Layer Class Reference

Layer class. More...

#include <SimdNeural.hpp>

Inheritance diagram for Layer:

Public Types
enum	Type {   Input ,   Convolutional ,   MaxPooling ,   AveragePooling ,   FullyConnected ,   Dropout }
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.
AveragePooling	Layer type corresponding to Simd::Neural::AveragePooling.
FullyConnected	Layer type corresponding to Simd::Neural::FullyConnectedLayer.
Dropout	Layer type corresponding to Simd::Neural::DropoutLayer.

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.