Intel(R) Math Kernel Library for Deep Neural Networks (Intel(R) MKL-DNN)
0.21.0
Performance library for Deep Learning
|
A descriptor of a shuffle operation. More...
#include <mkldnn_types.h>
Public Attributes | |
mkldnn_primitive_kind_t | primitive_kind |
The kind of primitive. More... | |
mkldnn_prop_kind_t | prop_kind |
The kind of propagation. More... | |
mkldnn_memory_desc_t | data_desc |
Source and destination memory descriptor, and source and destination gradient memory descriptor. More... | |
int | axis |
axis for shuffling. More... | |
int | group_size |
number of groups in group convolution More... | |
A descriptor of a shuffle operation.
mkldnn_primitive_kind_t mkldnn_shuffle_desc_t::primitive_kind |
The kind of primitive.
Used for self-identifying the primitive descriptor. Must be mkldnn_convolution.
mkldnn_prop_kind_t mkldnn_shuffle_desc_t::prop_kind |
The kind of propagation.
Possible values: mkldnn_forward_training, mkldnn_forward_inference, and mkldnn_backward_data.
mkldnn_memory_desc_t mkldnn_shuffle_desc_t::data_desc |
Source and destination memory descriptor, and source and destination gradient memory descriptor.
int mkldnn_shuffle_desc_t::axis |
axis for shuffling.
int mkldnn_shuffle_desc_t::group_size |
number of groups in group convolution