Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merge devel to master #1161

Merged
merged 32 commits into from
Mar 21, 2023
Merged
Changes from 1 commit
Commits
Show all changes
32 commits
Select commit Hold shift + click to select a range
c1d582b
merge master into devel (#1064)
amcadmus Dec 4, 2022
c1937ae
Add parameter 'srtab_file_path' so that one can use DP-ZBL potential …
Chengqian-Zhang Dec 4, 2022
e3f98e0
Refactor: remove association between ABACUS/STRU and the element numb…
pxlxingliang Dec 18, 2022
2089358
Fix: remove the reading of `ntype` when treating ABACUS related info …
pxlxingliang Dec 18, 2022
6ea1812
add placeholders for variants (#1068)
njzjz Dec 19, 2022
b5da4f4
fix pass action (#1082)
njzjz Dec 21, 2022
02d7d7d
fix compatibility with NumPy and pymatgen (#1085)
njzjz Dec 22, 2022
afebf11
Doc(abacus): modify the description of parameters (#1080)
pxlxingliang Dec 22, 2022
1bb85a6
Fix(abacus): parse orbital information after parsing of INPUT (#1079)
pxlxingliang Dec 22, 2022
a9d324b
choose numb_steps/stop_batch automatically (#1086)
njzjz Dec 23, 2022
673266a
replace distutils.version.LooseVersion by packaging.version.Version (…
njzjz Dec 30, 2022
ed26994
fix doc: "structures" should be a list (#1091)
HuangJiameng Dec 30, 2022
06bd270
Support forward files for simplify (#1092)
HuangJiameng Dec 30, 2022
749e28a
breaking: remove old dispatcher (#1097)
njzjz Dec 31, 2022
ad69c27
Replace "python3" in command by sys.executable (#1105)
HuangJiameng Jan 6, 2023
b14063e
fix_bug simplify.py (#1113)
Vibsteamer Jan 14, 2023
3e1891d
fix_bug simplify.py (#1114)
Vibsteamer Jan 15, 2023
fb8668b
add an option to merge data to one H5 file (#1119)
njzjz Jan 19, 2023
57a8c16
add and run pre-commit to format codes (#1124)
njzjz Jan 27, 2023
418e0ce
fix compatibility with the latest pymatgen (#1126)
njzjz Jan 28, 2023
98f4541
refactor(abacus): link the pp/orb files defined in STRU not jdata (#1…
pxlxingliang Jan 28, 2023
1aafd33
docs: add logo to docs and README (#1128)
njzjz Jan 29, 2023
18613d6
fix restart trajectory for `merge_traj` (#1111)
wankiwi Jan 29, 2023
23a362d
Raise warnings if there is no system in the path listed in sys_config…
HuangJiameng Jan 29, 2023
b5423bf
docs: add links to DP-GUI (#1131)
njzjz Jan 31, 2023
7a1ceb4
fix numpydoc styles (#1134)
njzjz Feb 6, 2023
a4eca19
Updated the `revise_lmp_input_dump` function. (#1137)
panxiang126 Feb 13, 2023
c73ae2e
add isort to sort imports (#1133)
njzjz Mar 17, 2023
4471d17
fix a bug in make_abacus_relax (#1150)
maki49 Mar 17, 2023
29a1bf8
fix(abacus): do not write to deepmd raw/npy, if no abacus data in pos…
pxlxingliang Mar 19, 2023
5503215
bug_fix reproduce.py (#1156)
Vibsteamer Mar 19, 2023
8453131
always pass codecov status (#1157)
njzjz Mar 19, 2023
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
choose numb_steps/stop_batch automatically (#1086)
Fix #1084. Both keys are valid, so we detect which one is used in
`default_training_param`.
njzjz authored Dec 23, 2022
commit a9d324b51e7430c7c30aa5665028535f4954af5c
6 changes: 4 additions & 2 deletions dpgen/generator/run.py
Original file line number Diff line number Diff line change
@@ -365,13 +365,15 @@ def make_train (iter_index,
raise RuntimeError("DP-GEN currently only supports for DeePMD-kit 1.x or 2.x version!" )
# set training reuse model
if training_reuse_iter is not None and iter_index >= training_reuse_iter:
if LooseVersion('1') <= LooseVersion(mdata["deepmd_version"]) < LooseVersion('2'):
if 'numb_steps' in jinput['training'] and training_reuse_stop_batch is not None:
jinput['training']['numb_steps'] = training_reuse_stop_batch
elif 'stop_batch' in jinput['training'] and training_reuse_stop_batch is not None:
jinput['training']['stop_batch'] = training_reuse_stop_batch
if LooseVersion('1') <= LooseVersion(mdata["deepmd_version"]) < LooseVersion('2'):
jinput['training']['auto_prob_style'] \
="prob_sys_size; 0:%d:%f; %d:%d:%f" \
%(old_range, training_reuse_old_ratio, old_range, len(init_data_sys), 1.-training_reuse_old_ratio)
elif LooseVersion('2') <= LooseVersion(mdata["deepmd_version"]) < LooseVersion('3'):
jinput['training']['numb_steps'] = training_reuse_stop_batch
jinput['training']['training_data']['auto_prob'] \
="prob_sys_size; 0:%d:%f; %d:%d:%f" \
%(old_range, training_reuse_old_ratio, old_range, len(init_data_sys), 1.-training_reuse_old_ratio)