dnnl::lrn_backward::desc Struct Reference

Descriptor for an LRN backward propagation primitive. More...

#include <dnnl.hpp>

Collaboration diagram for dnnl::lrn_backward::desc:

Public Member Functions
	desc (algorithm algorithm, const memory::desc &data_desc, const memory::desc &diff_data_desc, memory::dim local_size, float alpha, float beta, float k=1.f)
	Constructs a descriptor for an LRN backward propagation primitive. More...

Detailed Description

Descriptor for an LRN backward propagation primitive.

Examples:

cnn_training_f32.cpp, and cpu_cnn_training_bf16.cpp.

Constructor & Destructor Documentation

desc()

dnnl::lrn_backward::desc::desc ( algorithm  algorithm, const memory::desc &  data_desc, const memory::desc &  diff_data_desc, memory::dim  local_size, float  alpha, float  beta, float  k = 1.f  )

inline

Constructs a descriptor for an LRN backward propagation primitive.

Inputs:

• src (dnnl::primitive_desc_base::src_desc (0))
• diff_dst (dnnl::primitive_desc_base::diff_dst_desc (0))
• workspace (dnnl::primitive_desc_base::workspace_desc (0)), if the underlying implementation requires it; must be queried for using dnnl_primitive_desc_query_md() after a corresponding primitive descriptor is created

Outputs:

• diff_src (dnnl::primitive_desc_base::diff_src_desc (0))

Parameters

algorithm	LRN algorithm kind: either dnnl::algorithm::lrn_across_channels, or dnnl::algorithm::lrn_within_channel.
diff_data_desc	Diff source and diff destination memory descriptor.
data_desc	Source memory descriptor.
local_size	Regularization local size.
alpha	The alpha regularization parameter.
beta	The beta regularization parameter.
k	The k regularization parameter.

---

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

• include/dnnl.hpp