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 Softmax 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. More... | |
mkldnn_memory_desc_t | diff_desc |
Source and Destination of gradient memory descriptor. More... | |
int | softmax_axis |
The axis along which to perform the softmax. More... | |
A descriptor of a Softmax operation.
mkldnn_primitive_kind_t mkldnn_softmax_desc_t::primitive_kind |
The kind of primitive.
Used for self-identifying the primitive descriptor. Must be mkldnn_softmax.
mkldnn_prop_kind_t mkldnn_softmax_desc_t::prop_kind |
The kind of propagation.
Possible values: mkldnn_forward_training and mkldnn_forward_inference.
mkldnn_memory_desc_t mkldnn_softmax_desc_t::data_desc |
Source and destination memory descriptor.
mkldnn_memory_desc_t mkldnn_softmax_desc_t::diff_desc |
Source and Destination of gradient memory descriptor.
int mkldnn_softmax_desc_t::softmax_axis |
The axis along which to perform the softmax.