Getting Started Guide

Contents

Batch Processing

Layer Input

The forward two-dimensional stochastic pooling 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 ... x
n
p
that stores the non-negative input data for the forward two-dimensional stochastic pooling layer. This input can be an object of any class derived from
Tensor
.
If you provide the input data tensor with negative elements, the layer algorithm returns unpredicted results.

Layer Parameters

For common parameters of neural network layers, see Common Parameters .
In addition to the common parameters, the forward two-dimensional stochastic pooling 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
Performance-oriented computation method, the only method supported by the layer.
kernelSizes
KernelSizes(2, 2)
Data structure representing sizes
m
1
,
m
2
of two-dimensional tensor
K
.
strides
Strides(2, 2)
Data structure representing intervals
s
1
,
s
2
on which the subtensors for stochastic pooling are selected.
paddings
Paddings(0, 0)
Data structure representing numbers
p
1
,
p
2
of data elements to implicitly add to each side of the two-dimensional subtensor along which stochastic pooling is performed.
indices
Indices(p-2, p-1)
Indices
k
1
,
k
2
of the dimensions along which stochastic pooling is performed.
predictionStage
false
Flag that specifies whether the layer is used for the prediction stage.
DEPRECATED:
seed
777
This parameter is deprecated and will be removed in a future release.
Seed for multinomial random number generator.
engine
SharePtr< engines:: mt19937:: Batch>()
Pointer to the random number generator engine that is used internally for multinomial random number generation.

Layer Output

The forward two-dimensional stochastic pooling 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
l
1
x ... x
l
p
that stores the result of the forward two-dimensional stochastic pooling layer. This input can be an object of any class derived from
Tensor
.
resultForBackward
Collection of data needed for the backward two-dimensional stochastic pooling layer.
Element ID
Element
auxSelectedIndices
Tensor
S
of size
l
1
x ... x
l
p
that stores positions of selected elements.
auxInputDimensions
NumericTable
of size 1 x
p
that stores the sizes of the dimensions of input data tensor
X
:
n
1
,
n
2
, …,
n
p
.

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