Descriptor for a layer normalization backward propagation primitive. More...
#include <dnnl.hpp>
Public Member Functions | |
desc (prop_kind prop_kind, const memory::desc &diff_data_desc, const memory::desc &data_desc, const memory::desc &stat_desc, float epsilon, normalization_flags flags) | |
Constructs a descriptor for layer normalization backward propagation primitive. More... | |
desc (prop_kind prop_kind, const memory::desc &diff_data_desc, const memory::desc &data_desc, float epsilon, normalization_flags flags) | |
Constructs a descriptor for layer normalization backward propagation primitive. More... | |
Descriptor for a layer normalization backward propagation primitive.
|
inline |
Constructs a descriptor for layer normalization backward propagation primitive.
Inputs:
flags
Outputs:
flags
and prop_kind
= dnnl::prop_kind::backwardprop_kind | Propagation kind. Possible values are dnnl::prop_kind::backward_data and dnnl::prop_kind::backward (diffs for all parameters are computed in this case). |
diff_data_desc | Diff source and diff destination memory descriptor. |
data_desc | Source memory descriptor. |
stat_desc | Statistics memory descriptors. |
epsilon | Layer normalization epsilon parameter. |
flags | Layer normalization flags (dnnl::normalization_flags). |
|
inline |
Constructs a descriptor for layer normalization backward propagation primitive.
Inputs:
flags
Outputs:
flags
and prop_kind
= dnnl::prop_kind::backwardprop_kind | Propagation kind. Possible values are dnnl::prop_kind::backward_data and dnnl::prop_kind::backward (diffs for all parameters are computed in this case). |
diff_data_desc | Diff source and diff destination memory descriptor. |
data_desc | Source memory descriptor. |
epsilon | Layer normalization epsilon parameter. |
flags | Layer normalization flags (dnnl::normalization_flags). |