#include <dnnl_types.h>
Collaboration diagram for dnnl_prelu_desc_t:
Public Attributes | |
| dnnl_primitive_kind_t | primitive_kind |
| dnnl_prop_kind_t | prop_kind |
| dnnl_memory_desc_t | data_desc |
| Source and destination memory descriptor. More... | |
| dnnl_memory_desc_t | weights_desc |
| dnnl_memory_desc_t | diff_data_desc |
| Source and destination gradient memory descriptor. More... | |
| dnnl_memory_desc_t | diff_weights_desc |
| Learnable parameter alpha gradient memory descriptor. More... | |
Member Data Documentation
◆ data_desc
| dnnl_memory_desc_t dnnl_prelu_desc_t::data_desc |
Source and destination memory descriptor.
◆ diff_data_desc
| dnnl_memory_desc_t dnnl_prelu_desc_t::diff_data_desc |
Source and destination gradient memory descriptor.
◆ diff_weights_desc
| dnnl_memory_desc_t dnnl_prelu_desc_t::diff_weights_desc |
Learnable parameter alpha gradient memory descriptor.
◆ primitive_kind
| dnnl_primitive_kind_t dnnl_prelu_desc_t::primitive_kind |
The kind of primitive. Used for self-identifying the primitive descriptor. Must be dnnl_prelu.
◆ prop_kind
| dnnl_prop_kind_t dnnl_prelu_desc_t::prop_kind |
The kind of propagation. Possible values: dnnl_forward_training, dnnl_forward_inference, dnnl_backward
◆ weights_desc
| dnnl_memory_desc_t dnnl_prelu_desc_t::weights_desc |
Learnable parameter alpha memory descriptor. Alpha describes negative slope.
The documentation for this struct was generated from the following file:
- /work/mxnet/include/onednn/oneapi/dnnl/dnnl_types.h
