Simd Library Documentation.

Home | Release Notes | Download | Documentation | Issues | GitHub | SourceForge
Layer Class Referenceabstract

Layer class. More...

Inheritance diagram for Layer:
AveragePoolingLayer ConvolutionalLayer DropoutLayer FullyConnectedLayer InputLayer MaxPoolingLayer

Public Types

enum  Type {
  Input,
  Convolutional,
  MaxPooling,
  FullyConnected,
  Dropout,
  AveragePooling
}
 
enum  Method {
  Fast,
  Check,
  Train
}
 

Public Member Functions

virtual ~Layer ()
 

Detailed Description

Layer class.

Abstract base class for all possible layers.

Member Enumeration Documentation

◆ Type

enum Type

Describes types of network layers.

Enumerator
Input 

Layer type corresponding to Simd::Neural::InputLayer.

Convolutional 

Layer type corresponding to Simd::Neural::ConvolutionalLayer.

MaxPooling 

Layer type corresponding to Simd::Neural::MaxPoolingLayer.

FullyConnected 

Layer type corresponding to Simd::Neural::FullyConnectedLayer.

Dropout 

Layer type corresponding to Simd::Neural::DropoutLayer.

AveragePooling 

Layer type corresponding to Simd::Neural::AveragePooling.

◆ Method

enum Method

Describes method of forward propagation in the network layer.

Enumerator
Fast 

The fastest method. It is incompatible with train process.

Check 

Control checking during train process.

Train 

Forward propagation in train process.

Constructor & Destructor Documentation

◆ ~Layer()

virtual ~Layer ( )
virtual

Virtual destructor.