@Namespace(value="dnnl") @Properties(inherit=dnnl.class) public class layer_normalization_forward extends primitive
\addtogroup dnnl_api_layer_normalization Layer Normalization A primitive to perform layer normalization. Normalization is performed within the last logical dimension of data tensor. Both forward and backward propagation primitives support in-place operation; that is, src and dst can refer to the same memory for forward propagation, and diff_dst and diff_src can refer to the same memory for backward propagation. The layer normalization primitives computations can be controlled by specifying different dnnl::normalization_flags values. For example, layer normalization forward propagation can be configured to either compute the mean and variance or take them as arguments. It can either perform scaling and shifting using gamma and beta parameters or not. Optionally, it can also perform a fused ReLU, which in case of training would also require a workspace.
dev_guide_layer_normalization in developer guide
\{
Layer normalization forward propagation primitive.
| Modifier and Type | Class and Description |
|---|---|
static class |
layer_normalization_forward.desc
Descriptor for a layer normalization forward propagation primitive.
|
static class |
layer_normalization_forward.primitive_desc
Primitive descriptor for a layer normalization forward propagation
primitive.
|
primitive.kindPointer.CustomDeallocator, Pointer.Deallocator, Pointer.NativeDeallocator, Pointer.ReferenceCounter| Constructor and Description |
|---|
layer_normalization_forward()
Default constructor.
|
layer_normalization_forward(layer_normalization_forward.primitive_desc pd)
Constructs a layer normalization forward propagation primitive.
|
layer_normalization_forward(long size)
Native array allocator.
|
layer_normalization_forward(Pointer p)
Pointer cast constructor.
|
| Modifier and Type | Method and Description |
|---|---|
layer_normalization_forward |
getPointer(long i) |
layer_normalization_forward |
position(long position) |
execute, get_dnnl_primitive_desc, get_kindasBoolean, asDnnl_primitive, equals, get, get, notEquals, put, reset, resetaddress, asBuffer, asByteBuffer, availablePhysicalBytes, calloc, capacity, capacity, close, deallocate, deallocate, deallocateReferences, deallocator, deallocator, equals, fill, formatBytes, free, getPointer, getPointer, getPointer, hashCode, isNull, isNull, limit, limit, malloc, maxBytes, maxPhysicalBytes, memchr, memcmp, memcpy, memmove, memset, offsetof, offsetof, parseBytes, physicalBytes, position, put, realloc, referenceCount, releaseReference, retainReference, setNull, sizeof, sizeof, toString, totalBytes, totalCount, totalPhysicalBytes, withDeallocator, zeropublic layer_normalization_forward(Pointer p)
Pointer.Pointer(Pointer).public layer_normalization_forward(long size)
Pointer.position(long).public layer_normalization_forward()
public layer_normalization_forward(@Const @ByRef layer_normalization_forward.primitive_desc pd)
pd - Primitive descriptor for a layer normalization forward
propagation primitive.public layer_normalization_forward position(long position)
public layer_normalization_forward getPointer(long i)
getPointer in class primitiveCopyright © 2020. All rights reserved.