apollo::prediction::network::Conv1d Class Reference

Conv1d is the convolution 1d network layer. Conv1d layer output is y = Conv(x, w), where x is the input, w the weight. More...

#include <net_layer.h>

Inheritance diagram for apollo::prediction::network::Conv1d:

Collaboration diagram for apollo::prediction::network::Conv1d:

Public Member Functions
bool	Load (const apollo::prediction::LayerParameter &layer_pb) override
	Load the layer parameter from a pb message. More...
bool	Load (const apollo::prediction::Conv1dParameter &conv1d_pb)
	Load the conv1d layer parameter from a pb message. More...
void	Run (const std::vector< Eigen::MatrixXf > &inputs, Eigen::MatrixXf *output) override
	Compute the layer output from inputs. More...
Public Member Functions inherited from apollo::prediction::network::Layer
	Layer ()=default
	Constructor. More...
virtual	~Layer ()=default
	Destructor. More...
virtual void	ResetState ()
	Reset the internal state of a layer such as LSTM, GRU. More...
virtual void	SetState (const std::vector< Eigen::MatrixXf > &states)
	Set the internal state of a layer. More...
virtual void	State (std::vector< Eigen::MatrixXf > *states) const
	Access to the internal state of a layer. More...
std::string	Name () const
	Name of a layer. More...
int	OrderNumber () const
	Order number of a layer in a network. More...

Detailed Description

Conv1d is the convolution 1d network layer. Conv1d layer output is y = Conv(x, w), where x is the input, w the weight.

Parameter w and b can be loaded from pb message. if bias is not used, b = 0.

Member Function Documentation

Load() [1/2]

bool apollo::prediction::network::Conv1d::Load ( const apollo::prediction::LayerParameter &  layer_pb )

overridevirtual

Load the layer parameter from a pb message.

Parameters

A	pb message contains the parameters

Returns

True is loaded successively, otherwise False

Reimplemented from apollo::prediction::network::Layer.

Load() [2/2]

bool apollo::prediction::network::Conv1d::Load

(

const apollo::prediction::Conv1dParameter &

conv1d_pb

)

Load the conv1d layer parameter from a pb message.

Parameters

A	pb message contains the parameters

Returns

True is loaded successively, otherwise False

Run()

void apollo::prediction::network::Conv1d::Run ( const std::vector< Eigen::MatrixXf > &  inputs, Eigen::MatrixXf *  output  )

overridevirtual

Compute the layer output from inputs.

Parameters

Inputs	to a network layer
Output	of a network layer will be returned

Implements apollo::prediction::network::Layer.

---

The documentation for this class was generated from the following file:

• modules/prediction/network/net_layer.h