Data

Tools

Indexes

Applications

Experiments

Open Source Science

Recent Releases of dpgen

dpgen - v0.13.2

What's Changed

New features

  • feat: add support for flexible multiplicity in CP2K inputs by @SchrodingersCattt in https://github.com/deepmodeling/dpgen/pull/1785
  • feat: enhanced sys check when adding to allsys by @SchrodingersCattt in https://github.com/deepmodeling/dpgen/pull/1787

Bugfixes

  • fix(init_bulk): include the last perturbation in collected vasp data by @njzjz in https://github.com/deepmodeling/dpgen/pull/1748
  • Update param-ch4.json by @robinzyb in https://github.com/deepmodeling/dpgen/pull/1752
  • abacus: fix bug in makeabacusscf_stru by @pxlxingliang in https://github.com/deepmodeling/dpgen/pull/1755
  • fix: remove duplicated reading model deviation files by @njzjz in https://github.com/deepmodeling/dpgen/pull/1762
  • Update shuffle_poscar feature in run.py by @ztzkz in https://github.com/deepmodeling/dpgen/pull/1730

New Contributors

  • @SchrodingersCattt made their first contribution in https://github.com/deepmodeling/dpgen/pull/1785
  • @ztzkz made their first contribution in https://github.com/deepmodeling/dpgen/pull/1730

Full Changelog: https://github.com/deepmodeling/dpgen/compare/v0.13.1...v0.13.2

- Python
Published by njzjz 7 months ago

dpgen - v0.13.1

What's Changed

Bugfixes

  • Fix: ignore UP031 by @wanghan-iapcm in https://github.com/deepmodeling/dpgen/pull/1683
  • fix: bump the upper bound of deepmd version by @njzjz in https://github.com/deepmodeling/dpgen/pull/1691
  • fix bug in reading abacus stru by @pxlxingliang in https://github.com/deepmodeling/dpgen/pull/1714 and https://github.com/deepmodeling/dpgen/pull/1720

Full Changelog: https://github.com/deepmodeling/dpgen/compare/v0.13.0...v0.13.1

- Python
Published by njzjz about 1 year ago

dpgen - v0.13.0

Highlights

DP-GEN v0.13.0 adds the support for multiple backends introduced in DeePMD-kit v3.0.0, via train_backend option (set to tensorflow or pytorch).

What's Changed

New features

  • add option to select backends TF/PT by @thangckt in https://github.com/deepmodeling/dpgen/pull/1545
    • feat: support jax backend (although the JAX training hasn't been supported by DeePMD-kit) by @njzjz in https://github.com/deepmodeling/dpgen/pull/1671
  • Modify the postfpcp2k function to generate multisystem data. Allows to run different system at one single iteration model_devi step. by @dulinhan in https://github.com/deepmodeling/dpgen/pull/1513
  • support fparam in lmp template by @mingzhong15 in https://github.com/deepmodeling/dpgen/pull/1662

Enhancement

  • remove conda directory since not being maintained by @njzjz in https://github.com/deepmodeling/dpgen/pull/1516
  • feat(build): Add Git archives version files by @njzjz-bot in https://github.com/deepmodeling/dpgen/pull/1517
  • fix broken test by @njzjz in https://github.com/deepmodeling/dpgen/pull/1538
  • Simplify API version validation by @thangckt in https://github.com/deepmodeling/dpgen/pull/1556
  • chore: add the mlp_engine option by @njzjz in https://github.com/deepmodeling/dpgen/pull/1576
  • chore: ban module-level import of pymatgen by @njzjz in https://github.com/deepmodeling/dpgen/pull/1597
  • Improve function pert_scaled by @thangckt in https://github.com/deepmodeling/dpgen/pull/1563

Bugfix

  • Change default deepmd_version and make the screen output complete by @scott-5 in https://github.com/deepmodeling/dpgen/pull/1641
  • avoid syntax warning for "{" and "}" by @Yi-FanLi in https://github.com/deepmodeling/dpgen/pull/1539
  • fix pre-commit errors by @njzjz in https://github.com/deepmodeling/dpgen/pull/1540
  • fix: hard-coded model name in gromacs model devi calculation by @wanghan-iapcm in https://github.com/deepmodeling/dpgen/pull/1544
  • fix: fix SyntaxWarning: invalid escape sequence by @njzjz in https://github.com/deepmodeling/dpgen/pull/1550
  • Fix exception message by @wanghan-iapcm in https://github.com/deepmodeling/dpgen/pull/1554
  • fix: remove ref-names from .git_archival.txt by @njzjz-bot in https://github.com/deepmodeling/dpgen/pull/1578
  • fix: fix typo in run_train by @njzjz in https://github.com/deepmodeling/dpgen/pull/1581
  • fix: fix dtype of keywords_high_multiplicity by @njzjz in https://github.com/deepmodeling/dpgen/pull/1582
  • fix: skip setting seed when descriptor/fitting_net doesn't exist by @njzjz in https://github.com/deepmodeling/dpgen/pull/1584
  • fix: fix checkpoint filename for the PyTorch backend by @njzjz in https://github.com/deepmodeling/dpgen/pull/1585
  • fix: fix UnboundLocalError in _select_by_model_devi_standard by @njzjz in https://github.com/deepmodeling/dpgen/pull/1587
  • fix: fix PyTorch model extension in simplify by @njzjz in https://github.com/deepmodeling/dpgen/pull/1596
  • fix: support shuffle_poscar for other formats by @njzjz in https://github.com/deepmodeling/dpgen/pull/1610
  • solve Path error on Windows by @thangckt in https://github.com/deepmodeling/dpgen/pull/1627
  • fix: UT bug exposed by upgraded dpdata by @wanghan-iapcm in https://github.com/deepmodeling/dpgen/pull/1636
  • fix: compare pwscf energy by relative error by @wanghan-iapcm in https://github.com/deepmodeling/dpgen/pull/1643

Documentation

  • docs: setup uv for readthedocs by @njzjz in https://github.com/deepmodeling/dpgen/pull/1524
  • docs: remove set_prefix by @njzjz in https://github.com/deepmodeling/dpgen/pull/1537
  • docs: pin sphinx-argparse to < 0.5.0 by @njzjz-bot in https://github.com/deepmodeling/dpgen/pull/1591
  • docs(deps): pin sphinx_rtd_theme to >=0.6 by @njzjz in https://github.com/deepmodeling/dpgen/pull/1615
  • docs: update DeepModeling URLs by @njzjz-bot in https://github.com/deepmodeling/dpgen/pull/1637
  • docs: replace sphinx-rtd-theme with sphinx-book-theme by @njzjz-bot in https://github.com/deepmodeling/dpgen/pull/1657

CI/CD

  • ci: setup uv by @njzjz in https://github.com/deepmodeling/dpgen/pull/1522
  • ci: test against numpy v2 by @njzjz in https://github.com/deepmodeling/dpgen/pull/1614
  • ci: bump pymatgen-analysis-defects and skip failed tests by @njzjz in https://github.com/deepmodeling/dpgen/pull/1659
  • chore: skip failed tests by @njzjz in https://github.com/deepmodeling/dpgen/pull/1670

Dependency updates

  • build(deps): bump actions/checkout from 2 to 4 by @dependabot in https://github.com/deepmodeling/dpgen/pull/1509
  • build(deps): bump actions/setup-python from 2 to 5 by @dependabot in https://github.com/deepmodeling/dpgen/pull/1508
  • build(deps): bump codecov/codecov-action from 4 to 5 by @dependabot in https://github.com/deepmodeling/dpgen/pull/1673

New Contributors

  • @dependabot made their first contribution in https://github.com/deepmodeling/dpgen/pull/1509
  • @dulinhan made their first contribution in https://github.com/deepmodeling/dpgen/pull/1513
  • @thangckt made their first contribution in https://github.com/deepmodeling/dpgen/pull/1545
  • @scott-5 made their first contribution in https://github.com/deepmodeling/dpgen/pull/1641
  • @mingzhong15 made their first contribution in https://github.com/deepmodeling/dpgen/pull/1662

Full Changelog: https://github.com/deepmodeling/dpgen/compare/v0.12.1...v0.13.0

- Python
Published by njzjz over 1 year ago

dpgen - v0.12.1

What's Changed

Breaking change

  • breaking: use shlex.quote to quote shell commands by @njzjz in https://github.com/deepmodeling/dpgen/pull/1396 Single quotes (') can be automatically escaped. One does not need to escape single quotes in command manually anymore. To those who have escaped single quotes in command manually, this is a breaking change.

Enhancement

  • exclude docs and tests from sdist by @njzjz in https://github.com/deepmodeling/dpgen/pull/1385
  • tests: add UT for runmodeldevi by @njzjz in https://github.com/deepmodeling/dpgen/pull/1386
  • throw error if trainingiter0model_path is not found by @njzjz in https://github.com/deepmodeling/dpgen/pull/1391
  • pwscf: write floaing point number for atomic masses by @Yi-FanLi in https://github.com/deepmodeling/dpgen/pull/1387
  • model devi: download LAMMPS log files for pimd by @Yi-FanLi in https://github.com/deepmodeling/dpgen/pull/1406
  • only log the current iteration when restarting by @njzjz in https://github.com/deepmodeling/dpgen/pull/1420
  • support collecting MultiSystems by @njzjz in https://github.com/deepmodeling/dpgen/pull/1422
  • keep original model_devi.out files for pimd by @Yi-FanLi in https://github.com/deepmodeling/dpgen/pull/1472

Documentation

  • docs: add links to external documentation by @njzjz in https://github.com/deepmodeling/dpgen/pull/1392
  • docs: add the link for how to setup the conda environment by @njzjz in https://github.com/deepmodeling/dpgen/pull/1484
  • fp: add document and example for Quantum Espresso by @Yi-FanLi in https://github.com/deepmodeling/dpgen/pull/1405
  • dpgen simplify: add document for fp style pwscf by @Yi-FanLi in https://github.com/deepmodeling/dpgen/pull/1413

CI/CD

  • CI: Setup Dependabot for GitHub Actions by @njzjz-bot in https://github.com/deepmodeling/dpgen/pull/1492
  • CI: Bump codecov/codecov-action from v3 to v4 by @njzjz-bot in https://github.com/deepmodeling/dpgen/pull/1491

Bugfix

  • Fix UTs destroyed by pymatgen's update by @Yi-FanLi in https://github.com/deepmodeling/dpgen/pull/1471
  • Bugfix for pimd: sorting model_devi files by @Yi-FanLi in https://github.com/deepmodeling/dpgen/pull/1470
  • issue1475: a small bug of iterdict (generator/lib/cp2k.py) by @yohsama in https://github.com/deepmodeling/dpgen/pull/1476

New Contributors

  • @yohsama made their first contribution in https://github.com/deepmodeling/dpgen/pull/1476
  • @njzjz-bot made their first contribution in https://github.com/deepmodeling/dpgen/pull/1492

Full Changelog: https://github.com/deepmodeling/dpgen/compare/v0.12.0...v0.12.1

- Python
Published by njzjz almost 2 years ago

dpgen - v0.12.0

Breaking Changes

  • drop Python 3.8 support by @njzjz in https://github.com/deepmodeling/dpgen/pull/1264
  • breaking: remove default values for training reuse arguments by @njzjz in https://github.com/deepmodeling/dpgen/pull/1330

New features

  • add dptrainskipneighborstat argument by @njzjz in https://github.com/deepmodeling/dpgen/pull/1179
  • support mixed:N batch size by @njzjz in https://github.com/deepmodeling/dpgen/pull/1183
  • support oneh5 for simplify modeldevi step by @njzjz in https://github.com/deepmodeling/dpgen/pull/1185
  • simplify: allow initial models trained by initial data by @njzjz in https://github.com/deepmodeling/dpgen/pull/1201
  • support automatic trainingreuseold_ratio by @njzjz in https://github.com/deepmodeling/dpgen/pull/1209
  • split makefp and share `makefp_calculation` between run and simplify by @njzjz in https://github.com/deepmodeling/dpgen/pull/1235
  • add fp_style custom by @njzjz in https://github.com/deepmodeling/dpgen/pull/1244
  • simplify: support model deviation of energy per atom by @njzjz in https://github.com/deepmodeling/dpgen/pull/1312
  • simplify: support using true error as error indicator by @njzjz in https://github.com/deepmodeling/dpgen/pull/1321
  • dprc: add restart_from_iter option by @njzjz in https://github.com/deepmodeling/dpgen/pull/1322
  • support electronic tempeture data used in simplify; refactor postfpvasp by @njzjz in https://github.com/deepmodeling/dpgen/pull/1329
  • support training with -f or -t argument by @njzjz in https://github.com/deepmodeling/dpgen/pull/1340
  • Add dpgui entry point and dpgen gui CLI by @njzjz in https://github.com/deepmodeling/dpgen/pull/1349
  • model_devi: add support for pimd by @Yi-FanLi in https://github.com/deepmodeling/dpgen/pull/1366

Enhancement

  • refactor(abacus): modify poscar2stru in auto_test.lib.abacus by @pxlxingliang in https://github.com/deepmodeling/dpgen/pull/1193
  • simplify: improve performance of selecting frames by @njzjz in https://github.com/deepmodeling/dpgen/pull/1202
  • Use getglobalnumberofatoms() instead by @njzjz in https://github.com/deepmodeling/dpgen/pull/1256
  • load files according to filename suffix by @njzjz in https://github.com/deepmodeling/dpgen/pull/1255
  • check arguments with 2D lists by @njzjz in https://github.com/deepmodeling/dpgen/pull/1258
  • throw RuntimeError if no system is found by expandsysstr by @njzjz in https://github.com/deepmodeling/dpgen/pull/1292
  • rm old files when performing dp model-devi by @njzjz in https://github.com/deepmodeling/dpgen/pull/1332
  • argcheck: restrict the type of elements in a list by @njzjz in https://github.com/deepmodeling/dpgen/pull/1364
  • Update {Elastic,run,surf,Vasp,vasp}.py: To be compatible with Pymatgen by @ZhouXY-PKU in https://github.com/deepmodeling/dpgen/pull/1302

Bugfixes

  • fix(abacus): fix deepks bug in autotest by @pxlxingliang in https://github.com/deepmodeling/dpgen/pull/1163
  • fix(abacus): get ION step by searching "ION=" in relax job by @pxlxingliang in https://github.com/deepmodeling/dpgen/pull/1169
  • fix a bug in convert_training_data_to_hdf5 by @njzjz in https://github.com/deepmodeling/dpgen/pull/1167
  • fix batch size for simplify by @njzjz in https://github.com/deepmodeling/dpgen/pull/1184
  • fix(abacus): Compatibility with kspacing set to 3 values by @pxlxingliang in https://github.com/deepmodeling/dpgen/pull/1197
  • simplify: do not symlink if the file does not exist by @njzjz in https://github.com/deepmodeling/dpgen/pull/1191
  • Fix the numerical mismatch for 02.fp/task/cp2k_output after update dpdata by @robinzyb in https://github.com/deepmodeling/dpgen/pull/1219
  • fix(abacus): put pp/orb/dpks files to folder pporb in 02fp. by @pxlxingliang in https://github.com/deepmodeling/dpgen/pull/1214
  • fix bug in makesupercellabacus by @Liu-RX in https://github.com/deepmodeling/dpgen/pull/1212 and https://github.com/deepmodeling/dpgen/pull/1229
  • len(allsys) should > 0 for postfp_cp2k by @robinzyb in https://github.com/deepmodeling/dpgen/pull/1245
  • fix a typo in newtoold_ratio message by @njzjz in https://github.com/deepmodeling/dpgen/pull/1270
  • fix a bug in the number of frames for auto ratio by @njzjz in https://github.com/deepmodeling/dpgen/pull/1276
  • Using dict.get methods to get machine.local_root by @dingzhaohan in https://github.com/deepmodeling/dpgen/pull/1287
  • fix KeyError in init_reaction by @njzjz in https://github.com/deepmodeling/dpgen/pull/1352
  • fix Python 3.12 compatibility by @njzjz in https://github.com/deepmodeling/dpgen/pull/1367
  • abacus: fix bug of finding the final relax STRU by @pxlxingliang in https://github.com/deepmodeling/dpgen/pull/1344

Documentation

  • fix the links of DP-GUI by @njzjz in https://github.com/deepmodeling/dpgen/pull/1187
  • change size and apply dark mode for the logo by @njzjz in https://github.com/deepmodeling/dpgen/pull/1190
  • extend the doc of cp2k externalinputpath in detail by @robinzyb in https://github.com/deepmodeling/dpgen/pull/1225
  • fix: description in README.md by @cherushui in https://github.com/deepmodeling/dpgen/pull/1241
  • docs: move ratio_failed out of fp variant by @njzjz in https://github.com/deepmodeling/dpgen/pull/1243
  • docs: fix docs for fptaskmin by @njzjz in https://github.com/deepmodeling/dpgen/pull/1257
  • update deepmd input to v2; format JSON files by @njzjz in https://github.com/deepmodeling/dpgen/pull/1315
  • update issue templates by @njzjz in https://github.com/deepmodeling/dpgen/pull/1368
  • docs: update installation documentation by @njzjz in https://github.com/deepmodeling/dpgen/pull/1372

CI/CD

  • bump pymatgen to a stable version by @njzjz in https://github.com/deepmodeling/dpgen/pull/1186
  • bypass the upstream pymatgen error for CI by @njzjz in https://github.com/deepmodeling/dpgen/pull/1233
  • bump pymatgen to 2023.5.31 by @njzjz in https://github.com/deepmodeling/dpgen/pull/1250
  • use OIDC to publish packages by @njzjz in https://github.com/deepmodeling/dpgen/pull/1298
  • test: pin pymatgen-analysis-defects to <2023.08.22 by @njzjz in https://github.com/deepmodeling/dpgen/pull/1313
  • skip Sphinx 7.2.5 by @njzjz in https://github.com/deepmodeling/dpgen/pull/1324

Lint

  • apply ruff rules and fix lots of bugs by @njzjz in https://github.com/deepmodeling/dpgen/pull/1240
  • move to ruff formatter by @njzjz in https://github.com/deepmodeling/dpgen/pull/1375

New Contributors

  • @pre-commit-ci made their first contribution in https://github.com/deepmodeling/dpgen/pull/1171
  • @ZhouXY-PKU made their first contribution in https://github.com/deepmodeling/dpgen/pull/1302
  • @Yi-FanLi made their first contribution in https://github.com/deepmodeling/dpgen/pull/1366

Full Changelog: https://github.com/deepmodeling/dpgen/compare/v0.11.1...v0.12.0

- Python
Published by njzjz over 2 years ago

dpgen - v0.11.1

Breaking changes:

  • breaking: remove old dispatcher by @njzjz in https://github.com/deepmodeling/dpgen/pull/1097

Enhancements:

  • Add parameter 'srtabfilepath' so that one can use DP-ZBL potential successfully by @Chengqian-Zhang in https://github.com/deepmodeling/dpgen/pull/918
  • Refactor: remove association between ABACUS/STRU and the element number in param.json by @pxlxingliang in https://github.com/deepmodeling/dpgen/pull/1076
  • choose numbsteps/stopbatch automatically by @njzjz in https://github.com/deepmodeling/dpgen/pull/1086
  • replace distutils.version.LooseVersion by packaging.version.Version by @njzjz in https://github.com/deepmodeling/dpgen/pull/1095
  • Support forward files for simplify by @HuangJiameng in https://github.com/deepmodeling/dpgen/pull/1092
  • Replace "python3" in command by sys.executable by @HuangJiameng in https://github.com/deepmodeling/dpgen/pull/1105
  • add an option to merge data to one H5 file by @njzjz in https://github.com/deepmodeling/dpgen/pull/1119
  • add and run pre-commit to format codes by @njzjz in https://github.com/deepmodeling/dpgen/pull/1124
  • refactor(abacus): link the pp/orb files defined in STRU not jdata by @pxlxingliang in https://github.com/deepmodeling/dpgen/pull/1127
  • Raise warnings if there is no system in the path listed in sys_configs by @HuangJiameng in https://github.com/deepmodeling/dpgen/pull/1130
  • Updated the revise_lmp_input_dump function. by @panxiang126 in https://github.com/deepmodeling/dpgen/pull/1137
  • add isort to sort imports by @njzjz in https://github.com/deepmodeling/dpgen/pull/1133
  • always pass codecov status by @njzjz in https://github.com/deepmodeling/dpgen/pull/1157

Documentation, argument parsing and examples

  • add placeholders for variants by @njzjz in https://github.com/deepmodeling/dpgen/pull/1068
  • Doc(abacus): modify the description of parameters by @pxlxingliang in https://github.com/deepmodeling/dpgen/pull/1080
  • fix doc: "structures" should be a list by @HuangJiameng in https://github.com/deepmodeling/dpgen/pull/1091
  • docs: add logo to docs and README by @njzjz in https://github.com/deepmodeling/dpgen/pull/1128
  • docs: add links to DP-GUI by @njzjz in https://github.com/deepmodeling/dpgen/pull/1131

Bug fixings:

  • Fix: remove the reading of ntype when treating ABACUS related info by @pxlxingliang in https://github.com/deepmodeling/dpgen/pull/1075
  • fix pass action by @njzjz in https://github.com/deepmodeling/dpgen/pull/1082
  • fix compatibility with NumPy and pymatgen by @njzjz in https://github.com/deepmodeling/dpgen/pull/1085
  • Fix(abacus): parse orbital information after parsing of INPUT by @pxlxingliang in https://github.com/deepmodeling/dpgen/pull/1079
  • fix_bug simplify.py by @Vibsteamer in https://github.com/deepmodeling/dpgen/pull/1113
  • fix_bug simplify.py by @Vibsteamer in https://github.com/deepmodeling/dpgen/pull/1114
  • fix compatibility with the latest pymatgen by @njzjz in https://github.com/deepmodeling/dpgen/pull/1126
  • fix restart trajectory for merge_traj by @wankiwi in https://github.com/deepmodeling/dpgen/pull/1111
  • fix a bug in makeabacusrelax by @maki49 in https://github.com/deepmodeling/dpgen/pull/1150
  • fix(abacus): do not write to deepmd raw/npy, if no abacus data in postfpabacus_scf() by @pxlxingliang in https://github.com/deepmodeling/dpgen/pull/1153
  • bug_fix reproduce.py by @Vibsteamer in https://github.com/deepmodeling/dpgen/pull/1156
  • fix numpydoc styles by @njzjz in https://github.com/deepmodeling/dpgen/pull/1134

New Contributors

  • @wankiwi made their first contribution in https://github.com/deepmodeling/dpgen/pull/1111

Full Changelog: https://github.com/deepmodeling/dpgen/compare/v0.11.0...v0.11.1

- Python
Published by AnguseZhang almost 3 years ago

dpgen - v0.11.0

Breaking changes:

  • bump requires-python to >=3.8 (#1014)

New features:

  • gamma line calculation for bcc and fcc systems (#801)
  • support several CALYPSO run in different pressure in one iteration (#814)
  • autotest: add the interface of ABACUS in autotest (#834)
  • support merge_traj for lammps (#838 #961 )
  • support HDF5 files as initial data system (#973)
  • simplify: support list for pick_data (#994)

Enhancements:

  • refactor: delete relaxkspacing and mdkspacing in abacus init step (#848)
  • check runtasks before submission in runmdmodeldevi (#854 )
  • UT: add UT for createdisturbabacus_dev (#852)
  • Automatically set the relative atomic mass according to "type_map" (#867 #893)
  • add tests to check machine files (#874)
  • UT: update testdisturbabacus.py (#879)
  • add an error remind in dpgen_fp when NSW is not set to 1 (#903)
  • move some imports into runtime functions (#894)
  • support forward files for init_surf (#909)
  • fp: check failed tasks (#882)
  • remove requirements.txt (#948)
  • migrate from setup.py to pyproject.toml (#995)
  • _crd2frag: use OB native PBC implementation (#1006)
  • skip mirror gitee when organization is not deepmodeling (#1048)
  • add pass step to GitHub Actions (#1058)

Documentation, argument parsing and examples

  • args: ensembles -> ensemble (#805)
  • args: model_devi_v_trust_lo and model_devi_v_trust_hi are optional (#804)
  • removed model_devi_e_trust_lo and model_devi_e_trust_hi, which have been removed in #79 (#807)
  • args: add shuffle_poscar to run jdata (#806)
  • fix readme and qm7.json (#817)
  • args: trust level for modeldevijob should be optional (#818)
  • args: modeldevinopbc should be optional (#819)
  • args: fp_aniso_kspacing and cvasp should be optional (#820)
  • args: add entire training parameters (#829)
  • add entire arguments of gaussian style (#830)
  • fix deprecated bare pair_coeff (#831)
  • UT checks examples (#821 #870 )
  • change 'dpgen test' to 'dpgen autotest' (#875)
  • args: remove duplicated argument (#839)
  • update abacus input parameters (#836)
  • update the type of fp_aniso_kspacing as List of float (#843)
  • document: add the information of ABACUS in arginfo.fp_style_variant_type_args (#845)
  • add DP-GEN Structure.md to doc (#844)
  • doc: add FAQs (#856)
  • remove documentation for old dispatcher (#862)
  • add dargs to install_requires (#863)
  • example: add abacus examples (#853)
  • update run/dp2.x-lammps-cp2k example (#864)
  • add simplify example of MAPbI3-scan based on lebesgue (#840)
  • docs: add authors section for credits (#869)
  • docs: add init surf (#890 #904)
  • docs: ddd a Troubleshooting.md file (#888)
  • docs: user guide (#876)
  • docs: add numpydoc; set proper info (#895)
  • exampledp2.xlmp_gaussian (#887)
  • docs: update common-errors.md (#897)
  • fix typos and optimize autotest part in README (#899)
  • add DPRc (modeldeviengine amber and fp_style amber/diff) arguments (#911)
  • update simplify doucment (#912)
  • add init-bulk in dpgen documents (#907)
  • docs: clarify the usage of skiprelax in initsurf (#929)
  • docs: optimize autotest document based on #891 (#923)
  • manage TOC of DPGEN's document (#932)
  • add publication link to docs (#939)
  • move ch4 folder to examples directory (#949)
  • fix the description of fp_task (#950)
  • loose check dpgen run jdata (#952)
  • optimize document and error report based on FAQs (#967)
  • remove personal info in dp2.x-lammps-gaussian example (#972)
  • args: add init_bulk_jdata_arginfo and init_surf_jdata_arginfo (#936)
  • strict check simplify jdata (#951)
  • fix : autotest relaxation TOC (#982)
  • merge run-process.rst to index.rst (#966)
  • docs: add links to keys (#981)
  • docs: initsurf forwardfiles (#1025)
  • refactor readme and remove some duplicated contents (#946)
  • add arguments for lammps revise_template (#1015)
  • docs: add information about Python requirements (#1060)

Bug fixings:

  • fix postfpvasp and makefpconfigs for simplify (#803 )
  • fix UT testmakemd (#812)
  • fix bug of matrix multiply in create_disturbs_abacus_dev (#815)
  • set typemap for MultiSystems in modeldevi step (#825)
  • test: using assertEqual to compare two value in test_vasp.py (#828)
  • autotest: delete the redundant print in test_vasp.py (#835)
  • fix bug of no funding fp_params (#842)
  • fix a bug in runabacusmd and delete redundant line about gamma_only. (#850)
  • fix: incorrect using of range in auto_test/lib/abacus.py (#884)
  • fix: autotest: equistress should have the same unit as stress (#910)
  • fix: skip celltype if fromposcar is True in init_bulk (#930)
  • fix: fix forwardfiles for mergetraj in runmdmodel_devi (#947)
  • remove _link_fp_vasp_pp from make_fp_gaussian (#971)
  • fix incompatibility of autotest module with latest pymatgen>2022.7.19 (#963)
  • fix: modify the reading of parameter 'fpdpksdescriptor' in run.py (#989)
  • CVE-2007-4559 Patch (#990)
  • fix ImportError (#1001)
  • python3.10 support: collection.Mapping -> collection.abc.Mapping (#1020)
  • check data instead of tasks (#1031)
  • assign type_map for all systems (#1033)
  • fix codecov (#1034)
  • ignore dpdata 0.2.11 (#1062)

Full Changelog: https://github.com/deepmodeling/dpgen/compare/v0.10.6...v0.11.0

- Python
Published by wanghan-iapcm about 3 years ago

dpgen - v0.10.6

New features:

  • add DPRc implementation by @njzjz in https://github.com/deepmodeling/dpgen/pull/729

Enhancements:

  • add link to DP-GUI by @njzjz in https://github.com/deepmodeling/dpgen/pull/724
  • add many docs and examples by @njzjz in https://github.com/deepmodeling/dpgen/pull/736 , https://github.com/deepmodeling/dpgen/pull/758 , https://github.com/deepmodeling/dpgen/pull/751 , https://github.com/deepmodeling/dpgen/pull/759 , https://github.com/deepmodeling/dpgen/pull/762 , https://github.com/deepmodeling/dpgen/pull/747 , https://github.com/deepmodeling/dpgen/pull/788 , https://github.com/deepmodeling/dpgen/pull/787
  • refactor simplify by @njzjz in https://github.com/deepmodeling/dpgen/pull/730
  • supports non-list mdata by @njzjz in https://github.com/deepmodeling/dpgen/pull/748
  • Create Performing the Run process.md by @LiangWenshuo1118 in https://github.com/deepmodeling/dpgen/pull/714
  • upgrade all tasks to dpdispatcher by @njzjz in https://github.com/deepmodeling/dpgen/pull/749 , https://github.com/deepmodeling/dpgen/pull/755
  • update: add a new option of absolute volume in /dpgen/dpgen/auto_test/EOS.py by @HuangJiameng in https://github.com/deepmodeling/dpgen/pull/741
  • remove train_param from examples, which was deprecated in #68 by @njzjz in https://github.com/deepmodeling/dpgen/pull/789
  • Add netcdf4 dependency to conda recipe by @AnguseZhang in https://github.com/deepmodeling/dpgen/pull/792

Bug fixings:

  • fix a bug in makeabacusscf_input by @Liu-RX in https://github.com/deepmodeling/dpgen/pull/754
  • correct the wrong spelling of 'failure' by @HuangJiameng in https://github.com/deepmodeling/dpgen/pull/764
  • fix ‘postfpcp2k’, add param rfailed by @HuangJiameng in https://github.com/deepmodeling/dpgen/pull/765
  • Fix simplify by @HuangJiameng in https://github.com/deepmodeling/dpgen/pull/767 , https://github.com/deepmodeling/dpgen/pull/768
  • fix ZeroDivisionError raised by run.py by @HuangJiameng in https://github.com/deepmodeling/dpgen/pull/769
  • fix bug for sysidx dependent trust level and add option for modeldevi_job by @Cloudac7 in https://github.com/deepmodeling/dpgen/pull/786

New Contributors

  • @HuangJiameng made their first contribution in https://github.com/deepmodeling/dpgen/pull/741

Full Changelog: https://github.com/deepmodeling/dpgen/compare/v0.10.5...v0.10.6

- Python
Published by AnguseZhang over 3 years ago

dpgen - v0.10.5

Breaking changes: - ABACUS versions < 2.2 are not supported anymore.

New features: - support Calypso structure search in the exploration stage (#663) - add bcc interstitial calculation in autotest (#696) - Add ABACUS/lcao deepks interface to dpgen init and run, upgrade to support ABACUS >= 2.2. (#705)

Enhancements: - change some default parameters in lmp when doing autotest (#696) - batch replace 'except:' with 'except Exception:' (#703) - doc: dpgen run machine parameters (#710) - Delete information printed by dpgen -h to enable pip install dpgen (#718)

Bug fixings: - Update paramCH4deepmd-kit-2.0.1.json (#694) - Fix the usage of pair_coeff in auto_test (#696 #698) - Fix QE pwscf AssertionError (#685)

- Python
Published by amcadmus almost 4 years ago

dpgen - v0.10.4

New features: - Added ABACUS pw interface for dpgen init_bulk (#590)

Improvements: - Add minimize step with fix 1 all box/relax tri 0.0 to autotest/relax step (#631) - Update simplify.py for api > 1.0, and fix multi-suffixes bug . (#670) - Make Autotest compatible with the new version of dpdispatcher. (#667) - Add deepmodeling banner to doc (#688) - Set the seed of type_embedding network (#689)

Bug fixings: - Bug introduced by pr#611 (#626) - Add convert_mdata definition to fix simplify bug. (#634) - Fix cp2k post fp numerical mismatch (#644) - pwscf gamma sampling; fix the conflict between loc_frame descriptor and automatic sel label generation (#650)

- Python
Published by amcadmus almost 4 years ago

dpgen - v0.10.3

New features: - support dp compress (#607) - Adapt different trust level for different sys_configs (#609)

Enhancement: - Several enhancement in gromacs engine (#553) - autotest: run relaxation tasks in parallel (#573) - update abacus-scf generator (#575) - add lebesgue ch4 example (#571) - modeldeviclean_traj support int type (#583) - add a citation badge (#589) - bump dpdata version to 0.2.4 (#595) - change compress level to 6 from default 9 to accelerate compress (#593)

Bug fixings: - Update gen.py | compatibility with VASP (#529) - bugfix | initbulk | stages 3 | lost the last pert-dir in stages 2 (#530) - ssh: archieve files the symlink points to instead of symlink iteself (#552) - Change mv to cp when downloading softlinks. (#562) - fix the usage of pair_coeff (#567) - Fix examples in INCARmd and POTCAR (#570) - fix dispatcher bugs in autotest run (#568) - autotest: fix early return and result checking (#574) - autotest: rename task directory to avoid false result in a rerun (#572) - Fix bug in makesubmission of Auto-test (#577) - Add ase, custodian, GromacsWrapper in conda packages. (#578) - remove jr.json to allow rerun in autotest make (#579) - will convert localroot's './' to abspath to avoid hash conflict in new dpdispatcher (#582) - fix bug issue: #597 (#598) - initbulk: skip relax if skiprelax is true (#594) - bugfix | to support multi-element cases (#608) - bugfix | typo in setting default KSPACING (#611) - modeldevi | sort models in default&support user-defined order (#610)

- Python
Published by amcadmus about 4 years ago

dpgen - v0.10.2

Bug fixing: - fix typo in github actions release to conda #524

- Python
Published by amcadmus over 4 years ago

dpgen - v0.10.1

New features: - Allow user defined forwardcommonfiles and backward_files (#482) - Adaptive trust levels (#495) - Support relative force model deviation by normalizing the RMS force magnitude (#496)

Enhancement: - Update gromacs model devi engine #493 - add delete_apg interface in dpgen/dispatcher/ALI.py #519

Bug fixings: - fix bug with 1-dim modeldeviactivationfunc (#484) - exclude no converged task for cp2k fp (#486) - rename `nneurontoneuron` (#492) - delete dump.0.xyz in backforward file #498 - cant get groupsize in older ALI-Dispatcher #520

- Python
Published by amcadmus over 4 years ago

dpgen - v0.10.0

New features: - Support gromacs in model deviation (#427) - Support DeePMD-kit v2 (#420) - Added ABACUS interface for first principle calculations (#433) - Allow assigning different activation functions to embedding and fitting nets (#461)

Enhancement - Remove the support for deepmd-kit v0.x (#397 ) - Support for new dpdispatcher (#449) - Example machine file for 4 GPUs on a local machine (#400 #412 ) - Better error message in too many failed FP jobs (#428 ) - Slurm customized flags (#368 ) - ssh session is not active (#382 ) - Retry slurm commands when failing (#381 ) - Store sftp and reduce the frequency of opening sftp (#387 ) - Taskwise restart for manual cuda device (#383 ) - Add Cu's init_surf examples. (#406) - Add input files of enhanced sampling method (#446) - Update CP2K new example and slurm-lsf-mix machine (#456)

Bug fixings: - PBS error message (#396 ) - Bug inter_type in autotest Lammps support (#423 ) - Bug in autotest multicomponent surface systems (#378 ) - Too long argument list for tar command (#380 ) - force overwrite when using gzip (#384 ) - MPI execute error (#405 ) - Support hybrid descriptor (fix #458) (#459) - Fix parameter error for LSF GPU tasks (#463) - Fix NSW value in INCAR; fix local_root check (#464)

- Python
Published by amcadmus over 4 years ago

dpgen - v0.9.2

Bug fixing: - stop printing pytmatgen.__version__ that is not supported by version 2022

- Python
Published by amcadmus almost 5 years ago

dpgen - v0.9.1

Bug fixing: - Solve the comparability issue of the pymatgen v2022.0.* #358

- Python
Published by amcadmus almost 5 years ago

dpgen - v0.9.0

New feature: - New autotest

Improvement: - Improve support for batch systems #303 #313 #337 #341 #352 - Support different template settings for different systems #328 #346 - Support cp2k template #348 - Support restarting in lammps #335 #336

Bug fixings - #332 #334 #340 #342 #343 #344 #345

- Python
Published by amcadmus about 5 years ago

dpgen - v0.8.1

New feature: - support stress in cp2k

Bug fixings: several know issues

- Python
Published by amcadmus over 5 years ago

dpgen - v0.8.0

New features: - support pwmat - support nopbc - support init model parameter from old models - support aniso kspacing for vasp - support plm_path that defines CV in a separate file - support checking bad fp confs - support collect data - support initializing from an existing model - support simplify for LabeledSystem and System - with accurate thresthold, decay number of fp tasks to 0 if it is already accurate enough - support different activation func for different models

Updates: - set default multiplicity to auto; add parameter fragmentguesses - better suppport on deepmd-kit >= v1.1 - tag failures on allowfailure - better cvasp support - better ali support - restart shell by uuid - restart training if interrupted - retry slurm commands when failing

Bug fixings: - error in checking slurm status - error in ensuring alive - shell submit script should exit with code 1 - transfer typemap.raw. enforce the the same typemap in the training input.json - bad surf configurations - check if the length of batch size list is enough - auto test user provided INCAR - getting nframes in make_train - fix issue #247 add = to flags starting with -- - nve doesn't set the initial temperature

- Python
Published by amcadmus over 5 years ago

dpgen - 0.7.0

New features - Workflow for simplifying a dataset - Init reaction - More flexible cp2k input - Support Ali clould machines - Support non-periodic systems

Bug fixings - Full record of job information.

- Python
Published by amcadmus about 6 years ago

dpgen - v0.6.0

New features: - support aws - support electron temperature, as frame or atom parameter - data or iteration statatistics by run/report - build init surface via ase

Bug fixings: - jobid log in pmap does not work in lazy-local model - initbulk cannot use batch system other than slurm

- Python
Published by amcadmus over 6 years ago