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 into master #3165

Merged
merged 98 commits into from
Jan 23, 2024
Merged
Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
98 commits
Select commit Hold shift + click to select a range
6c99220
Merge master into devel (#2956)
njzjz Oct 27, 2023
9a4a4dd
support compressing gelu_tf (#2957)
njzjz Oct 30, 2023
1429e46
fix SpecifierSet behavior with prereleases (#2959)
njzjz Oct 30, 2023
5be8fc9
[pre-commit.ci] pre-commit autoupdate (#2961)
pre-commit-ci[bot] Oct 31, 2023
389d403
merge prob_sys_size with prob_sys_size;0:nsys:1.0 (#2963)
CaRoLZhangxy Oct 31, 2023
1529e72
move to ruff formatter (#2951)
njzjz Nov 1, 2023
1cbe63d
docs: add theory from v2 paper (#2715)
njzjz Nov 2, 2023
9154da2
docs: configuring automatically generated release notes (#2975)
njzjz Nov 6, 2023
574068c
docs: use relative links (#2976)
njzjz Nov 6, 2023
7fb94ef
[pre-commit.ci] pre-commit autoupdate (#2978)
pre-commit-ci[bot] Nov 7, 2023
ffbdcf8
respect user defined CUDAARCHS (#2979)
njzjz Nov 7, 2023
a40dcaa
lmp: refactor ixnode (#2971)
njzjz Nov 7, 2023
283e8fe
bump scikit-build-core to 0.6 (#2981)
njzjz Nov 8, 2023
43fc073
rename `deepmd_cli` to `deepmd_utils` (#2983)
njzjz Nov 9, 2023
4c888d8
docs: remove lammps.md (#2986)
njzjz Nov 13, 2023
55d678d
bump CUDA version to 12.2 for pre-built packages (#2960)
njzjz Nov 16, 2023
6e9a575
[pre-commit.ci] pre-commit autoupdate (#2990)
pre-commit-ci[bot] Nov 17, 2023
87d9ffb
add unit tests for LAMMPS fparam/aparam keywords (#2998)
njzjz Nov 20, 2023
a342e94
fix restarting from compressed training with type embedding (#2996)
njzjz Nov 20, 2023
af6eb43
Bump docker/build-push-action from 5.0.0 to 5.1.0 (#2999)
dependabot[bot] Nov 21, 2023
66259b1
docs: document horovod on Conda-Forge (#3001)
njzjz Nov 21, 2023
4d1c5fd
[pre-commit.ci] pre-commit autoupdate (#3000)
pre-commit-ci[bot] Nov 21, 2023
f321046
Add the missing initializations for extra embedding variables (#3005)
nahso Nov 24, 2023
c03416d
add cu11 prebuilt packages (#3002)
njzjz Nov 26, 2023
efb0a34
print system prob using scientific natation (#3008)
njzjz Nov 28, 2023
b4bb3a9
[pre-commit.ci] pre-commit autoupdate (#3011)
pre-commit-ci[bot] Nov 28, 2023
12baf12
Fix macro issue with multiple arguments (#3016)
njzjz Nov 29, 2023
ea45295
[pre-commit.ci] pre-commit autoupdate (#3032)
pre-commit-ci[bot] Dec 5, 2023
44aba83
bump scikit-build-core to 0.7 (#3038)
njzjz Dec 6, 2023
3c54949
breaking(lmp): do not apply scale factor to model deviation (#3036)
njzjz Dec 6, 2023
fe488a4
fix se_a_ebd_v2 when nloc != nall (#3037)
njzjz Dec 7, 2023
a210799
skip pushing when an action is triggered by dependeabot (#3035)
njzjz Dec 7, 2023
0547940
Bump docker/metadata-action from 5.0.0 to 5.3.0 (#3029)
dependabot[bot] Dec 7, 2023
ce25ff4
fix: invalid read and write when natom grows (#3031)
Cloudac7 Dec 11, 2023
a6f1333
build neighbor list with external Python program (#3046)
njzjz Dec 11, 2023
2204ec1
fix GPU mapping error for Horovod + finetune (#3048)
njzjz Dec 11, 2023
7648d7a
remove unused codes in se_a.py (#3049)
nahso Dec 12, 2023
406e8f7
Bump actions/deploy-pages from 2 to 3 (#3052)
dependabot[bot] Dec 12, 2023
8db5e6a
Bump actions/setup-python from 4 to 5 (#3051)
dependabot[bot] Dec 12, 2023
558051e
Bump actions/labeler from 4 to 5 (#3050)
dependabot[bot] Dec 12, 2023
33c2c8d
[pre-commit.ci] pre-commit autoupdate (#3055)
pre-commit-ci[bot] Dec 12, 2023
e5c9c59
docs: document external neighbor list (#3056)
njzjz Dec 12, 2023
ddfa781
print NaN loss when labeled data is not found (#3047)
njzjz Dec 12, 2023
06cd3c1
fix labeler.yml with actions/labeler v5 (#3059)
njzjz Dec 14, 2023
1a7e252
nvnmd: init-model feature and 256 neighbors (#3058)
LiuGroupHNU Dec 14, 2023
e048389
Fix possible memory leak in constructors (#3062)
njzjz Dec 15, 2023
18902be
fix memory leaks related to `char*` (#3063)
njzjz Dec 15, 2023
a266b48
add utils for DP native model format (#3064)
njzjz Dec 15, 2023
a0f30f4
bump LAMMPS to stable_2Aug2023_update2 (#3066)
njzjz Dec 18, 2023
a47cd06
Update the path to training and validation data dir in zinc_se_a_mask…
dingye18 Dec 21, 2023
2b52187
[pre-commit.ci] pre-commit autoupdate (#3073)
pre-commit-ci[bot] Dec 21, 2023
0032f5d
add CodeQL checks (#3075)
njzjz Dec 21, 2023
f79eac1
Bump actions/upload-artifact from 3 to 4 (#3070)
dependabot[bot] Dec 21, 2023
b4fe171
Fix catching by value (#3077)
njzjz Dec 21, 2023
39f13c0
docs: update documentation for pre-compiled C library (#3083)
njzjz Dec 25, 2023
412bc37
Bump actions/deploy-pages from 3 to 4 (#3085)
dependabot[bot] Dec 25, 2023
6819b8e
Bump docker/metadata-action from 5.3.0 to 5.4.0 (#3086)
dependabot[bot] Dec 25, 2023
54e5988
Bump actions/upload-pages-artifact from 2 to 3 (#3087)
dependabot[bot] Dec 26, 2023
2287111
[pre-commit.ci] pre-commit autoupdate (#3089)
pre-commit-ci[bot] Dec 28, 2023
985a886
lmp: Register styles when using CMake (#3097)
njzjz Jan 2, 2024
a905817
Add pairwise tabulation as an independent model (#3101)
njzjz Jan 3, 2024
674ea17
rm rcut from DeepmdDataSystem (#3106)
wanghan-iapcm Jan 5, 2024
61ee4f2
fix segfault in ~Region (#3108)
njzjz Jan 5, 2024
db22812
add activation_function and resnet arguments and NumPy implementation…
njzjz Jan 5, 2024
c4b7baa
NativeLayer: support None bias. (#3111)
wanghan-iapcm Jan 5, 2024
7b3c3c0
fix native layer concat bug. (#3112)
wanghan-iapcm Jan 5, 2024
f181a30
model format for the embedding net (#3113)
wanghan-iapcm Jan 8, 2024
d1c0074
support numerical precision and env_mat (#3114)
wanghan-iapcm Jan 9, 2024
25cdd19
Bump docker/metadata-action from 5.4.0 to 5.5.0 (#3115)
dependabot[bot] Jan 9, 2024
a971d92
[pre-commit.ci] pre-commit autoupdate (#3116)
pre-commit-ci[bot] Jan 9, 2024
438bc78
Add dp model format sea (#3123)
wanghan-iapcm Jan 10, 2024
dac64cf
input order of env_mat changed to be consistent with descriptor (#3125)
wanghan-iapcm Jan 10, 2024
398f037
doc string for dp model format descriptor se_e2_a (#3124)
wanghan-iapcm Jan 10, 2024
43f9639
add native Networks for mutiple Network classes (#3117)
njzjz Jan 10, 2024
ff58456
add definition for the output of fitting and model (#3128)
wanghan-iapcm Jan 12, 2024
04f07ef
lmp: fix evflag initialization (#3133)
njzjz Jan 12, 2024
828df66
cc: refactor DeepPotModelDevi, making it framework-independent (#3134)
njzjz Jan 12, 2024
d5590a4
fix: model check assumes __call__ as the forward method (#3136)
wanghan-iapcm Jan 12, 2024
308f97e
support fitting net (#3137)
wanghan-iapcm Jan 12, 2024
15117a0
refactorize NativeLayer, interface does not rely on the platform (#3138)
wanghan-iapcm Jan 13, 2024
ae90498
refactorize networks, now can be used cross platform (#3141)
wanghan-iapcm Jan 13, 2024
2096b80
move utility to `deepmd_utils` (without modifaction) (#3140)
njzjz Jan 13, 2024
539e4ab
add cross-platform AutoBatchSize (#3143)
njzjz Jan 14, 2024
89d9a88
move deepmd.entrypoints.{doc,gui} to deepmd_utils.entrypoints.{doc,gu…
njzjz Jan 14, 2024
e218f9c
cc: refactor DeepPot to support multiple backends (#3142)
njzjz Jan 15, 2024
ed76cff
resolve "Multiplication result converted to larger type" (#3149)
njzjz Jan 17, 2024
9be1ad2
[pre-commit.ci] pre-commit autoupdate (#3147)
pre-commit-ci[bot] Jan 17, 2024
850575a
cc: refactor DeepTensor for multiple-backend framework (#3151)
njzjz Jan 17, 2024
1efc7f8
cc: refactor DataModifier for multiple-backend framework (#3148)
njzjz Jan 17, 2024
5493921
fix: some issue of the output def (#3152)
wanghan-iapcm Jan 18, 2024
d915a91
cc: merge `DeepPotBase` and `DeepTensor` member functions (#3145)
njzjz Jan 18, 2024
8c1b467
docs: update Amber interface (#3074)
njzjz Jan 20, 2024
efe0962
move `OutOfMemoryError` from `deepmd` to `deepmd_utils` (#3153)
njzjz Jan 20, 2024
937f03f
cmake: fix setting `CMAKE_HIP_FLAGS` (#3155)
njzjz Jan 20, 2024
4d82430
docs: document CP2K interface (#3158)
njzjz Jan 20, 2024
1097062
resolve "Multiplication result converted to larger type" (#3159)
njzjz Jan 20, 2024
e5f9117
set dpgui entry point to `deepmd_utils` (#3161)
njzjz Jan 22, 2024
138ffef
Fix max nbor size related issues (#3157)
denghuilu Jan 23, 2024
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
breaking(lmp): do not apply scale factor to model deviation (#3036)
Resolves #3027.

---------

Signed-off-by: Jinzhe Zeng <jinzhe.zeng@rutgers.edu>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
  • Loading branch information
njzjz and pre-commit-ci[bot] authored Dec 6, 2023
commit 3c549492dbba017aaa994b090f926deeb29bb687
1 change: 1 addition & 0 deletions doc/third-party/lammps-command.md
Original file line number Diff line number Diff line change
Expand Up @@ -82,6 +82,7 @@ Evaluate the interaction of the system by using [Deep Potential][DP] or [Deep Po
This pair style takes the deep potential defined in a model file that usually has the .pb extension. The model can be trained and frozen by package [DeePMD-kit](https://github.com/deepmodeling/deepmd-kit), which can have either double or single float precision interface.

The model deviation evalulates the consistency of the force predictions from multiple models. By default, only the maximal, minimal and average model deviations are output. If the key `atomic` is set, then the model deviation of force prediction of each atom will be output.
The unit follows [LAMMPS units](#units) and the [scale factor](https://docs.lammps.org/pair_hybrid.html) is not applied.

By default, the model deviation is output in absolute value. If the keyword `relative` is set, then the relative model deviation of the force will be output, including values output by the keyword `atomic`. The relative model deviation of the force on atom $i$ is defined by

Expand Down
15 changes: 7 additions & 8 deletions source/lmp/pair_deepmd.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -767,12 +767,12 @@ void PairDeepMD::compute(int eflag, int vflag) {
all_v_avg = sqrt(all_v_avg / 9);
}
if (rank == 0) {
all_v_max *= scale[1][1] * ener_unit_cvt_factor;
all_v_min *= scale[1][1] * ener_unit_cvt_factor;
all_v_avg *= scale[1][1] * ener_unit_cvt_factor;
all_f_max *= scale[1][1] * force_unit_cvt_factor;
all_f_min *= scale[1][1] * force_unit_cvt_factor;
all_f_avg *= scale[1][1] * force_unit_cvt_factor;
all_v_max *= ener_unit_cvt_factor;
all_v_min *= ener_unit_cvt_factor;
all_v_avg *= ener_unit_cvt_factor;
all_f_max *= force_unit_cvt_factor;
all_f_min *= force_unit_cvt_factor;
all_f_avg *= force_unit_cvt_factor;
fp << setw(12) << update->ntimestep << " " << setw(18) << all_v_max
<< " " << setw(18) << all_v_min << " " << setw(18) << all_v_avg
<< " " << setw(18) << all_f_max << " " << setw(18) << all_f_min
Expand All @@ -798,8 +798,7 @@ void PairDeepMD::compute(int eflag, int vflag) {
displacements, MPI_DOUBLE, 0, world);
if (rank == 0) {
for (int dd = 0; dd < all_nlocal; ++dd) {
std_f_all[tagrecv[dd] - 1] =
stdfrecv[dd] * scale[1][1] * force_unit_cvt_factor;
std_f_all[tagrecv[dd] - 1] = stdfrecv[dd] * force_unit_cvt_factor;
}
for (int dd = 0; dd < all_nlocal; ++dd) {
fp << " " << setw(18) << std_f_all[dd];
Expand Down
Loading