tenzr::nn::Linear¶

Fully connected affine module applying a weight and optional bias.

#include <linear.h>

Public Functions¶

	Name
	Linear(int64_t in_features, int64_t out_features, bool use_bias, DType dtype, std::optional< uint64_t > seed =std::nullopt)
template <typename T =float>	Linear(int64_t in_features, int64_t out_features, bool use_bias =true, std::optional< uint64_t > seed =std::nullopt) Construct with the parameter dtype inferred from T.
template <typename T >	Linear(std::type_identity< T > , int64_t in_features, int64_t out_features, bool use_bias =true, std::optional< uint64_t > seed =std::nullopt) Construct from an explicit std::type_identity dtype tag.
virtual Tensor	Forward(const Tensor & input) override
Tensor &	Weight()
const Tensor &	Weight() const
Tensor &	Bias()
const Tensor &	Bias() const
int64_t	InFeatures() const
int64_t	OutFeatures() const
bool	HasBias() const
virtual std::string	Name() const override
template <typename T =float> Linear	Create(int64_t in_features, int64_t out_features, bool use_bias =true, std::optional< uint64_t > seed =std::nullopt) Static factory mirroring the templated constructor.

Additional inherited members¶

Public Functions inherited from tenzr::nn::Module

	Name
virtual	~Module() =default
Tensor	operator()(const Tensor & input)
virtual void	Train(bool mode)
void	Train() Switch to training mode.
void	Eval() Switch to evaluation mode.
bool	IsTraining() const
Tensor &	RegisterParameter(std::string name, Tensor param)
template <typename T ,typename... Args> std::shared_ptr< T >	RegisterSubmodule(std::string name, Args &&... args)
std::shared_ptr< Module >	RegisterSubmodule(std::string name, std::shared_ptr< Module > submod)
std::vector< Tensor >	Parameters(bool recurse =true) const
std::unordered_map< std::string, Tensor >	NamedParameters(std::string prefix ="", bool recurse =true) const
std::unordered_map< std::string, Tensor >	StateDict() const
void	LoadStateDict(const std::unordered_map< std::string, Tensor > & state)

Protected Attributes inherited from tenzr::nn::Module

	Name
std::unordered_map< std::string, Tensor >	parameters_
std::unordered_map< std::string, std::shared_ptr< Module > >	submodules_
bool	training_

Public Functions Documentation¶

function Linear¶

Linear(
    int64_t in_features,
    int64_t out_features,
    bool use_bias,
    DType dtype,
    std::optional< uint64_t > seed =std::nullopt
)

Parameters:

in_features Number of input features.
out_features Number of output features.
use_bias Add a bias term when true.
dtype Parameter dtype.
seed Optional PRNG seed.
in_features Input feature count.
out_features Output feature count.
use_bias Whether to allocate a bias term.
dtype Parameter dtype.
seed Optional seed for weight initialization.

Construct with an explicit runtime dtype. Create a linear layer with Glorot-uniform weights.

function Linear¶

template <typename T  =float>
inline Linear(
    int64_t in_features,
    int64_t out_features,
    bool use_bias =true,
    std::optional< uint64_t > seed =std::nullopt
)

Construct with the parameter dtype inferred from T.

function Linear¶

template <typename T >
inline explicit Linear(
    std::type_identity< T > ,
    int64_t in_features,
    int64_t out_features,
    bool use_bias =true,
    std::optional< uint64_t > seed =std::nullopt
)

Construct from an explicit std::type_identity dtype tag.

function Forward¶

virtual Tensor Forward(
    const Tensor & input
) override

Parameters:

input Input of shape (..., in_features).
input Input tensor of shape [..., in_features].

Return:

Output of shape (..., out_features).
Output tensor of shape [..., out_features].

Reimplements: tenzr::nn::Module::Forward

Apply the affine transform to input. Compute input @ weight + bias.

function Weight¶

inline Tensor & Weight()

Return: Mutable reference to the weight tensor.

function Weight¶

inline const Tensor & Weight() const

Return: Const reference to the weight tensor.

function Bias¶

inline Tensor & Bias()

Return: Mutable reference to the bias tensor.

function Bias¶

inline const Tensor & Bias() const

Return: Const reference to the bias tensor.

function InFeatures¶

inline int64_t InFeatures() const

Return: Number of input features.

function OutFeatures¶

inline int64_t OutFeatures() const

Return: Number of output features.

function HasBias¶

inline bool HasBias() const

Return: true when the layer has a bias term.

function Name¶

inline virtual std::string Name() const override

Return: "Linear".

Reimplements: tenzr::nn::Module::Name

function Create¶

template <typename T  =float>
static inline Linear Create(
    int64_t in_features,
    int64_t out_features,
    bool use_bias =true,
    std::optional< uint64_t > seed =std::nullopt
)

Static factory mirroring the templated constructor.