pulsatrix/api/sgd__optimizer_8hpp_source.html

#pragma once


#include "pulsatrix/module.hpp"


namespace pulsatrix {


class SGDOptimizer {

public:

    explicit SGDOptimizer(float learning_rate) : learning_rate_(learning_rate) {}


    void step(Module& module);


    void zero_grad(Module& module);


private:

    float learning_rate_;

};


}  // namespace pulsatrix

pulsatrix::Module
Base class for every layer type (LinearModule, Conv2DModule, activations, ...).
Definition module.hpp:58

pulsatrix::SGDOptimizer
param -= learning_rate * grad, per parameter, for every parameter a Module exposes.
Definition sgd_optimizer.hpp:12

pulsatrix::SGDOptimizer::SGDOptimizer
SGDOptimizer(float learning_rate)
Constructs an SGD optimizer.
Definition sgd_optimizer.hpp:18

pulsatrix::SGDOptimizer::step
void step(Module &module)
Applies one SGD update to every parameter the module exposes.

pulsatrix::SGDOptimizer::zero_grad
void zero_grad(Module &module)
Resets every parameter's gradient to zero.

module.hpp
Abstract base every layer subclasses – NVI forward(), pure-virtual LRP contract.

pulsatrix
Definition acquisition_functions.hpp:16