A descriptor of a Layer Normalization operation. More...

#include <dnnl_types.h>

Collaboration diagram for dnnl_layer_normalization_desc_t:

[legend]

Public Attributes
dnnl_primitive_kind_t	primitive_kind
	The kind of primitive. More...

dnnl_prop_kind_t	prop_kind
	The kind of propagation. More...

dnnl_memory_desc_t	data_desc
	Source and destination memory descriptor.

dnnl_memory_desc_t	diff_data_desc
	Source and destination gradient memory descriptor.

dnnl_memory_desc_t	data_scaleshift_desc
	Scale and shift data and gradient memory descriptors. More...

dnnl_memory_desc_t	stat_desc
	Mean and variance data memory descriptors. More...

float	layer_norm_epsilon
	Layer normalization epsilon parameter.

Detailed Description

A descriptor of a Layer Normalization operation.

Member Data Documentation

◆ primitive_kind

dnnl_primitive_kind_t dnnl_layer_normalization_desc_t::primitive_kind

The kind of primitive.

Used for self-identifying the primitive descriptor. Must be dnnl_layer_normalization.

◆ prop_kind

dnnl_prop_kind_t dnnl_layer_normalization_desc_t::prop_kind

The kind of propagation.

Possible values: dnnl_forward_training, dnnl_forward_inference, dnnl_backward, and dnnl_backward_data.

◆ data_scaleshift_desc

dnnl_memory_desc_t dnnl_layer_normalization_desc_t::data_scaleshift_desc

Scale and shift data and gradient memory descriptors.

Scaleshift memory descriptor uses 2D dnnl_ab format[2, normalized_dim] where 1-st dimension contains gamma parameter, 2-nd dimension contains beta parameter. Normalized_dim is equal to the last logical dimension of the data tensor across which normalization is performed.

◆ stat_desc

dnnl_memory_desc_t dnnl_layer_normalization_desc_t::stat_desc

Mean and variance data memory descriptors.

Statistics (mean and variance) memory descriptor is the k-dimensional tensor where k is equal to data_tensor_ndims - 1 and may have any plain (stride[last_dim] == 1) user-provided format.

The documentation for this struct was generated from the following file: