dnnl::pooling_backward::desc Struct Reference

Descriptor for a pooling backward propagation primitive. More...

#include <dnnl.hpp>

Collaboration diagram for dnnl::pooling_backward::desc:

Public Member Functions
	desc (algorithm algorithm, const memory::desc &diff_src_desc, const memory::desc &diff_dst_desc, const memory::dims &strides, const memory::dims &kernel, const memory::dims &padding_l, const memory::dims &padding_r)
	Constructs a descriptor for pooling backward propagation primitive. More...

Detailed Description

Descriptor for a pooling backward propagation primitive.

Examples:

cnn_training_f32.cpp, and cpu_cnn_training_bf16.cpp.

Constructor & Destructor Documentation

desc()

dnnl::pooling_backward::desc::desc ( algorithm  algorithm, const memory::desc &  diff_src_desc, const memory::desc &  diff_dst_desc, const memory::dims &  strides, const memory::dims &  kernel, const memory::dims &  padding_l, const memory::dims &  padding_r  )

inline

Constructs a descriptor for pooling backward propagation primitive.

Inputs:

• diff_dst (dnnl::primitive_desc_base::diff_dst_desc (0))
• workspace (dnnl::primitive_desc_base::workspace_desc (0)), if alg_kind = dnnl::algorithm::pooling_max; must be queried for using dnnl::primitive_desc_base::query_md() after a corresponding primitive descriptor is created

Outputs:

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

Parameters

algorithm	Pooling algorithm kind: either dnnl::algorithm::pooling_max, dnnl::algorithm::pooling_avg_include_padding, or dnnl::algorithm::pooling_avg (same as dnnl::algorithm::pooling_avg_exclude_padding).
diff_src_desc	Diff source memory descriptor.
diff_dst_desc	Diff destination memory descriptor.
strides	Vector of strides for spatial dimension.
kernel	Vector of kernel spatial dimensions.
padding_l	Vector of padding values for low indices for each spatial dimension (front, top, left).
padding_r	Vector of padding values for high indices for each spatial dimension (back, bottom, right).

---

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

• include/dnnl.hpp