Batch Processing

Layer Input

The backward two-dimensional spatial pyramid 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

inputGradient

Pointer to tensor G of size n1 x n' that stores the input gradient computed on the preceding layer. This input can be an object of any class derived from Tensor.

inputFromForward

Collection of data needed for the backward two-dimensional spatial pyramid pooling layer.

Algorithm

Element ID

Element

any

auxInputDimensions

NumericTable of size 1 x p that stores the sizes of the dimensions of input data tensor X: n1, n2, …, np.

spatial pyramid max pooling, spatial pyramid stochastic pooling

auxSelectedIndices

Tensor T of size n1 x n' that stores indices of maximum/stochastic elements.

Layer Parameters

For common parameters of neural network layers, see Common Parameters.

In addition to the common parameters, the backward two-dimensional spatial pyramid pooling layer has the following parameters:

Algorithm

Parameter

Default Value

Description

any

algorithmFPType

float

The floating-point type that the algorithm uses for intermediate computations. Can be float or double.

any

method

defaultDense

Performance-oriented computation method, the only method supported by the layer.

any

indices

Indices(p-2, p-1)

Indices k1, k2 of the dimensions along which spatial pyramid pooling is performed.

spatial pyramid stochastic pooling

pyramidHeight

Not applicable

Value L of the pyramid height.

spatial pyramid stochastic pooling

engine

SharePtr< engines:: mt19937:: Batch>()

Pointer to the random number generator engine that is used internally for multinomial random number generation.

Layer Output

The backward two-dimensional spatial pyramid 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

gradient

Pointer to tensor Z of size n1 x n2 x n3 x n4 that stores the result of the backward two-dimensional spatial pyramid pooling layer. This input can be an object of any class derived from Tensor.

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