Simd Library Documentation.

Home | Release Notes | Download | Documentation | Issues | GitHub | SourceForge
MaxPoolingLayer Class Reference

MaxPoolingLayer class. More...

Inheritance diagram for MaxPoolingLayer:
PoolingLayer Layer

Public Member Functions

 MaxPoolingLayer (Function::Type f, const Size &srcSize, size_t srcDepth, const Size &poolingSize, const Size &poolingStride, const Size &poolingPad=Size())
 Creates new MaxPoolingLayer class. More...
 
- Public Member Functions inherited from Layer
virtual ~Layer ()
 

Additional Inherited Members

- Public Types inherited from Layer
enum  Type {
  Input,
  Convolutional,
  MaxPooling,
  AveragePooling,
  FullyConnected,
  Dropout
}
 
enum  Method {
  Fast,
  Check,
  Train
}
 

Detailed Description

MaxPoolingLayer class.

Max pooling layer in neural network.

Constructor & Destructor Documentation

◆ MaxPoolingLayer()

MaxPoolingLayer ( Function::Type  f,
const Size srcSize,
size_t  srcDepth,
const Size poolingSize,
const Size poolingStride,
const Size poolingPad = Size() 
)

Creates new MaxPoolingLayer class.

Parameters
[in]f- a type of activation function used in this layer.
[in]srcSize- a size (width and height) of input image.
[in]srcDepth- a number of input channels (images).
[in]poolingSize- a pooling size.
[in]poolingStride- a pooling stride.
[in]poolingPad- a pooling pad. By default it is equal to (0, 0).