Intel(R) Math Kernel Library for Deep Neural Networks (Intel(R) MKL-DNN)  0.21.0
Performance library for Deep Learning
Classes | Public Member Functions | List of all members
mkldnn::batch_normalization_forward Struct Reference

#include <mkldnn.hpp>

Inheritance diagram for mkldnn::batch_normalization_forward:
Inheritance graph
[legend]
Collaboration diagram for mkldnn::batch_normalization_forward:
Collaboration graph
[legend]

Classes

struct  desc
 
struct  primitive_desc
 

Public Member Functions

 batch_normalization_forward (const primitive_desc &aprimitive_desc, const primitive::at &src, const primitive::at &mean, const primitive::at &variance, const primitive::at &weights, const memory &dst)
 
 batch_normalization_forward (const primitive_desc &aprimitive_desc, const primitive::at &src, const primitive::at &mean, const primitive::at &variance, const memory &dst)
 
 batch_normalization_forward (const primitive_desc &aprimitive_desc, const primitive::at &src, const primitive::at &weights, const memory &dst, const memory &mean, const memory &variance)
 
 batch_normalization_forward (const primitive_desc &aprimitive_desc, const primitive::at &src, const primitive::at &weights, const memory &dst, const memory &mean, const memory &variance, const memory &workspace)
 
 batch_normalization_forward (const primitive_desc &aprimitive_desc, const primitive::at &src, const memory &dst, const memory &mean, const memory &variance)
 
 batch_normalization_forward (const primitive_desc &aprimitive_desc, const primitive::at &src, const memory &dst, const memory &mean, const memory &variance, const memory &workspace)
 
 batch_normalization_forward (const primitive_desc &aprimitive_desc, const primitive::at &src, const primitive::at &weights, const memory &dst)
 
 batch_normalization_forward (const primitive_desc &aprimitive_desc, const primitive::at &src, const memory &dst)
 
- Public Member Functions inherited from mkldnn::primitive
const_mkldnn_primitive_desc_t get_primitive_desc () const
 Returns the descriptor of the underlying C API primitive. More...
 
- Public Member Functions inherited from mkldnn::handle< mkldnn_primitive_t >
 handle (mkldnn_primitive_t t=0, bool weak=false)
 Constructs a C handle wrapper. More...
 
 handle (const handle &other)
 
handleoperator= (const handle &other)
 
bool operator== (const handle &other) const
 
bool operator!= (const handle &other) const
 
void reset (mkldnn_primitive_t t, bool weak=false)
 Resets the value of a C handle. More...
 
mkldnn_primitive_t get () const
 Returns the value of the underlying C handle. More...
 

Additional Inherited Members

- Public Types inherited from mkldnn::primitive
enum  kind {
  kind::undefined_primitive = mkldnn_undefined_primitive, kind::memory = mkldnn_memory, kind::view = mkldnn_view, kind::reorder = mkldnn_reorder,
  kind::concat = mkldnn_concat, kind::concat_inplace = mkldnn_concat_inplace, kind::sum = mkldnn_sum, kind::convolution = mkldnn_convolution,
  kind::deconvolution = mkldnn_deconvolution, kind::shuffle = mkldnn_shuffle, kind::eltwise = mkldnn_eltwise, kind::softmax = mkldnn_softmax,
  kind::pooling = mkldnn_pooling, kind::lrn = mkldnn_lrn, kind::batch_normalization = mkldnn_batch_normalization, kind::inner_product = mkldnn_inner_product,
  kind::rnn = mkldnn_rnn
}
 A proxy to C primitive kind enum. More...
 
- Protected Member Functions inherited from mkldnn::handle< mkldnn_primitive_t >
bool operator== (const mkldnn_primitive_t other) const
 
bool operator!= (const mkldnn_primitive_t other) const
 

Constructor & Destructor Documentation

◆ batch_normalization_forward() [1/8]

mkldnn::batch_normalization_forward::batch_normalization_forward ( const primitive_desc aprimitive_desc,
const primitive::at src,
const primitive::at mean,
const primitive::at variance,
const primitive::at weights,
const memory dst 
)
inline

◆ batch_normalization_forward() [2/8]

mkldnn::batch_normalization_forward::batch_normalization_forward ( const primitive_desc aprimitive_desc,
const primitive::at src,
const primitive::at mean,
const primitive::at variance,
const memory dst 
)
inline

◆ batch_normalization_forward() [3/8]

mkldnn::batch_normalization_forward::batch_normalization_forward ( const primitive_desc aprimitive_desc,
const primitive::at src,
const primitive::at weights,
const memory dst,
const memory mean,
const memory variance 
)
inline
Warning
batch_normalization_forward has two constructors with very similar signatures:
  • (pd, src, weights, dst, mean, variance) // 2 in, 3 out
  • (pd, src, dst, mean, variance, workspace) // 1 in, 4 out The only way to distinguish between them is to explicitly cast all input parameters to their type; that is, to const primitive:at &.

◆ batch_normalization_forward() [4/8]

mkldnn::batch_normalization_forward::batch_normalization_forward ( const primitive_desc aprimitive_desc,
const primitive::at src,
const primitive::at weights,
const memory dst,
const memory mean,
const memory variance,
const memory workspace 
)
inline

◆ batch_normalization_forward() [5/8]

mkldnn::batch_normalization_forward::batch_normalization_forward ( const primitive_desc aprimitive_desc,
const primitive::at src,
const memory dst,
const memory mean,
const memory variance 
)
inline

◆ batch_normalization_forward() [6/8]

mkldnn::batch_normalization_forward::batch_normalization_forward ( const primitive_desc aprimitive_desc,
const primitive::at src,
const memory dst,
const memory mean,
const memory variance,
const memory workspace 
)
inline
Warning
batch_normalization_forward has two constructors with very similar signatures:
  • (pd, src, weights, dst, mean, variance) // 2 in, 3 out
  • (pd, src, dst, mean, variance, workspace) // 1 in, 4 out The only way to distinguish between them is to explicitly cast all input parameters to their type; that is, to const primitive:at &.
Note
To make users' experience a little better, this constructor checks whether parameters match the corresponding primitive descriptor, and if not, calls the other (proper) constructor.

◆ batch_normalization_forward() [7/8]

mkldnn::batch_normalization_forward::batch_normalization_forward ( const primitive_desc aprimitive_desc,
const primitive::at src,
const primitive::at weights,
const memory dst 
)
inline

◆ batch_normalization_forward() [8/8]

mkldnn::batch_normalization_forward::batch_normalization_forward ( const primitive_desc aprimitive_desc,
const primitive::at src,
const memory dst 
)
inline

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