Deep Neural Network Library (DNNL)  1.1.3
Performance library for Deep Learning
Public Attributes | List of all members
dnnl_batch_normalization_desc_t Struct Reference

A descriptor of a Batch Normalization operation. More...

#include <dnnl_types.h>

Collaboration diagram for dnnl_batch_normalization_desc_t:
Collaboration graph
[legend]

Public Attributes

dnnl_primitive_kind_t primitive_kind
 The kind of primitive. More...
 
dnnl_prop_kind_t prop_kind
 The kind of propagation. More...
 
dnnl_memory_desc_t data_desc
 Source and destination memory descriptor.
 
dnnl_memory_desc_t diff_data_desc
 Source and destination gradient memory descriptor.
 
dnnl_memory_desc_t data_scaleshift_desc
 Scale and shift data and gradient memory descriptors. More...
 
dnnl_memory_desc_t stat_desc
 Statistics memory descriptor. More...
 
float batch_norm_epsilon
 Batch normalization epsilon parameter.
 

Detailed Description

A descriptor of a Batch Normalization operation.

Member Data Documentation

◆ primitive_kind

dnnl_primitive_kind_t dnnl_batch_normalization_desc_t::primitive_kind

The kind of primitive.

Used for self-identifying the primitive descriptor. Must be dnnl_batch_normalization.

◆ prop_kind

dnnl_prop_kind_t dnnl_batch_normalization_desc_t::prop_kind

The kind of propagation.

Possible values: dnnl_forward_training, dnnl_forward_inference, dnnl_backward, and dnnl_backward_data.

◆ data_scaleshift_desc

dnnl_memory_desc_t dnnl_batch_normalization_desc_t::data_scaleshift_desc

Scale and shift data and gradient memory descriptors.

Scaleshift memory descriptor uses 2D dnnl_nc format[2,Channels]. 1-st dimension contains gamma parameter, 2-nd dimension contains beta parameter.

◆ stat_desc

dnnl_memory_desc_t dnnl_batch_normalization_desc_t::stat_desc

Statistics memory descriptor.

Statistics (mean or variance) descriptor use 1D dnnl_x format[Channels].


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