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 n1 x ... x np 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.

Note

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 m1, m2 of two-dimensional tensor K.

strides

Strides(2, 2)

Data structure representing intervals s1, s2 on which the subtensors for stochastic pooling are selected.

paddings

Paddings(0, 0)

Data structure representing numbers p1, p2 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 k1, k2 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

Note

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 l1 x ... x lp 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 l1 x ... x lp 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: n1, n2, …, np.

For more complete information about compiler optimizations, see our Optimization Notice.
Select sticky button color: 
Orange (only for download buttons)