DP-GEN Manual

Table of Contents

• DP-GEN Manual
  • Table of Contents
  • About DP-GEN
    • Highlighted features
    • Code structure and interface
    • License and credits
  • Download and Install
  • Init: Preparing Initial Data
    • Init_bulk
    • Init_surf
  • Run: Main Process of Generator
  • Test: Auto-test for Deep Generator
  • Set up machine
  • Troubleshooting
  • License

About DP-GEN

DP-GEN (Deep Generator) is a software written in Python, delicately designed to generate a deep learning based model of interatomic potential energy and force field. DP-GEN is dependent on DeepMD-kit. With highly scalable interface with common softwares for molecular simulation, DP-GEN is capable to automatically prepare scripts and maintain job queues on HPC machines (High Performance Cluster) and analyze results.

If you use this software in any publication, please cite:

Yuzhi Zhang, Haidi Wang, Weijie Chen, Jinzhe Zeng, Linfeng Zhang, Han Wang, and Weinan E, DP-GEN: A concurrent learning platform for the generation of reliable deep learning based potential energy models, Computer Physics Communications, 2020, 107206.

Highlighted features

• Accurate and efficient: DP-GEN is capable to sample more than tens of million structures and select only a few for first principles calculation. DP-GEN will finally obtain a uniformly accurate model.
• User-friendly and automatic: Users may install and run DP-GEN easily. Once succusefully running, DP-GEN can dispatch and handle all jobs on HPCs, and thus there's no need for any personal effort.
• Highly scalable: With modularized code structures, users and developers can easily extend DP-GEN for their most relevant needs. DP-GEN currently supports for HPC systems (Slurm, PBS, LSF and cloud machines ), Deep Potential interface with DeePMD-kit, MD interface with LAMMPS, Gromacs and ab-initio calculation interface with VASP, PWSCF, CP2K, SIESTA and Gaussian, Abacus, PWMAT, etc . We're sincerely welcome and embraced to users' contributions, with more possibilities and cases to use DP-GEN.

Code structure and interface

• dpgen:

  • data: source codes for preparing initial data of bulk and surf systems.

  • generator: source codes for main process of deep generator.

  • auto_test : source code for undertaking materials property analysis.

  • remote and dispatcher : source code for automatically submiting scripts,maintaining job queues and collecting results. Notice this part hase been integrated into dpdispatcher

  • database : source code for collecting data generated by DP-GEN and interface with database.

• examples : providing example JSON files.

• tests : unittest tools for developers.

One can easily run DP-GEN with :

dpgen TASK PARAM MACHINE

where TASK is the key word, PARAM and MACHINE are both JSON files.

Options for TASK:

• init_bulk : Generating initial data for bulk systems.
• init_surf : Generating initial data for surface systems.
• run : Main process of Deep Generator.
• test: Auto-test for Deep Potential.
• db: Collecting data from DP-GEN.

Here are examples you can refer to. You should make sure that provide a correct JSON file. You can use following command to check your JSON file.

import json
#Specify machine parameters in machine.json
json.load(open("machine.json"))

Download and Install

One can download the source code of dpgen by

git clone https://github.com/deepmodeling/dpgen.git

then you may install DP-GEN easily by:

cd dpgen
pip install --user .

With this command, the dpgen executable is install to $HOME/.local/bin/dpgen. You may want to export the PATH by

export PATH=$HOME/.local/bin:$PATH

To test if the installation is successful, you may execute

dpgen -h

Init: Preparing Initial Data

Init_bulk

You may prepare initial data for bulk systems with VASP by:

dpgen init_bulk PARAM [MACHINE]

The MACHINE configure file is optional. If this parameter exists, then the optimization tasks or MD tasks will be submitted automatically according to MACHINE.json.

Basically init_bulk can be devided into four parts , denoted as stages in PARAM:

1. Relax in folder 00.place_ele
2. Pertub and scale in folder 01.scale_pert
3. Run a shor AIMD in folder 02.md
4. Collect data in folder 02.md.

All stages must be in order. One doesn't need to run all stages. For example, you may run stage 1 and 2, generating supercells as starting point of exploration in dpgen run.

If MACHINE is None, there should be only one stage in stages. Corresponding tasks will be generated, but user's intervention should be involved in, to manunally run the scripts.

Following is an example for PARAM, which generates data from a typical structure hcp.

{
    "stages" : [1,2,3,4],
    "cell_type":    "hcp",
    "latt":     4.479,
    "super_cell":   [2, 2, 2],
    "elements":     ["Mg"],
    "potcars":      ["....../POTCAR"],
    "relax_incar": "....../INCAR_metal_rlx",
    "md_incar" : "....../INCAR_metal_md",
    "scale":        [1.00],
    "skip_relax":   false,
    "pert_numb":    2,
    "md_nstep" : 5,
    "pert_box":     0.03,
    "pert_atom":    0.01,
    "coll_ndata":   5000,
    "type_map" : [ "Mg", "Al"],
    "_comment":     "that's all"
}

If you want to specify a structure as starting point for init_bulk, you may set in PARAM as follows.

"from_poscar":	true,
"from_poscar_path":	"....../C_mp-47_conventional.POSCAR",

init_bulk support both VASP and ABACUS for first-principle calculation. You can choose the software by specifying the key init_fp_style. If init_fp_style is not specified, the default software will be VASP.

When using ABACUS for init_fp_style, the keys of the paths of INPUT files for relaxation and MD simulations are the same as INCAR for VASP, which are relax_incar and md_incar respectively. You have to additionally specify relax_kspacing and md_kspacing for k points spacing, and dpgen will automatically generate KPT files according to them. You may also use relax_kpt and md_kpt instead of them for the relative path for KPT files of relaxation and MD simulations. However, either relax_kspacing and md_kspacing, or relax_kpt and md_kpt is needed. If from_poscar is set to false, you have to specify atom_masses in the same order as elements.

The following table gives explicit descriptions on keys in PARAM.

The bold notation of key (such as Elements) means that it's a necessary key.

Key	Type	Example	Discription
stages	List of Integer	[1,2,3,4]	Stages for init_bulk
Elements	List of String	["Mg"]	Atom types
cell_type	String	"hcp"	Specifying which typical structure to be generated. Options include fcc, hcp, bcc, sc, diamond.
latt	Float	4.479	Lattice constant for single cell.
from_poscar	Boolean	True	Deciding whether to use a given poscar as the beginning of relaxation. If it's true, keys (cell_type, latt) will be aborted. Otherwise, these two keys are necessary.
from_poscar_path	String	"....../C_mp-47_conventional.POSCAR"	Path of POSCAR for VASP or STRU for ABACUS. Necessary if from_poscar is true.
relax_incar	String	"....../INCAR"	Path of INCAR for VASP or INPUT for ABACUS for relaxation in VASP. Necessary if stages include 1.
md_incar	String	"....../INCAR"	Path of INCAR for VASP or INPUT for ABACUS for MD in VASP. Necessary if stages include 3.
scale	List of float	[0.980, 1.000, 1.020]	Scales for transforming cells.
skip_relax	Boolean	False	If it's true, you may directly run stage 2 (pertub and scale) using an unrelaxed POSCAR.
pert_numb	Integer	30	Number of pertubations for each POSCAR.
pert_box	Float	0.03	Percentage of Perturbation for cells.
pert_atom	Float	0.01	Pertubation of each atoms (Angstrom).
md_nstep	Integer	10	Steps of AIMD in stage 3. If it's not equal to settings via NSW in md_incar, DP-GEN will follow NSW.
coll_ndata	Integer	5000	Maximal number of collected data.
type_map	List	[ "Mg", "Al"]	The indices of elements in deepmd formats will be set in this order.
init_fp_style	String	"ABACUS" or "VASP"	First-principle software. If this key is abscent, the default value will be "VASP".
relax_kpt	String	"....../KPT"	Path of KPT file for relaxation in stage 1. Only useful if init_fp_style is "ABACUS".
relax_kspacing	Integer or List of 3 integers	10	kspacing parameter for relaxation in stage 1. Only useful if init_fp_style is "ABACUS".
md_kpt	String	"....../KPT"	Path of KPT file for MD simulations in stage 3. Only useful if init_fp_style is "ABACUS".
md_kspacing	Integer or List of 3 integers	10	kspacing parameter for MD simulations in stage 3. Only useful if init_fp_style is "ABACUS".
atom_masses	List of float	[24]	List of atomic masses of elements. The order should be the same as Elements. Only useful if init_fp_style is "ABACUS".

Init_surf

You may prepare initial data for surface systems with VASP by:

dpgen init_surf PARAM [MACHINE]

The MACHINE configure file is optional. If this parameter exists, then the optimization tasks or MD tasks will be submitted automatically according to MACHINE.json.

Basically init_surf can be devided into two parts , denoted as stages in PARAM:

1. Build specific surface in folder 00.place_ele
2. Pertub and scale in folder 01.scale_pert

All stages must be in order.

Following is an example for PARAM, which generates data from a typical structure hcp.

{
  "stages": [
    1,
    2
  ],
  "cell_type": "fcc",
  "latt": 4.034,
  "super_cell": [
    2,
    2,
    2
  ],
  "layer_numb": 3,
  "vacuum_max": 9,
  "vacuum_resol": [
    0.5,
    1
  ],
  "mid_point": 4.0,
  "millers": [
    [
      1,
      0,
      0
    ],
    [
      1,
      1,
      0
    ],
    [
      1,
      1,
      1
    ]
  ],
  "elements": [
    "Al"
  ],
  "potcars": [
    "....../POTCAR"
  ],
  "relax_incar": "....../INCAR_metal_rlx_low",
  "scale": [
    1.0
  ],
  "skip_relax": true,
  "pert_numb": 2,
  "pert_box": 0.03,
  "pert_atom": 0.01,
  "_comment": "that's all"
}

Another example is from_poscar method. Here you need to specify the POSCAR file.

{
  "stages": [
    1,
    2
  ],
  "cell_type": "fcc",
  "from_poscar":	true,
  "from_poscar_path":	"POSCAR",
  "super_cell": [
    1,
    1,
    1
  ],
  "layer_numb": 3,
  "vacuum_max": 5,
  "vacuum_resol": [0.5,2],
  "mid_point": 2.0,
  "millers": [
    [
      1,
      0,
      0
    ]
  ],
  "elements": [
    "Al"
  ],
  "potcars": [
    "./POTCAR"
  ],
  "relax_incar" : "INCAR_metal_rlx_low",
  "scale": [
    1.0
  ],
  "skip_relax": true,
  "pert_numb": 5,
  "pert_box": 0.03,
  "pert_atom": 0.01,
  "coll_ndata": 5000,
  "_comment": "that's all"
}

The following table gives explicit descriptions on keys in PARAM.

The bold notation of key (such as Elements) means that it's a necessary key.

Key	Type	Example	Discription
stages	List of Integer	[1,2,3,4]	Stages for init_surf
Elements	List of String	["Mg"]	Atom types
cell_type	String	"hcp"	Specifying which typical structure to be generated. Options include fcc, hcp, bcc, sc, diamond.
latt	Float	4.479	Lattice constant for single cell.
layer_numb	Integer	3	Number of equavilent layers of slab.
z__min	Float	9.0	Thickness of slab without vacuum (Angstrom). If the layer_numb and z_min are all setted, the z_min value will be ignored.
vacuum_max	Float	9	Maximal thickness of vacuum (Angstrom).
vacuum_min	Float	3.0	Minimal thickness of vacuum (Angstrom). Default value is 2 times atomic radius.
vacuum_resol	List of float	[0.5, 1 ]	Interval of thichness of vacuum. If size of vacuum_resol is 1, the interval is fixed to its value. If size of vacuum_resol is 2, the interval is vacuum_resol[0] before mid_point, otherwise vacuum_resol[1] after mid_point.
millers	List of list of Integer	[[1,0,0]]	Miller indices.
relax_incar	String	"....../INCAR"	Path of INCAR for relaxation in VASP. Necessary if stages include 1.
scale	List of float	[0.980, 1.000, 1.020]	Scales for transforming cells.
skip_relax	Boolean	False	If it's true, you may directly run stage 2 (pertub and scale) using an unrelaxed POSCAR.
pert_numb	Integer	30	Number of pertubations for each POSCAR.
pert_box	Float	0.03	Percentage of Perturbation for cells.
pert_atom	Float	0.01	Pertubation of each atoms (Angstrom).
coll_ndata	Integer	5000	Maximal number of collected data.

Run: Main Process of Generator

You may call the main process by: dpgen run PARAM MACHINE.

The whole process of generator will contain a series of iterations, succussively undertaken in order such as heating the system to certain temperature.

In each iteration, there are three stages of work, namely, 00.train 01.model_devi 02.fp.

• 00.train: DP-GEN will train several (default 4) models based on initial and generated data. The only difference between these models is the random seed for neural network initialization.

• 01.model_devi : represent for model-deviation. Model-deviation engine in 01.model_devi can be chosen between Molecular Dynamics(LAMMPS and GROMACS) or Structures Prediction(CALYPSO). DP-GEN will use models obtained from 00.train to run Molecular Dynamics or to run structure optimization with ASE in CALYPSO. Larger deviation for structure properties (default is force of atoms) means less accuracy of the models. Using this criterion, a few structures will be selected and put into next stage 02.fp for more accurate calculation based on First Principles.

• 02.fp : Selected structures will be calculated by first principles methods(default VASP). DP-GEN will obtain some new data and put them together with initial data and data generated in previous iterations. After that a new training will be set up and DP-GEN will enter next iteration!

DP-GEN identifies the current stage by a record file, record.dpgen, which will be created and upgraded by codes.Each line contains two number: the first is index of iteration, and the second ,ranging from 0 to 9 ,records which stage in each iteration is currently running.

0,1,2 correspond to make_train, run_train, post_train. DP-GEN will write scripts in make_train, run the task by specific machine in run_train and collect result in post_train. The records for model_devi and fp stage follow similar rules.

In PARAM, you can specialize the task as you expect.

{
  "type_map": [
    "H",
    "C"
  ],
  "mass_map": [
    1,
    12
  ],
  "init_data_prefix": "....../init/",
  "init_data_sys": [
    "CH4.POSCAR.01x01x01/02.md/sys-0004-0001/deepmd"
  ],

  "sys_configs_prefix": "....../init/",
  "sys_configs": [
    [
      "CH4.POSCAR.01x01x01/01.scale_pert/sys-0004-0001/scale*/00000*/POSCAR"
    ],
    [
      "CH4.POSCAR.01x01x01/01.scale_pert/sys-0004-0001/scale*/00001*/POSCAR"
    ]
  ],
 
  "_comment": " that's all ",
  "numb_models": 4,
  "default_training_param": {
     "model": {
            "type_map": [
                "H",
                "C"
            ],
            "descriptor": {
                "type": "se_a",
                "sel": [
                    16,
                    4
                ],
                "rcut_smth": 0.5,
                "rcut": 5,
                "neuron": [
                    120,
                    120,
                    120
                ],
                "resnet_dt": true,
                "axis_neuron": 12,
                "seed": 1
            },
            "fitting_net": {
                "neuron": [
                    25,
                    50,
                    100
                ],
                "resnet_dt": false,
                "seed": 1
            }
        },
        "learning_rate": {
            "type": "exp",
            "start_lr": 0.001,
            "decay_steps": 100,
            "decay_rate": 0.95
        },
        "loss": {
            "start_pref_e": 0.02,
            "limit_pref_e": 2,
            "start_pref_f": 1000,
            "limit_pref_f": 1,
            "start_pref_v": 0.0,
            "limit_pref_v": 0.0
        },
        "training": {
            "set_prefix": "set",
            "stop_batch": 2000,
            "batch_size": 1,
            "disp_file": "lcurve.out",
            "disp_freq": 1000,
            "numb_test": 4,
            "save_freq": 1000,
            "save_ckpt": "model.ckpt",
            "load_ckpt": "model.ckpt",
            "disp_training": true,
            "time_training": true,
            "profiling": false,
            "profiling_file": "timeline.json",
            "_comment": "that's all"
        }
  },
  "model_devi_dt": 0.002,
  "model_devi_skip": 0,
  "model_devi_f_trust_lo": 0.05,
  "model_devi_f_trust_hi": 0.15,
  "model_devi_clean_traj": true,
  "model_devi_jobs": [
    {
      "sys_idx": [
        0
      ],
      "temps": [
        100
      ],
      "press": [
        1.0
      ],
      "trj_freq": 10,
      "nsteps": 300,
      "ensemble": "nvt",
      "_idx": "00"
    },
    {
      "sys_idx": [
        1
      ],
      "temps": [
        100
      ],
      "press": [
        1.0
      ],
      "trj_freq": 10,
      "nsteps": 3000,
      "ensemble": "nvt",
      "_idx": "01"
    }
  ],
  "fp_style": "vasp",
  "shuffle_poscar": false,
  "fp_task_max": 20,
  "fp_task_min": 1,
  "fp_pp_path": "....../methane/",
  "fp_pp_files": [
    "POTCAR"
  ],
  "fp_incar": "....../INCAR_methane"
}

The following table gives explicit descriptions on keys in PARAM.

The bold notation of key (such aas type_map) means that it's a necessary key.

Key	Type	Example	Discription
#Basics
type_map	List of string	["H", "C"]	Atom types
mass_map	List of float	[1, 12]	Standard atom weights.
use_ele_temp	int	0	Currently only support fp_style vasp. 0(default): no electron temperature. 1: eletron temperature as frame parameter. 2: electron temperature as atom parameter.
#Data
init_data_prefix	String	"/sharedext4/.../data/"	Prefix of initial data directories
init_data_sys	List of string	["CH4.POSCAR.01x01x01/.../deepmd"]	Directories of initial data. You may use either absolute or relative path here. Systems will be detected recursively in the directories.
sys_format	String	"vasp/poscar"	Format of initial data. It will be vasp/poscar if not set.
init_batch_size	String of integer	[8]	Each number is the batch_size of corresponding system for training in init_data_sys. One recommended rule for setting the sys_batch_size and init_batch_size is that batch_size mutiply number of atoms ot the stucture should be larger than 32. If set to auto, batch size will be 32 divided by number of atoms.
sys_configs_prefix	String	"/sharedext4/.../data/"	Prefix of sys_configs
sys_configs	List of list of string	[ ["/sharedext4/.../POSCAR"], ["....../POSCAR"] ]	Containing directories of structures to be explored in iterations.Wildcard characters are supported here.
sys_batch_size	List of integer	[8, 8]	Each number is the batch_size for training of corresponding system in sys_configs. If set to auto, batch size will be 32 divided by number of atoms.
#Training
numb_models	Integer	4 (recommend)	Number of models to be trained in 00.train.
training_iter0_model_path	list of string	["/path/to/model0_ckpt/", ...]	The model used to init the first iter training. Number of element should be equal to numb_models
training_init_model	bool	False	Iteration > 0, the model parameters will be initilized from the model trained at the previous iteration. Iteration == 0, the model parameters will be initialized from training_iter0_model_path.
default_training_param	Dict		Training parameters for deepmd-kit in 00.train. You can find instructions from here: (https://github.com/deepmodeling/deepmd-kit)..
dp_compress	bool	false	Use dp compress to compress the model. Default is false.
#Exploration
model_devi_dt	Float	0.002 (recommend)	Timestep for MD
model_devi_skip	Integer	0	Number of structures skipped for fp in each MD
model_devi_f_trust_lo	Float or List of float or Dict[str, float]	0.05	Lower bound of forces for the selection. If List, should be set for each index in sys_configs, respectively.
model_devi_f_trust_hi	Float or List of float or Dict[str, float]	0.15	Upper bound of forces for the selection. If List, should be set for each index in sys_configs, respectively.
model_devi_v_trust_lo	Float or List of float or Dict[str, float]	1e10	Lower bound of virial for the selection. If List, should be set for each index in sys_configs, respectively. Should be used with DeePMD-kit v2.x.
model_devi_v_trust_hi	Float or List of float or Dict[str, float]	1e10	Upper bound of virial for the selection. If List, should be set for each index in sys_configs, respectively. Should be used with DeePMD-kit v2.x.
model_devi_adapt_trust_lo	Boolean	False	Adaptively determines the lower trust levels of force and virial. This option should be used together with model_devi_numb_candi_f, model_devi_numb_candi_v and optionally with model_devi_perc_candi_f and model_devi_perc_candi_v. dpgen will make two sets: 1. From the frames with force model deviation lower than model_devi_f_trust_hi, select max(model_devi_numb_candi_f, model_devi_perc_candi_f*n_frames) frames with largest force model deviation. 2. From the frames with virial model deviation lower than model_devi_v_trust_hi, select max(model_devi_numb_candi_v, model_devi_perc_candi_v*n_frames) frames with largest virial model deviation. The union of the two sets is made as candidate dataset
model_devi_numb_candi_f	Int	10	See model_devi_adapt_trust_lo.
model_devi_numb_candi_v	Int	0	See model_devi_adapt_trust_lo.
model_devi_perc_candi_f	Float	0.0	See model_devi_adapt_trust_lo.
model_devi_perc_candi_v	Float	0.0	See model_devi_adapt_trust_lo.
model_devi_f_avg_relative	Boolean	False	Normalized the force model deviations by the RMS force magnitude along the trajectory. This key should not be used with use_relative.
model_devi_clean_traj	Boolean or Int	true	If type of model_devi_clean_traj is boolean type then it denote whether to clean traj folders in MD since they are too large. If it is Int type, then the most recent n iterations of traj folders will be retained, others will be removed.
model_devi_nopbc	Boolean	False	Assume open boundary condition in MD simulations.
model_devi_activation_func	List of list of string	[["tanh","tanh"],["tanh","gelu"],["gelu","tanh"],["gelu","gelu"]]	Set activation functions for models, length of the List should be the same as numb_models, and two elements in the list of string respectively assign activation functions to the embedding and fitting nets within each model. Backward compatibility: the orginal "List of String" format is still supported, where embedding and fitting nets of one model use the same activation function, and the length of the List should be the same as numb_models
model_devi_jobs	[ { "sys_idx": [0], "temps": [100], "press": [1], "trj_freq": 10, "nsteps": 1000, "ensembles": "nvt" }, ... ]	List of dict	Settings for exploration in 01.model_devi. Each dict in the list corresponds to one iteration. The index of model_devi_jobs exactly accord with index of iterations
model_devi_jobs["sys_idx"]	List of integer	[0]	Systems to be selected as the initial structure of MD and be explored. The index corresponds exactly to the sys_configs.
model_devi_jobs["temps"]	List of integer	[50, 300]	Temperature (K) in MD
model_devi_jobs["press"]	List of integer	[1,10]	Pressure (Bar) in MD
model_devi_jobs["trj_freq"]	Integer	10	Frequecy of trajectory saved in MD.
model_devi_jobs["nsteps"]	Integer	3000	Running steps of MD.
model_devi_jobs["ensembles"]	String	"nvt"	Determining which ensemble used in MD, options include “npt” and “nvt”.
model_devi_jobs["neidelay"]	Integer	"10"	delay building until this many steps since last build
model_devi_jobs["taut"]	Float	"0.1"	Coupling time of thermostat (ps)
model_devi_jobs["taup"]	Float	"0.5"	Coupling time of barostat (ps)
model_devi_jobs["model_devi_f_trust_lo"] model_devi_jobs["model_devi_f_trust_hi"] model_devi_jobs["model_devi_v_trust_lo"] model_devi_jobs["model_devi_v_trust_hi"]	Float or Dict[str, float]	See global model_devi config above like model_devi_f_trust_lo. For dict, should be set for each index in sys_idx, respectively.
#Labeling
fp_style	string	"vasp"	Software for First Principles. Options include “vasp”, “pwscf”, “siesta” and “gaussian” up to now.
fp_task_max	Integer	20	Maximum of structures to be calculated in 02.fp of each iteration.
fp_task_min	Integer	5	Minimum of structures to calculate in 02.fp of each iteration.
fp_accurate_threshold	Float	0.9999	If the accurate ratio is larger than this number, no fp calculation will be performed, i.e. fp_task_max = 0.
fp_accurate_soft_threshold	Float	0.9999	If the accurate ratio is between this number and fp_accurate_threshold, the fp_task_max linearly decays to zero.
fp_cluster_vacuum	Float	None	If the vacuum size is smaller than this value, this cluster will not be choosen for labeling
fp_style == VASP
fp_pp_path	String	"/sharedext4/.../ch4/"	Directory of psuedo-potential file to be used for 02.fp exists.
fp_pp_files	List of string	["POTCAR"]	Psuedo-potential file to be used for 02.fp. Note that the order of elements should correspond to the order in type_map.
fp_incar	String	"/sharedext4/../ch4/INCAR"	Input file for VASP. INCAR must specify KSPACING and KGAMMA.
fp_aniso_kspacing	List of integer	[1.0,1.0,1.0]	Set anisotropic kspacing. Usually useful for 1-D or 2-D materials. Only support VASP. If it is setting the KSPACING key in INCAR will be ignored.
cvasp	Boolean	true	If cvasp is true, DP-GEN will use Custodian to help control VASP calculation.
fp_style == Gaussian
use_clusters	Boolean	false	If set to true, clusters will be taken instead of the whole system. This option does not work with DeePMD-kit 0.x.
cluster_cutoff	Float	3.5	The cutoff radius of clusters if use_clusters is set to true.
fp_params	Dict		Parameters for Gaussian calculation.
fp_params["keywords"]	String or list	"mn15/6-31g** nosymm scf(maxcyc=512)"	Keywords for Gaussian input.
fp_params["multiplicity"]	Integer or String	1	Spin multiplicity for Gaussian input. If set to auto, the spin multiplicity will be detected automatically. If set to frag, the "fragment=N" method will be used.
fp_params["nproc"]	Integer	4	The number of processors for Gaussian input.
fp_style == siesta
use_clusters	Boolean	false	If set to true, clusters will be taken instead of the whole system. This option does not work with DeePMD-kit 0.x.
cluster_cutoff	Float	3.5	The cutoff radius of clusters if use_clusters is set to true.
fp_params	Dict		Parameters for siesta calculation.
fp_params["ecut"]	Integer	300	Define the plane wave cutoff for grid.
fp_params["ediff"]	Float	1e-4	Tolerance of Density Matrix.
fp_params["kspacing"]	Float	0.4	Sample factor in Brillouin zones.
fp_params["mixingweight"]	Float	0.05	Proportion a of output Density Matrix to be used for the input Density Matrix of next SCF cycle (linear mixing).
fp_params["NumberPulay"]	Integer	5	Controls the Pulay convergence accelerator.
fp_style == cp2k
user_fp_params	Dict		Parameters for cp2k calculation. find detail in manual.cp2k.org. only the kind section must be set before use. we assume that you have basic knowledge for cp2k input.
external_input_path	String		Conflict with key:user_fp_params, use the template input provided by user, some rules should be followed, read the following text in detail.
fp_style == ABACUS
user_fp_params	Dict		Parameters for ABACUS INPUT. find detail Here. If deepks_model is set, the model file should be in the pseudopotential directory. You can also set KPT file by adding k_points that corresponds to a list of six integers in this dictionary.
fp_orb_files	List		List of atomic orbital files. The files should be in pseudopotential directory.
fp_dpks_descriptor	String		DeePKS descriptor file name. The file should be in pseudopotential directory.

One can choose the model-deviation engine by specifying the key model_devi_engine. If model_devi_engine is not specified, the default model-deviation engine will be LAMMPS.

There are some new keys needed to be added into param and machine if CALYPSO as model-deviation engine.

The bold notation of key (such as calypso_path) means that it's a necessary key.

Key	Type	Example	Discription
in param file
model_devi_engine	string	"calypso"	CALYPSO as model-deviation engine.
calypso_input_path	string	"/home/zhenyu/workplace/debug"	The absolute path of CALYPSO input file named input.dat(PSTRESS and fmax should be included), when this keys exists, all the iters will use the same CALYPSO input file until reach the number of max iter specified by model_devi_max_iter and model_devi_jobs key will not work.
model_devi_max_iter	int	10	The max iter number code can run, it works when calypso_input_path exists.
model_devi_jobs	List of Dict	[{ "times":[3],"NameOfAtoms":["Al","Cu"],"NumberOfAtoms":[1,10],"NumberOfFormula":[1,2],"Volume":[300],"DistanceOfIon":[[ 1.48,1.44],[ 1.44,1.41]],"PsoRatio":[0.6],"PopSize":[5],"MaxStep":[3],"ICode":[1],"Split":"T"},...]	Settings for exploration in 01.model_devi. Different number in times List means different iteration index and iterations mentioned in List wil use same CALYPSO parameters.
model_devi_jobs["times"]	List of int	[0,1,2]	Different number in times List means different iteration index and iterations mentioned in List wil use same CALYPSO parameters.
model_devi_jobs["NameOfAtoms"]	List of string	["Al","Cu"]	Parameter of CALYPSO input file, means the element species of structures to be generated.
model_devi_jobs["NumberOfAtoms"]	List of int	[1,10]	Parameter of CALYPSO input file, means the number of atoms for each chemical species in one formula unit.
model_devi_jobs["NumberOfFormula"]	List of int	[1,2]	Parameter of CALYPSO input file, means the range of formula unit per cell.
model_devi_jobs["Volume"]	List of int	[300]	Parameter of CALYPSO input file, means the colume per formula unit(angstrom^3).
model_devi_jobs["DistanceOfIon"]	List of float	[[ 1.48,1.44],[ 1.44,1.41]]	Parameter of CALYPSO input file, means minimal distance between atoms of each chemical species. Unit is in angstrom.
model_devi_jobs["PsoRatio"]	List of float	[0.6]	Parameter of CALYPSO input file, means the proportion of the structures generated by PSO.
model_devi_jobs["PopSize"]	List of int	[5]	Parameter of CALYPSO input file, means the number of structures to be generated in one step in CALYPSO.
model_devi_jobs["MaxStep"]	List of int	[3]	Parameter of CALYPSO input file, means the number of max step in CALYPSO.
model_devi_jobs["ICode"]	List of int	[13]	Parameter of CALYPSO input file, means the chosen of local optimization, 1 is vasp and 13 is ASE with dp.
model_devi_jobs["Split"]	String	"T"	Parameter of CALYPSO input file, means that generating structures and optimizing structures are split into two parts, in dpgen workflow, Split must be T.
model_devi_jobs["PSTRESS"]	List of float	[0.001]	Same as PSTRESS in INCAR.
model_devi_jobs["fmax"]	List of float	[0.01]	The convergence criterion is that the force on all individual atoms should be less than fmax.
in machine file
model_devi["deepmdkit_python"]	String	"/home/zhenyu/soft/deepmd-kit/bin/python"	A python path with deepmd package.
model_devi["calypso_path"]	string	"/home/zhenyu/workplace/debug"	The absolute path of calypso.x.

Rules for cp2k input at dictionary form

Converting cp2k input is very simple as dictionary used to dpgen input. You just need follow some simple rule:

• kind section parameter must be provide
• replace keyword in cp2k as keyword in dict.
• replace keyword parameter in cp2k as value in dict.
• replace section name in cp2k as keyword in dict. . The corresponding value is a dict.
• repalce section parameter in cp2k as value with dict. keyword "_"
• repeat section in cp2k just need to be written once with repeat parameter as list.

If you want to use your own paramter, just write a corresponding dictionary. The COORD section will be filled by dpgen automatically, therefore do not include this in dictionary. The OT or Diagonalization section is require for semiconductor or metal system. For specific example, have a look on example directory.

Here are examples for setting:

#minimal information you should provide for input
#other we have set other parameters in code, if you want to
#use your own paramter, just write a corresponding dictionary
"user_fp_params":   {
    "FORCE_EVAL":{
        "DFT":{
            "BASIS_SET_FILE_NAME": "path",
            "POTENTIAL_FILE_NAME": "path",
            "SCF":{
                "OT":{ "keyword":"keyword parameter", "keyword2":"keyword parameter" }
            }
        }
        "SUBSYS":{
            "KIND":{
                "_": ["N","C","H"],
                "POTENTIAL": ["GTH-PBE-q5","GTH-PBE-q4", "GTH-PBE-q1"],
                "BASIS_SET": ["DZVP-MOLOPT-GTH","DZVP-MOLOPT-GTH","DZVP-MOLOPT-GTH"]
            }
        }
    }
}

Rules for use cp2k template input provided by user

See Full example template.inp and dpgen input parameter file in

tests/generator/cp2k_make_fp_files/exinput/template.inp and tests/generator/param-mgo-cp2k-exinput.json

Here is example for provide external input

    {
    "_comment":     " 02.fp ",
     "fp_style":     "cp2k",
     "shuffle_poscar":   false,
     "fp_task_max":  100,
     "fp_task_min":  10,
     "fp_pp_path":   ".",
     "fp_pp_files":  [],
     "external_input_path": "./cp2k_make_fp_files/exinput/template.inp",
     "_comment":     " that's all 
     }

the following essential section should be provided in user template

 &FORCE_EVAL
   # add this line if you need to fit virial
   STRESS_TENSOR ANALYTICAL
   &PRINT
     &FORCES ON
     &END FORCES
     # add this line if you need to fit virial
     &STRESS_TENSOR ON
     &END FORCES
   &END PRINT
   &SUBSYS
     &CELL
       ABC LEFT FOR DPGEN
     &END CELL
     &COORD
     @include coord.xyz
     &END COORD
   &END SUBSYS
&END FORCE_EVAL

Test: Auto-test for Deep Generator

configure and param.json

At this step, we assume that you have prepared some graph files like graph.*.pb and the particular pseudopotential POTCAR.

The main code of this step is

dpgen test PARAM MACHINE

where PARAM and MACHINE are both json files. MACHINE is the same as above.

The whole program contains a series of tasks shown as follows. In each task, there are three stages of work, generate, run and compute.

• 00.equi:(default task) the equilibrium state

• 01.eos: the equation of state

• 02.elastic: the elasticity like Young's module

• 03.vacancy: the vacancy formation energy

• 04.interstitial: the interstitial formation energy

• 05.surf: the surface formation energy

Dpgen auto_test will auto make dir for each task it tests, the dir name is the same as the dir name. And the test results will in a plain text file named result. For example cat ./01.eos/Al/std-fcc/deepmd/result

We take Al as an example to show the parameter settings of param.json. The first part is the fundamental setting for particular alloy system.

    "_comment": "models",
    "potcar_map" : {
	"Al" : "/somewhere/POTCAR"
    },
    "conf_dir":"confs/Al/std-fcc",
    "key_id":"API key of Material project",
    "task_type":"deepmd",
    "task":"eos",

You need to add the specified paths of necessary POTCAR files in "potcar_map". The different POTCAR paths are separated by commas. Then you also need to add the folder path of particular configuration, which contains POSCAR file.

"confs/[element or alloy]/[std-* or mp-**]"
std-*: standard structures, * can be fcc, bcc, hcp and so on.
mp-**: ** means Material id from Material Project.

Usually, if you add the relative path of POSCAR as the above format, dpgen test will check the existence of such file and automatically downloads the standard and existed configurations of the given element or alloy from Materials Project and stores them in confs folder, which needs the API key of Materials project.

• task_type contains 3 optional types for testing, i.e. vasp, deepmd and meam.
• task contains 7 options, equi, eos, elastic, vacancy, interstitial, surf and all. The option all can do all the tasks.

It is worth noting that the subsequent tasks need to rely on the calculation results of the equilibrium state, so it is necessary to give priority to the calculation of the equilibrium state while testing. And due to the stable consideration, we recommand you to test the equilibrium state of vasp before other tests.

The second part is the computational settings for vasp and lammps. According to your actual needs， you can choose to add the paths of specific INCAR or use the simplified INCAR by setting vasp_params. The priority of specified INCAR is higher than using vasp_params. The most important setting is to add the folder path model_dir of deepmd model and supply the corresponding element type map. Besides, dpgen test also is able to call common lammps packages, such as meam.

"relax_incar":"somewhere/relax_incar",
"scf_incar":"somewhere/scf_incar",
"vasp_params":	{
	"ecut":		650,
	"ediff":	1e-6,
	"kspacing":	0.1,
	"kgamma":	false,
	"npar":		1,
	"kpar":		1,
	"_comment":	" that's all "
    },
    "lammps_params":    {
        "model_dir":"somewhere/example/Al_model",
        "type_map":["Al"],
        "model_name":false,
        "model_param_type":false
    },

The last part is the optional settings for various tasks mentioned above. You can change the parameters according to actual needs.

param.json in a dictionary.

Fields	Type	Example	Discription
potcar_map	dict	{"Al": "example/POTCAR"}	a dict like { "element" : "position of POTCAR" }
conf_dir	path like string	"confs/Al/std-fcc"	the dir which contains vasp's POSCAR
key_id	string	"DZIwdXCXg1fiXXXXXX"	the API key of Material project
task_type	string	"vasp"	task type, one of deepmd vasp meam
task	string or list	"equi"	task, one or several tasks from { equi, eos, elastic, vacancy, interstitial, surf } or all stands for all tasks
vasp_params	dict	seeing below	params relating to vasp INCAR
lammps_params	dict	seeing below	params relating to lammps

The keys in param["vasp_params"] is shown below.

Fields	Type	Example	Discription
ecut	real number	650	the plane wave cutoff for grid.
ediff	real number	1e-6	Tolerance of Density Matrix
kspacing	real number	0.1	Sample factor in Brillouin zones
kgamma	boolen	false	whether generate a Gamma centered grid
npar	positive integer	1	the number of k-points that are to be treated in parallel
kpar	positive integer	1	the number of bands that are treated in parallel

the keys in param["lammps_params"].

Key	Type	Example	Discription
model_dir	path like string	"example/Al_model"	the model dir which contains .pb file
type_map	list of string	["Al"]	a list contains the element, usually useful for multiple element situation
model_name	boolean	false
model_param_type	boolean	false

auto_test tasks

00.equi

    "_comment":"00.equi",
    "store_stable":true,

• store_stable:(boolean) whether to store the stable energy and volume

param.json.

Field	Type	Example	Discription
EpA(eV)	real number	-3.7468	the potential energy of a atom
VpA(A^3)	real number	16.511	theEquilibrium volume of a atom

test results

conf_dir:        EpA(eV)  VpA(A^3)
confs/Al/std-fcc  -3.7468   16.511

Field	Type	Example	Discription
EpA(eV)	real number	-3.7468	the potential energy of a atom
VpA(A^3)	real number	16.511	theEquilibrium volume of a atom

01.eos

    "_comment": "01.eos",
    "vol_start":	12,
    "vol_end":		22,
    "vol_step":		0.5,

• vol_start, vol_end and vol_step determine the volumetric range and accuracy of the eos.

test results

conf_dir:confs/Al/std-fcc
VpA(A^3)  EpA(eV)
15.500   -3.7306
16.000   -3.7429
16.500   -3.7468
17.000   -3.7430

Field	Type	Example	Discription
EpA(eV)	list of real number	[15.5,16.0,16.5,17.0]	the potential energy of a atom in quilibrium state
VpA(A^3)	list of real number	[-3.7306, -3.7429, -3.746762, -3.7430]	the equilibrium volume of a atom

02.elastic

    "_comment": "02.elastic",
    "norm_deform":	2e-2,
    "shear_deform":	5e-2,

• norm_deform and shear_deform are the scales of material deformation. This task uses the stress-strain relationship to calculate the elastic constant.

Key	Type	Example	Discription
norm_deform	real number	0.02	uniaxial deformation range
shear_deform	real number	0.05	shear deformation range

test results

conf_dir:confs/Al/std-fcc
130.50   57.45   54.45    4.24    0.00    0.00
57.61  130.31   54.45   -4.29   -0.00   -0.00
54.48   54.48  133.32   -0.00   -0.00   -0.00
4.49   -4.02   -0.89   33.78    0.00   -0.00
-0.00   -0.00   -0.00   -0.00   33.77    4.29
0.00   -0.00   -0.00   -0.00    4.62   36.86
# Bulk   Modulus BV = 80.78 GPa
# Shear  Modulus GV = 36.07 GPa
# Youngs Modulus EV = 94.19 GPa
# Poission Ratio uV = 0.31

Field	Type	Example	Discription
elastic module(GPa)	6*6 matrix of real number	[[130.50 57.45 54.45 4.24 0.00 0.00] [57.61 130.31 54.45 -4.29 -0.00 -0.00] [54.48 54.48 133.32 -0.00 -0.00 -0.00] [4.49 -4.02 -0.89 33.78 0.00 -0.00] [-0.00 -0.00 -0.00 -0.00 33.77 4.29] [0.00 -0.00 -0.00 -0.00 4.62 36.86]]	Voigt-notation elastic module;sequence of row and column is (xx, yy, zz, yz, zx, xy)
bulk modulus(GPa)	real number	80.78	bulk modulus
shear modulus(GPa)	real number	36.07	shear modulus
Youngs Modulus(GPa)	real number	94.19	Youngs Modulus
Poission Ratio	real number	0.31	Poission Ratio

03.vacancy

    "_comment":"03.vacancy",
    "supercell":[3,3,3],

• supercell:(list of integer) the supercell size used to generate vacancy defect and interstitial defect

Key	Type	Example	Discription
supercell	list of integer	[3,3,3]	the supercell size used to generate vacancy defect and interstitial defect

test result

conf_dir:confs/Al/std-fcc
Structure:      Vac_E(eV)  E(eV) equi_E(eV)
struct-3x3x3-000:   0.859  -96.557 -97.416

Field	Type	Example	Discription
Structure	list of string	['struct-3x3x3-000']	structure name
Vac_E(eV)	real number	0.723	the vacancy formation energy
E(eV)	real number	-96.684	potential energy of the vacancy configuration
equi_E(eV)	real number	-97.407	potential energy of the equilibrium state

04.interstitial

    "_comment":"04.interstitial",
    "insert_ele":["Al"],
    "reprod-opt":false,

• insert_ele:(list of string) the elements used to generate point interstitial defect
• repord-opt:(boolean) whether to reproduce trajectories of interstitial defect

Key	Type	Example	Discription
insert_ele	list of string	["Al"]	the elements used to generate point interstitial defect
reprod-opt	boolean	false	whether to reproduce trajectories of interstitial defect

test result

conf_dir:confs/Al/std-fcc
Insert_ele-Struct: Inter_E(eV)  E(eV) equi_E(eV)
struct-Al-3x3x3-000:   3.919  -100.991 -104.909
struct-Al-3x3x3-001:   2.681  -102.229 -104.909

Field	Type	Example	Discription
Structure	string	'struct-Al-3x3x3-000'	structure name
Inter_E(eV)	real number	0.723	the interstitial formation energy
E(eV)	real number	-96.684	potential energy of the interstitial configuration
equi_E(eV)	real number	-97.407	potential energy of the equilibrium state

05.surface

    "_comment": "05.surface",
    "min_slab_size":	10,
    "min_vacuum_size":	11,
    "_comment": "pert xz to work around vasp bug...",
    "pert_xz":		0.01,
    "max_miller": 2,
    "static-opt":false,
    "relax_box":false,

• min_slab_size and min_vacuum_size are the minimum size of slab thickness and the vacuume width.
• pert_xz is the perturbation through xz direction used to compute surface energy.
• max_miller (integer) is the maximum miller index
• static-opt:(boolean) whether to use atomic relaxation to compute surface energy. if false, the structure will be relaxed.
• relax_box:(boolean) set true if the box is relaxed, otherwise only relax atom positions.

Key	Type	Example	Discription
min_slab_size	real number	10	the minimum size of slab thickness
min_vacuum_size	real number	11	the minimum size of the vacuume width
pert_xz	real number	0.01	the perturbation through xz direction used to compute surface energy
max_miller	integer	2	the maximum miller index
static-opt	boolean	false	whether to use atomic relaxation to compute surface energy. if false, the structure will be relaxed.
relax_box	boolean	false	set true if the box is relaxed, otherwise only relax atom positions

test result

conf_dir:confs/Al/std-fcc
Miller_Indices:         Surf_E(J/m^2) EpA(eV) equi_EpA(eV)
struct-000-m1.1.1m:        0.673     -3.628   -3.747
struct-001-m2.2.1m:        0.917     -3.592   -3.747

Field	Type	Example	Discription
Miller_Indices	string	struct-000-m1.1.1m	Miller Indices
Surf_E(J/m^2)	real number	0.673	the surface formation energy
EpA(eV)	real number	-3.628	potential energy of the surface configuration
equi_EpA	real number	-3.747	potential energy of the equilibrium state

The content of the auto_test

To know what actually will dpgen autotest do, including the lammps and vasp script, the input file and atom configuration file auto_test will generate, please refer to https://hackmd.io/@yeql5ephQLaGJGgFgpvIDw/rJY1FO92B

Simplify

When you have a dataset containing lots of repeated data, this step will help you simplify your dataset. The workflow contains three stages: train, model_devi, and fp. The train stage and the fp stage are as the same as the run step, and the model_devi stage will calculate model deviations of the rest data that has not been confirmed accurate. Data with small model deviations will be confirmed accurate, while the program will pick data from those with large model deviations to the new dataset.

Use the following script to start the workflow:

dpgen simplify param.json machine.json

Here is an example of param.json for QM7 dataset:

{
    "type_map": [
        "C",
        "H",
        "N",
        "O",
        "S"
    ],
    "mass_map": [
        12.011,
        1.008,
        14.007,
        15.999,
        32.065
    ],
    "pick_data": "/scratch/jz748/simplify/qm7",
    "init_data_prefix": "",
    "init_data_sys": [],
    "sys_batch_size": [
        "auto"
    ],
    "numb_models": 4,
    "default_training_param": {
        "model": {
            "type_map": [
                "C",
                "H",
                "N",
                "O",
                "S"
            ],
            "descriptor": {
                "type": "se_a",
                "sel": [
                    7,
                    16,
                    3,
                    3,
                    1
                ],
                "rcut_smth": 1.00,
                "rcut": 6.00,
                "neuron": [
                    25,
                    50,
                    100
                ],
                "resnet_dt": false,
                "axis_neuron": 12
            },
            "fitting_net": {
                "neuron": [
                    240,
                    240,
                    240
                ],
                "resnet_dt": true
            }
        },
        "learning_rate": {
            "type": "exp",
            "start_lr": 0.001,
            "decay_steps": 10,
            "decay_rate": 0.99
        },
        "loss": {
            "start_pref_e": 0.02,
            "limit_pref_e": 1,
            "start_pref_f": 1000,
            "limit_pref_f": 1,
            "start_pref_v": 0,
            "limit_pref_v": 0,
            "start_pref_pf": 0,
            "limit_pref_pf": 0
        },
        "training": {
            "set_prefix": "set",
            "stop_batch": 10000,
            "disp_file": "lcurve.out",
            "disp_freq": 1000,
            "numb_test": 1,
            "save_freq": 1000,
            "save_ckpt": "model.ckpt",
            "load_ckpt": "model.ckpt",
            "disp_training": true,
            "time_training": true,
            "profiling": false,
            "profiling_file": "timeline.json"
        },
        "_comment": "that's all"
    },
    "fp_style": "gaussian",
    "shuffle_poscar": false,
    "fp_task_max": 1000,
    "fp_task_min": 10,
    "fp_pp_path": "/home/jzzeng/",
    "fp_pp_files": [],
    "fp_params": {
        "keywords": "mn15/6-31g** force nosymm scf(maxcyc=512)",
        "nproc": 28,
        "multiplicity": 1,
        "_comment": " that's all "
    },
    "init_pick_number":100,
    "iter_pick_number":100,
    "e_trust_lo":1e10,
    "e_trust_hi":1e10,
    "f_trust_lo":0.25,
    "f_trust_hi":0.45,
    "_comment": " that's all "
}

Here pick_data is the directory to data to simplify where the program recursively detects systems System with deepmd/npy format. init_pick_number and iter_pick_number are the numbers of picked frames. e_trust_lo, e_trust_hi mean the range of the deviation of the frame energy, and f_trust_lo and f_trust_hi mean the range of the max deviation of atomic forces in a frame. fp_style can only be gaussian currently. Other parameters are as the same as those of generator.

Set up machine

new dpdispatcher update note

dpdispatcher Update Note: dpdispatcher has updated and the api of machine.json is changed. dpgen will use new dpdispatcher if the key api_version in dpgen's machine.json's value is equal or large than 1.0.

And dpgen will use old dpdispatcher if the key api_version is not specified in machine.json or the api_version is smaller than 1.0. This gurantees that the old machine.jsons still work.

And for now dpdispatcher is maintained on a seperate repo. The repo link: https://github.com/deepmodeling/dpdispatcher

The api of new dpdispatcher is close to old one except for a few changes.

The new machine.json examples can be seen here

And Here are the explanations of the keys in machine resources.

Here is a example machine.json for dpgen's new dpdispatcher. Please check the documents for more information about new dpdispatcher.

an example of new dpgen's machine.json

{
  "api_version": "1.0",
  "train":
    {
      "command": "dp",
      "machine": {
        "batch_type": "PBS",
        "context_type": "SSHContext",
        "local_root": "./",
        "remote_root": "/home/user1234/work_path_dpdispatcher_test",
        "remote_profile": {
            "hostname": "39.xxx.xx.xx",
            "username": "user1234"
        }
      },
      "resources": {
        "number_node": 1,
        "cpu_per_node": 4,
        "gpu_per_node": 1,
        "queue_name": "T4_4_15",
        "group_size": 1,
        "custom_flags":["#SBATCH --mem=32G"],
        "strategy": {"if_cuda_multi_devices": true},
        "para_deg": 3,
        "source_list": ["/home/user1234/deepmd.1.2.4.env"]
      }
    },
  "model_devi":
    {
      "command": "lmp",
      "machine":{
        "batch_type": "PBS",
        "context_type": "SSHContext",
        "local_root": "./",
        "remote_root": "/home/user1234/work_path_dpdispatcher_test",
        "remote_profile": {
          "hostname": "39.xxx.xx.xx",
          "username": "user1234"
        }
      },
      "resources": {
        "number_node": 1,
        "cpu_per_node": 4,
        "gpu_per_node": 1,
        "queue_name": "T4_4_15",
        "group_size": 5,
        "source_list": ["/home/user1234/deepmd.1.2.4.env"]
      }
    },
  "fp":
    {
      "command": "vasp_std",
      "machine":{
        "batch_type": "PBS",
        "context_type": "SSHContext",
        "local_root": "./",
        "remote_root": "/home/user1234/work_path_dpdispatcher_test",
        "remote_profile": {
          "hostname": "39.xxx.xx.xx",
          "username": "user1234"
        }
      },
      "resources": {
        "number_node": 1,
        "cpu_per_node": 32,
        "gpu_per_node": 0,
        "queue_name": "G_32_128",
        "group_size": 1,
        "source_list": ["~/vasp.env"]
      }
    }
}

note1: the key "local_root" in dpgen's machine.json is always ./

old dpdispatcher

When switching into a new machine, you may modifying the MACHINE, according to the actual circumstance. Once you have finished, the MACHINE can be re-used for any DP-GEN tasks without any extra efforts.

An example for MACHINE is:

{
  "train":
    {
      "machine": {
        "batch": "slurm",
        "hostname": "localhost",
        "port": 22,
        "username": "Angus",
        "work_path": "....../work"
      },
      "resources": {
        "numb_node": 1,
        "numb_gpu": 1,
        "task_per_node": 4,
        "partition": "AdminGPU",
        "exclude_list": [],
        "source_list": [
          "....../train_tf112_float.env"
        ],
        "module_list": [],
        "time_limit": "23:0:0",
        "qos": "data"
      },
      "command": "USERPATH/dp"
    },
  "model_devi":
    {
      "machine": {
        "batch": "slurm",
        "hostname": "localhost",
        "port": 22,
        "username": "Angus",
        "work_path": "....../work"
      },
      "resources": {
        "numb_node": 1,
        "numb_gpu": 1,
        "task_per_node": 2,
        "partition": "AdminGPU",
        "exclude_list": [],
        "source_list": [
          "......./lmp_tf112_float.env"
        ],
        "module_list": [],
        "time_limit": "23:0:0",
        "qos": "data"
      },
      "command": "lmp_serial",
      "group_size": 1
    },
  "fp":
    {
      "machine": {
        "batch": "slurm",
        "hostname": "localhost",
        "port": 22,
        "username": "Angus",
        "work_path": "....../work"
      },
      "resources": {
        "task_per_node": 4,
        "numb_gpu": 1,
        "exclude_list": [],
        "with_mpi": false,
        "source_list": [],
        "module_list": [
          "mpich/3.2.1-intel-2017.1",
          "vasp/5.4.4-intel-2017.1",
          "cuda/10.1"
        ],
        "time_limit": "120:0:0",
        "partition": "AdminGPU",
        "_comment": "that's All"
      },
      "command": "vasp_gpu",
      "group_size": 1
    }
}

Following table illustrates which key is needed for three types of machine: train,model_devi and fp. Each of them is a list of dicts. Each dict can be considered as an independent environmnet for calculation.

Key	train	model_devi	fp
machine	NEED	NEED	NEED
resources	NEED	NEED	NEED
command	NEED	NEED	NEED
group_size	NEED	NEED	NEED

The following table gives explicit descriptions on keys in param.json.

Key	Type	Example	Discription
machine	Dict		Settings of the machine for TASK.
resources	Dict		Resources needed for calculation.
# Followings are keys in resources
numb_node	Integer	1	Node count required for the job
task_per_node	Integer	4	Number of CPU cores required
numb_gpu	Integer	Integer	4
manual_cuda_devices	Interger	1	Used with key "manual_cuda_multiplicity" specify the gpu number
manual_cuda_multiplicity	Interger	5	Used in 01.model_devi,used with key "manual_cuda_devices" specify the MD program number running on one GPU at the same time,dpgen will automatically allocate MD jobs on different GPU. This can improve GPU usage for GPU like V100.
node_cpu	Integer	4	Only for LSF. The number of CPU cores on each node that should be allocated to the job.
new_lsf_gpu	Boolean	false	Only for LSF. Control whether new syntax of GPU to be enabled. If enabled, DP-GEN will generate line like #BSUB -gpu num=1:mode=shared:j_exclusive=yes in job submission script. Only support LSF>=10.1.0.3, and LSB_GPU_NEW_SYNTAX=Y should be set. Default: false.
exclusive	Boolean	false	Only for LSF, and only take effect when new_lsf_gpu enabled. Control whether enable j_exclusive during running. Default: false.
source_list	List of string	"....../vasp.env"	Environment needed for certain job. For example, if "env" is in the list, 'source env' will be written in the script.
module_list	List of string	[ "Intel/2018", "Anaconda3"]	For example, If "Intel/2018" is in the list, "module load Intel/2018" will be written in the script.
partition	String	"AdminGPU"	Partition / queue in which to run the job.
time_limit	String (time format)	23:00:00	Maximal time permitted for the job
mem_limit	Interger	16	Maximal memory permitted to apply for the job.
with_mpi	Boolean	true	Deciding whether to use mpi for calculation. If it's true and machine type is Slurm, "srun" will be prefixed to command in the script.
qos	"string"	"bigdata"	Deciding priority, dependent on particular settings of your HPC.
allow_failure	Boolean	false	Allow the command to return a non-zero exit code.
# End of resources
command	String	"lmp_serial"	Executable path of software, such as lmp_serial, lmp_mpi and vasp_gpu, vasp_std, etc.
group_size	Integer	5	DP-GEN will put these jobs together in one submitting script.
user_forward_files	List of str	["/path_to/vdw_kernel.bindat"]	These files will be uploaded in each calculation task. You should make sure provide the path exists.
user_backward_files	List of str	["HILLS"]	Besides DP-GEN's normal output, these files will be downloaded after each calculation. You should make sure these files can be generated.

Troubleshooting

1. The most common problem is whether two settings correspond with each other, including:

   • The order of elements in type_map and mass_map and fp_pp_files.
   • Size of init_data_sys and init_batch_size.
   • Size of sys_configs and sys_batch_size.
   • Size of sel_a and actual types of atoms in your system.
   • Index of sys_configs and sys_idx

2. Please verify the directories of sys_configs. If there isnt's any POSCAR for 01.model_devi in one iteration, it may happen that you write the false path of sys_configs.

3. Correct format of JSON file.

4. In 02.fp, total cores you require through task_per_node should be devided by npar times kpar.

5. The frames of one system should be larger than batch_size and numb_test in default_training_param. It happens that one iteration adds only a few structures and causes error in next iteration's training. In this condition, you may let fp_task_min be larger than numb_test.

License

The project dpgen is licensed under GNU LGPLv3.0.