C++ API Reference for Intel® Data Analytics Acceleration Library 2020 Update 1

Namespaces | Enumerations
daal::algorithms::neural_networks::layers::maximum_pooling2d Namespace Reference

Contains classes for maximum two-dimensional (2D) pooling layer.

Namespaces

 backward
 Contains classes for backward maximum 2D pooling layer.
 
 forward
 Contains classes for forward maximum 2D pooling layer.
 
 interface1
 Contains version 1.0 of Intel(R) Data Analytics Acceleration Library (Intel(R) DAAL) interface.
 

Enumerations

enum  Method { defaultDense = 0 }
 Computation methods for the maximum 2D pooling layer. More...
 
enum  LayerDataId { auxSelectedIndices, auxData }
 Identifiers of input tensors for the backward maximum 2D pooling layer and results for the forward maximum 2D pooling layer. More...
 
enum  LayerDataNumericTableId { auxInputDimensions = lastLayerDataId + 1 }
 Identifiers of input numeric tables for the backward maximum 2D pooling layer and results for the forward maximum 2D pooling layer. More...
 

Enumeration Type Documentation

Enumerator
auxSelectedIndices 

p-dimensional tensor that stores the positions of maximum elements

auxData 

p-dimensional tensor that stores the data processed at the forward stage of the layer

Enumerator
auxInputDimensions 

Numeric table of size 1 x p that contains the sizes of the dimensions of the input data tensor

enum Method

Enumerator
defaultDense 

Default: performance-oriented method

For more complete information about compiler optimizations, see our Optimization Notice.