t::lrn_alpha

LRN alpha parameter.

float dnnl_lrn_desc_t::lrn_beta

LRN beta parameter.

float dnnl_lrn_desc_t::lrn_k

LRN k parameter.

dnnl_primitive_kind_t dnnl_lrn_desc_t::primitive_kind

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

dnnl_prop_kind_t dnnl_lrn_desc_t::prop_kind

The kind of propagation. Possible values: dnnl_forward_training, dnnl_forward_inference, dnnl_backward, and dnnl_backward_data.

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