esolver_dp.cpp File Reference

Implementation of ESolver_DP class for DeePMD method. More...

#include "esolver_dp.h"
#include "source_base/parallel_common.h"
#include "source_base/timer.h"
#include "source_io/output_log.h"
#include "source_io/cif_io.h"
#include <iomanip>
#include <sstream>
#include <unordered_map>

Include dependency graph for esolver_dp.cpp:

Detailed Description

Implementation of ESolver_DP class for DeePMD method.

#include "source_io/module_parameter/parameter.h"

This file contains the implementation of the ESolver_DP class, which is used for solving the energy and forces in a Deep Potential Molecular Dynamics (DeePMD) simulation. DeePMD is a method for training deep neural networks to accurately predict the potential energy surface of a molecular system.

For more information about DeePMD, see the following reference:

Han Wang, Linfeng Zhang, Jiequn Han, and Roberto Car. "DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics," Computer Physics Communications 228, 178-184 (2018). https://doi.org/10.1016/j.cpc.2018.03.016

Author

YuLiu98

Date

2023-05-15