Intel(R) Math Kernel Library for Deep Neural Networks (Intel(R) MKL-DNN)  0.16
Performance library for Deep Learning
Public Attributes | List of all members
mkldnn_wino_desc_t Struct Reference
C API » Types » Auxiliary types for memory description

Description of tensor of weights for integer 8bit winograd convolution. More...

#include <mkldnn_types.h>

Public Attributes

mkldnn_wino_memory_format_t wino_format
 
int r
 
int alpha
 
int ic
 
int oc
 
int ic_block
 
int oc_block
 
int ic2_block
 
int oc2_block
 
size_t size
 

Detailed Description

Description of tensor of weights for integer 8bit winograd convolution.

Member Data Documentation

◆ alpha

int mkldnn_wino_desc_t::alpha

◆ ic

int mkldnn_wino_desc_t::ic

◆ ic2_block

int mkldnn_wino_desc_t::ic2_block

◆ ic_block

int mkldnn_wino_desc_t::ic_block

◆ oc

int mkldnn_wino_desc_t::oc

◆ oc2_block

int mkldnn_wino_desc_t::oc2_block

◆ oc_block

int mkldnn_wino_desc_t::oc_block

◆ r

int mkldnn_wino_desc_t::r

◆ size

size_t mkldnn_wino_desc_t::size

◆ wino_format

mkldnn_wino_memory_format_t mkldnn_wino_desc_t::wino_format
The documentation for this struct was generated from the following file:
Generated by   doxygen 1.8.13