LRN¶

Overview¶

A primitive to perform local response normalization (LRN) across or within channels. More…

// structs

struct dnnl::lrn_backward;
struct dnnl::lrn_forward;

// global functions

dnnl_status_t DNNL_API dnnl_lrn_forward_primitive_desc_create(
    dnnl_primitive_desc_t* primitive_desc,
    dnnl_engine_t engine,
    dnnl_prop_kind_t prop_kind,
    dnnl_alg_kind_t alg_kind,
    const_dnnl_memory_desc_t src_desc,
    const_dnnl_memory_desc_t dst_desc,
    dnnl_dim_t local_size,
    float alpha,
    float beta,
    float k,
    const_dnnl_primitive_attr_t attr
    );

dnnl_status_t DNNL_API dnnl_lrn_backward_primitive_desc_create(
    dnnl_primitive_desc_t* primitive_desc,
    dnnl_engine_t engine,
    dnnl_alg_kind_t alg_kind,
    const_dnnl_memory_desc_t diff_src_desc,
    const_dnnl_memory_desc_t diff_dst_desc,
    const_dnnl_memory_desc_t src_desc,
    dnnl_dim_t local_size,
    float alpha,
    float beta,
    float k,
    const_dnnl_primitive_desc_t hint_fwd_pd,
    const_dnnl_primitive_attr_t attr
    );

Detailed Documentation¶

A primitive to perform local response normalization (LRN) across or within channels.

Global Functions¶

dnnl_status_t DNNL_API dnnl_lrn_forward_primitive_desc_create(
    dnnl_primitive_desc_t* primitive_desc,
    dnnl_engine_t engine,
    dnnl_prop_kind_t prop_kind,
    dnnl_alg_kind_t alg_kind,
    const_dnnl_memory_desc_t src_desc,
    const_dnnl_memory_desc_t dst_desc,
    dnnl_dim_t local_size,
    float alpha,
    float beta,
    float k,
    const_dnnl_primitive_attr_t attr
    )

Creates a primitive descriptor for an LRN forward propagation primitive.

Parameters:

primitive_desc	Output primitive_descriptor.
engine	Engine to use.
prop_kind	Propagation kind. Possible values are dnnl_forward_training and dnnl_forward_inference.
alg_kind	LRN algorithm kind: either dnnl_lrn_across_channels or dnnl_lrn_within_channel.
src_desc	Source memory descriptor.
dst_desc	Destination memory descriptor.
local_size	Regularization local size.
alpha	The alpha regularization parameter.
beta	The beta regularization parameter.
k	The k regularization parameter.
attr	Primitive attributes (can be NULL).

Returns:

dnnl_success on success and a status describing the error otherwise.

dnnl_status_t DNNL_API dnnl_lrn_backward_primitive_desc_create(
    dnnl_primitive_desc_t* primitive_desc,
    dnnl_engine_t engine,
    dnnl_alg_kind_t alg_kind,
    const_dnnl_memory_desc_t diff_src_desc,
    const_dnnl_memory_desc_t diff_dst_desc,
    const_dnnl_memory_desc_t src_desc,
    dnnl_dim_t local_size,
    float alpha,
    float beta,
    float k,
    const_dnnl_primitive_desc_t hint_fwd_pd,
    const_dnnl_primitive_attr_t attr
    )

Creates a primitive descriptor for an LRN backward propagation primitive.