Developer Guide

Contents

Batch Processing

Layer Input

The forward local contrast normalization layer accepts the input described below. Pass the Input ID as a parameter to the methods that provide input for your algorithm. For more details, see Algorithms.
Input ID
Input
data
Pointer to tensor
X
of size
n
1
x
n
2
x
n
3
x
n
4
that stores the input data for the forward local contrast normalization layer. This input can be an object of any class derived from
Tensor
.

Layer Parameters

For common parameters of neural network layers, see Common Parameters.
In addition to the common parameters, the forward local contrast normalization layer has the following parameters:
Parameter
Default Value
Description
algorithmFPType
float
The floating-point type that the algorithm uses for intermediate computations. Can be
float
or
double
.
method
defaultDense
Default computation method used by the algorithm, the only method supported by the layer.
kernel
HomogenTensor<float>
of size 5 x 5 with values 0.04
Tensor with sizes
m
1
x
m
2
of the two-dimensional kernel. Only kernels with odd dimensions are currently supported.
indices
indices
(2,3)
Data structure representing dimensions
k
1
and
k
2
for kernels.
sumDimension
HomogenNumericTable
<float>
of size 1 x 1 with value 1
Numeric table of size 1 x 1 that stores dimension
f
. If it is
NULL
, there is no summation over this dimension.

Layer Output

The forward local contrast normalization layer calculates the result described below. Pass the Result ID as a parameter to the methods that access the results of your algorithm. For more details, see Algorithms.
Result ID
Result
value
Pointer to tensor
Y
of size
n
1
x
n
2
x
n
3
x
n
4
that stores the result of the forward local contrast normalization layer. This input can be an object of any class derived from
Tensor
.
layerData
Collection of input data needed for the backward local contrast normalization layer. This collection can contain objects of any class derived from
Tensor
.
Element ID
Element
auxInvMax
Pointer to the tensor:
  • 1/
    m
    nij
    of size
    n
    1
    x
    n
    3
    x
    n
    4
    if
    sumDimension
    is not
    NULL
  • 1/
    m
    nqij
    of size
    n
    1
    x
    n
    2
    x
    n
    3
    x
    n
    4
    if
    sumDimension
    is
    NULL
This tensor stores the inverted max values. This input can be an object of any class derived from
Tensor
.
auxCenteredData
Pointer to tensor
v
n
q
i
j
of size
n
1
x
n
2
x
n
3
x
n
4
that stores values as shown above. This input can be an object of any class derived from
Tensor
.
auxSigma
Pointer to tensor
σ
n
i
j
of size
n
1
x
n
3
x
n
4
if
sumDimension
is not
NULL, or
tensor
σ
n
q
i
j
of size
n
1
x
n
2
x
n
3
x
n
4
otherwise, that stores values as shown above. This input can be an object of any class derived from
Tensor
.
auxC
Pointer to tensor
c
n
of size
n
1
if
sumDimension
is not
NULL, or
tensor
c
n
q
of size
n
1
x
n
2
otherwise, that stores values as shown above. This input can be an object of any class derived from
Tensor
.

Product and Performance Information

1

Intel's compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include SSE2, SSE3, and SSSE3 instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice.

Notice revision #20110804