oneAPI Deep Neural Network Library (oneDNN)
Performance library for Deep Learning
1.96.0
dnnl::batch_normalization_backward::desc Struct Reference

Descriptor for a batch normalization backward propagation primitive. More...

#include <dnnl.hpp>

Collaboration diagram for dnnl::batch_normalization_backward::desc:

Public Member Functions

 desc (prop_kind aprop_kind, const memory::desc &diff_data_desc, const memory::desc &data_desc, float epsilon, normalization_flags flags)
 Constructs a batch normalization descriptor for backward propagation. More...
 

Detailed Description

Descriptor for a batch normalization backward propagation primitive.

Constructor & Destructor Documentation

◆ desc()

dnnl::batch_normalization_backward::desc::desc ( prop_kind  aprop_kind,
const memory::desc diff_data_desc,
const memory::desc data_desc,
float  epsilon,
normalization_flags  flags 
)
inline

Constructs a batch normalization descriptor for backward propagation.

Parameters
aprop_kindPropagation kind. Possible values are dnnl::prop_kind::backward_data and dnnl::prop_kind::backward (diffs for all parameters are computed in this case).
diff_data_descDiff source and diff destination memory descriptor.
data_descSource memory descriptor.
epsilonBatch normalization epsilon parameter.
flagsBatch normalization flags (dnnl::normalization_flags).

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