oneAPI Deep Neural Network Library (oneDNN)
Performance library for Deep Learning
1.96.0
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 aalgorithm, 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_bf16.cpp, and cnn_training_f32.cpp.

Constructor & Destructor Documentation

◆ desc()

dnnl::pooling_backward::desc::desc ( algorithm  aalgorithm,
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.

Arrays strides, kernel, padding_l, and padding_r contain values for spatial dimensions only and hence must have the same number of elements as there are spatial dimensions. The order of values is the same as in the tensor: depth (for 3D tensors), height (for 3D and 2D tensors), and width.

Parameters
aalgorithmPooling 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_descDiff source memory descriptor.
diff_dst_descDiff destination memory descriptor.
stridesVector of strides for spatial dimension.
kernelVector of kernel spatial dimensions.
padding_lVector of padding values for low indices for each spatial dimension ([[front,] top,] left).
padding_rVector of padding values for high indices for each spatial dimension ([[back,] bottom,] right).

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