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 master #6

Merged
merged 776 commits into from
Sep 11, 2021
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
776 commits
Select commit Hold shift + click to select a range
27a35e8
fix bugs in examples
Apr 20, 2021
0926971
Merge pull request #541 from amcadmus/devel
amcadmus Apr 20, 2021
6c87859
Merge pull request #2 from deepmodeling/devel
YWolfeee Apr 20, 2021
068d2fb
add what's new in v2.0 to readme. move troubleshooting to a separate …
Apr 20, 2021
6f5e4c1
Merge pull request #542 from amcadmus/devel
amcadmus Apr 20, 2021
d42968f
use bit operations to construct nbor sort keys
denghuilu Apr 20, 2021
88e26ea
fix bug of using old name se_a, changed to se_e2_a
Apr 21, 2021
a5a31a6
fix bugs in UT
Apr 21, 2021
a5cb130
Merge pull request #547 from amcadmus/devel
amcadmus Apr 21, 2021
58e83ae
add ut for encoding/decoding nbor info
denghuilu Apr 23, 2021
f9000a6
Merge pull request #27 from deepmodeling/devel
denghuilu Apr 23, 2021
7defc15
Merge pull request #545 from denghuilu/devel
amcadmus Apr 23, 2021
7b79ede
close loss normalization, since it need further examination
YWolfeee Apr 23, 2021
7f45c18
Merge pull request #6 from deepmodeling/devel
iProzd Apr 23, 2021
9067c97
Merge pull request #559 from YWolfeee/devel
amcadmus Apr 23, 2021
23a9b22
Fix bug in coord.cu
iProzd Apr 25, 2021
9bc7e99
Merge pull request #7 from deepmodeling/devel
iProzd Apr 25, 2021
0641961
Merge pull request #566 from iProzd/devel
amcadmus Apr 25, 2021
1d11f6c
Merge pull request #8 from deepmodeling/devel
iProzd Apr 27, 2021
fde04de
Add lib coord unittest
iProzd Apr 27, 2021
0d0cb77
Merge pull request #569 from iProzd/devel
amcadmus Apr 27, 2021
7df619c
refact fit/ener.py, add UT for atom_ener, fix zero divider bug in se_a
Apr 28, 2021
0547de2
add support for type embedding in fitting. fix bugs in fit/ener.py
Apr 28, 2021
b82f882
extend the input dim of embedding net
Apr 28, 2021
8e2a897
Merge remote-tracking branch 'upstream/devel' into devel
Apr 29, 2021
6c7272d
add support for type embedding
Apr 29, 2021
d22068f
update doc for input parameters
Apr 29, 2021
4bf3545
add doc for type_embed, fix bug
Apr 29, 2021
73482ac
add UT for type_one_side
Apr 30, 2021
2ed422f
Merge pull request #581 from amcadmus/devel
amcadmus May 1, 2021
75d702a
fix bug: type embedding should be optional
May 4, 2021
d77a6a1
Merge remote-tracking branch 'upstream/devel' into devel
May 4, 2021
850169f
Merge pull request #588 from amcadmus/devel
amcadmus May 4, 2021
206955e
UT for std calculations
May 6, 2021
7d24520
refact the impl. of std and relative std
May 7, 2021
6ed3ec4
impl model deviation of virial
May 7, 2021
0e4d294
support relative model deviation for virial
May 7, 2021
6218faf
fix bug: declaration of all_virial should be available to all precisions
May 7, 2021
75d7ca1
Merge pull request #594 from amcadmus/devel
amcadmus May 8, 2021
6a1d643
fix issue #598
May 8, 2021
e12acdf
test lammps builds
njzjz May 8, 2021
0ad8856
copy lammps plugin
njzjz May 8, 2021
a3742d5
Merge pull request #9 from deepmodeling/devel
iProzd May 8, 2021
50fc2db
Merge pull request #600 from njzjz/test-lammps-builds
amcadmus May 9, 2021
2dfb64a
Re-structured Doc (#513)
tuoping May 9, 2021
bcdd9f6
Merge pull request #599 from amcadmus/fix-598
amcadmus May 9, 2021
33c0c0f
add ut for model compression (#586)
denghuilu May 9, 2021
900dd5a
Merge Tensor Loss Training and Polar Normalization (#593)
YWolfeee May 10, 2021
169ea25
print the virial model deviations in the place of zeros (#606)
amcadmus May 11, 2021
f9181ca
fix bug of type embed
yhliu918 May 11, 2021
559939a
fix bug of type embedding
yhliu918 May 11, 2021
6286554
Merge pull request #33 from deepmodeling/devel
denghuilu May 11, 2021
c721128
optimize UT for dp transfer
denghuilu May 11, 2021
7b5d4de
fix bug in test_transfer.py
denghuilu May 11, 2021
18e1caa
add coverage report for c/c++ api
njzjz May 11, 2021
478ee0d
uploading once is enough
njzjz May 11, 2021
50283b2
Merge pull request #34 from deepmodeling/devel
denghuilu May 11, 2021
65cfd8a
fix bug of issue/580
denghuilu May 11, 2021
c27df8b
Fix bug in tf allocate_temp
iProzd May 11, 2021
780885d
Merge pull request #10 from deepmodeling/devel
iProzd May 11, 2021
2fa34cd
change options
njzjz May 11, 2021
cbc2621
Apply suggestions from code review
njzjz May 11, 2021
eaa774f
link coverage_config
njzjz May 11, 2021
9724071
Merge pull request #609 from jxxiaoshaoye/devel
amcadmus May 11, 2021
84b618c
Merge pull request #611 from denghuilu/fix580
amcadmus May 11, 2021
d7d81eb
Merge pull request #612 from iProzd/devel
amcadmus May 11, 2021
5f71eae
Merge pull request #610 from denghuilu/devel
amcadmus May 11, 2021
90c0f60
Merge pull request #35 from deepmodeling/devel
denghuilu May 11, 2021
31707c2
Ignore tests
njzjz May 11, 2021
18b9987
Merge branch 'devel' into coverage
njzjz May 11, 2021
012b9fc
fix TB logdir remove bug
marian-code May 12, 2021
8f76b6c
add UUID support for DP
denghuilu May 12, 2021
073c733
Merge pull request #621 from denghuilu/devel
amcadmus May 12, 2021
9ce0286
Merge pull request #617 from marian-code/devel
amcadmus May 12, 2021
f70437f
Merge pull request #613 from njzjz/coverage
amcadmus May 13, 2021
396a41c
check validity of data systems. print help message
May 13, 2021
ed5bac8
Merge pull request #624 from amcadmus/devel
amcadmus May 13, 2021
9fd6ddc
add Important hint at getting-start.md (#622)
denghuilu May 13, 2021
c93a084
add doc of type embedding (#625)
yhliu918 May 13, 2021
72de108
Optimized mkindex function in doc/conf.py and added two files in trou…
tuoping May 14, 2021
6bba7fc
support MPI and other atom_styles for LAMMPS atomic keyword (#628)
njzjz May 14, 2021
98c3ba1
fix spell mistake (#638)
njzjz May 15, 2021
83fffbe
Readme and Examples for Tensor mode (#632)
YWolfeee May 18, 2021
363f9ba
append to out_file when LAMMPS restarts (#640)
njzjz May 18, 2021
cb2c118
add an example of C++ inference to doc (#652)
njzjz May 24, 2021
5a8bc2c
Add instructions for i-PI (#660)
tuoping May 26, 2021
b3cfe45
Added doc for netsize setting, num_nodes specification, and sel setti…
tuoping May 29, 2021
a74ce2d
fix issue 668 (#680)
denghuilu May 31, 2021
6058351
fix bug in op definition prod_virial_grad_multi_device.cc. (#685)
amcadmus Jun 1, 2021
778321e
Add ROCM support for DEEPMD (#656)
galeselee Jun 1, 2021
57b50cc
Fix uniform random seed (#691)
amcadmus Jun 2, 2021
ab7621e
Doc api cc (#663)
tuoping Jun 3, 2021
3588c2d
add op unittests for prod_force, prod_virial, prod_force_grad and pro…
iProzd Jun 4, 2021
0d2ffb3
fix bug of adding int to a None random seed (#705)
amcadmus Jun 5, 2021
a4992e3
update the doc for training input (#706)
amcadmus Jun 5, 2021
0a66758
fix bug: reuse the zero layer rather than building a new one (#714)
amcadmus Jun 9, 2021
21740c0
Sync gitee (#707)
tuoping Jun 9, 2021
0f84f52
UT for model devi C++ interface (#731)
amcadmus Jun 14, 2021
6b44266
Add subcommand to calculate model-deviation (#715)
Ericwang6 Jun 14, 2021
9997ad6
add CUDA/ROCM documents & fix CI (fix #730) (#739)
njzjz Jun 14, 2021
af7bf3b
Use fmod to wrap the coord of atoms. UT for force/virial ops (#741)
iProzd Jun 15, 2021
c200e9a
remove unused tqdm (#746)
njzjz Jun 15, 2021
5e9648e
remove typing_extensions for python>=3.7 (#752)
njzjz Jun 15, 2021
86db65d
remove `-std=c++17` for cuda<=10 (#759)
njzjz Jun 17, 2021
4648764
only add inputs_zero node if atom_ener exists (#766)
njzjz Jun 18, 2021
0c7f490
add type-embedding developer doc (#762)
tuoping Jun 19, 2021
f326a86
add model compression support for models with exclude_types feature …
denghuilu Jun 19, 2021
44d49f3
Add a more detailed introduction for model compression (#772)
denghuilu Jun 20, 2021
b15944d
allow c++ tests to run without internet (#785)
y1xiaoc Jun 22, 2021
4555034
support converting models generated in v1.3 to 2.0 compatibility (#725)
njzjz Jun 22, 2021
7d145c5
add documents for conda (#798)
njzjz Jun 26, 2021
b145ca3
throw a message if tf runtime is incompatible (#797)
njzjz Jun 26, 2021
4db15c8
Fix bug of empty input in gelu.cu (#800)
iProzd Jun 27, 2021
68da791
add OOM message (#801)
njzjz Jun 27, 2021
a951d8b
give a default value to T and convert models from v1.2 (#789)
njzjz Jun 27, 2021
8ce9884
fix model compression bug of zero environment matrix (#808)
denghuilu Jun 29, 2021
b956217
`box.npy` is not necessary for nopbc (#810)
njzjz Jun 29, 2021
4a693ae
speedup ROCm kernels which use atomicAdd (#809)
darelbeida Jun 29, 2021
614bcef
Synchronize CUDA _r modifications to ROCM (#815)
galeselee Jun 30, 2021
1203c04
speedup CUDA kernels(use atomicAdd inside) by reducing the global me…
denghuilu Jun 30, 2021
0ae7cea
fix bug of custom op's multiple initialization (#812)
denghuilu Jun 30, 2021
424fe13
make deep tensor deriv again (#805)
y1xiaoc Jul 1, 2021
afc557a
fill rij with zero (#818)
njzjz Jul 1, 2021
de428e3
`NOT_LOADABLE` should be `tuple` (#825)
njzjz Jul 4, 2021
914c054
fix bug 824 and Synchronize updates to CUDA cod (#828)
galeselee Jul 6, 2021
34c9bc9
speedup tabulate cuda kernel by reducing shm using (#830)
darelbeida Jul 7, 2021
cd11885
support to specify CUDA/ROCm root in python pkg building (#834)
darelbeida Jul 8, 2021
15de001
use cached Session to speed up py tests (#833)
njzjz Jul 8, 2021
1f5dd92
automatically determine the `sel` from the training data. (#831)
amcadmus Jul 9, 2021
e1c64ec
speed up format_nlist_b (#832)
BaoHhhhhhan Jul 11, 2021
cd3c920
add message for DecodeError (#839)
njzjz Jul 11, 2021
94635ba
also convert input v1 to v2 for dp compress (#844)
njzjz Jul 13, 2021
78123a5
Synchronize format_nlist_b in CUDA with ROCm (#845)
BaoHhhhhhan Jul 15, 2021
1f01650
pin sphinx to a previous version (#848)
njzjz Jul 15, 2021
9b5e2b9
remove cub include for CUDA>=11 (#866)
njzjz Jul 19, 2021
4985932
Add Errcheck after every kernel function runs And merge redundant cod…
galeselee Jul 22, 2021
851fa96
Fix the empty neighbor distance array in neighbor_stat.py (#882)
nicklin96 Jul 26, 2021
c4b9c9e
adapt changes to auditwheel directory in manylinux (#889)
njzjz Jul 28, 2021
953621f
Update getting-started.md (#898)
dingye18 Jul 29, 2021
4a229fe
build low and high precision at the same time (#879)
njzjz Jul 30, 2021
31f1ef6
Replace PS-Worker mode with multi-worker one. (#892)
shishaochen Jul 30, 2021
70508a5
fix `InvalidArgumentError` caused by zero `sel` and optimize zero mat…
njzjz Jul 31, 2021
043ac86
enhance the cli to generate doc json file (#891)
njzjz Jul 31, 2021
7b9f303
Find available GPUs in an elegant way. (#905)
shishaochen Aug 1, 2021
b5b15fa
fix 'NoneType' has no len() in `auto_sel` (#911)
njzjz Aug 1, 2021
689ffa4
raise warning before training if sel is not enough (#914)
njzjz Aug 2, 2021
ee0ed99
Fix the expanding logic of `SLURM_JOB_NODELIST` and add unit tests fo…
shishaochen Aug 2, 2021
0c66c92
update conda install documents (#925)
njzjz Aug 6, 2021
3ae80b3
Fix member declartion of `deepmd` and `deepmd.entrypoints`. (#922)
shishaochen Aug 6, 2021
4ced020
set input DeepmdData.type_map to input type_map (#924)
amcadmus Aug 6, 2021
4be5eb1
Passing error to TF instead of exit (#918)
njzjz Aug 6, 2021
b30a75e
add lammps compute style for atomic deep tensor (#927)
amcadmus Aug 8, 2021
23c59e1
add aliases to Arguments (#932)
njzjz Aug 8, 2021
d7e7dbb
fix a typo in #932 (#934)
njzjz Aug 9, 2021
994cc11
add aliases to Arguments (#933)
njzjz Aug 9, 2021
4a9943e
Reconstruct the interface of model compression (#921)
denghuilu Aug 9, 2021
c9fb8f4
rm `load_ckpt` (#936)
amcadmus Aug 9, 2021
382e92a
rm load_ckpt (#935)
amcadmus Aug 9, 2021
06d591d
clean library and header dependencies (#930)
njzjz Aug 10, 2021
c4856ef
fix bug of gelu activation function (#939)
denghuilu Aug 10, 2021
e8a9101
add model compression support for models without training script (#948)
denghuilu Aug 11, 2021
5529a97
convert `decay_rate` to `stop_lr` from old inputs (#949)
njzjz Aug 12, 2021
72aaa9b
add LAMMPS plugin (#945)
njzjz Aug 12, 2021
3c2a2bd
make native MD compatible with v2.0 (#950)
njzjz Aug 12, 2021
e345105
Cherry pick #492 and #664: create issue templates (#961)
njzjz Aug 12, 2021
d02416f
only enable link what you use on GNU compilers (#962)
njzjz Aug 12, 2021
56fd343
Do not find protobuf for python (#963)
njzjz Aug 12, 2021
fd397bb
cherry pick #338: fix an error in stress by ase interface (#964)
njzjz Aug 12, 2021
f743bda
cherry pick #564: add more badges (#965)
njzjz Aug 12, 2021
074f3f2
speedup model compression UTs (#956)
denghuilu Aug 12, 2021
ee0f6e6
update type embedding doc (#967)
yhliu918 Aug 13, 2021
6c83c27
add code comment for InputNlist struct (#968)
denghuilu Aug 14, 2021
68577be
[ImgBot] Optimize images (#970)
njzjz Aug 15, 2021
6d8c31c
update contributors (#975)
amcadmus Aug 16, 2021
820b3ed
refactor docs (#952)
njzjz Aug 16, 2021
e16d75c
remove bare `except` and limit the `try` clause (#977)
njzjz Aug 16, 2021
a1914ea
fix python cmake error (#976)
denghuilu Aug 17, 2021
795a79b
add an example of `nopbc` and related docs (#994)
njzjz Aug 18, 2021
4f54de0
add `dp --version` (#995)
njzjz Aug 19, 2021
cf3e7d9
Add the argument `tensorboard_freq` to control sampling ratio during …
shishaochen Aug 19, 2021
f3b08b3
add sphinx plugins `viewcode` and `intersphinx` (#997)
njzjz Aug 20, 2021
106f570
generate Python API document automatically (#998)
njzjz Aug 20, 2021
f2a7303
unpin tensorflow version (#999)
njzjz Aug 20, 2021
475b3d7
fix type hints and add doc for `exclude_types` (#1005)
njzjz Aug 21, 2021
346fab6
add a note for DP-GUI (#1004)
njzjz Aug 21, 2021
532e84b
fix a bug in `setup.py` (#1002)
njzjz Aug 21, 2021
16b81f4
fix incorrect type hints and docstrings (#1001)
njzjz Aug 21, 2021
472d7c4
add model compression training support for deepmd-kit (#1000)
denghuilu Aug 21, 2021
e9edec6
add examples to docstings (#1010)
njzjz Aug 22, 2021
1306c32
rm dp transfer from the model compression workflow (#1008)
denghuilu Aug 22, 2021
965d91d
bump sphinx_rtd_theme to >=1.0.0rc1 (#1014)
njzjz Aug 22, 2021
f7a5b08
show citation in the GitHub (#1012)
njzjz Aug 22, 2021
d42ca99
move parameters docstring from constructor method to class itself (#1…
njzjz Aug 22, 2021
a1a97fe
give a clear message if `model.get_ntypes()<data.get_ntypes()` (#1016)
njzjz Aug 23, 2021
d46469b
Instantiate RunOptions first when training. (#1019)
shishaochen Aug 23, 2021
297ce70
add docstring to `DescrptSeA` (#1017)
njzjz Aug 23, 2021
29546c1
add `InputNlist` into API doc (#1009)
njzjz Aug 23, 2021
93c140f
Update easy-install.md (#1021)
caic99 Aug 24, 2021
c0874f0
update doc for model compression (#1022)
denghuilu Aug 24, 2021
fd1f371
add docstring for `EnerFitting` (#1024)
njzjz Aug 25, 2021
8048e77
Use a local Numpy random generator. (#1030)
shishaochen Aug 25, 2021
96bc025
save checkpoint files with step and keep recent files (#1031)
njzjz Aug 25, 2021
0004484
Avoid the same batch sequence among workers. (#1032)
shishaochen Aug 25, 2021
f35afe0
get library extension suffix from built-in method (#1036)
njzjz Aug 25, 2021
602760e
speedup scan_nlist kernel (#1028)
denghuilu Aug 25, 2021
ed20998
use TF's built-in method to get numpy dtype (#1035)
njzjz Aug 26, 2021
b51f981
clean up the unused including files of device source files (#1037)
denghuilu Aug 26, 2021
8bbe565
Fix typo: CMAKE_COMPILER_IS_GNUCXX (#1038)
caic99 Aug 26, 2021
90b1f52
Fix typo: CMAKE_COMPILER_IS_GNUCXX (#1038) (#1041)
njzjz Aug 26, 2021
5ab5fa1
decouple activation function's type from model compression's process …
liangadam Aug 27, 2021
37af1d1
fix model compression error (#1043)
denghuilu Aug 27, 2021
1024b65
merge devel into master
Aug 27, 2021
f923ee5
change to almostEqual in UT to avoid difference at FP precision
Aug 27, 2021
1a25414
Merge pull request #1047 from amcadmus/master
amcadmus Aug 28, 2021
a7e4760
change to almostEqual in UT to avoid difference at FP precision (#1048)
amcadmus Aug 28, 2021
5f8989b
fix hybrid descriptor training error (#1052)
njzjz Aug 28, 2021
1dd6e97
add compatibility to `dp freeze` (#1055)
njzjz Aug 29, 2021
8dbc211
fix device UT error (#1056)
denghuilu Aug 29, 2021
26b4492
copy `all_virial` for float precision (#1069)
njzjz Aug 31, 2021
37fe14c
upgrade os.system to subporcess.popen method (#1066)
denghuilu Aug 31, 2021
8cf52fd
use `np.testing.assert_almost_equal` for array comparing (#1059)
njzjz Aug 31, 2021
4c10232
set `allow_growth` in `default_tf_session_config` (#1067)
njzjz Aug 31, 2021
75160c7
fix Fail to build on macos: explicit instantiation of 'deepmd::Region…
amcadmus Aug 31, 2021
63baa30
undo reset lcurve.out during the model compression process (#1080)
denghuilu Sep 1, 2021
91787ab
use @loader_path on macos instead of $ORIGIN (#1078)
njzjz Sep 1, 2021
385dcd6
fix typo: `lcueve.out`->`lcurve.out` (#1077)
njzjz Sep 1, 2021
c716b9f
Model compression checkpoint (#1076)
denghuilu Sep 1, 2021
03a05bd
Enable parallel training UT in GitHub CI. (#1075)
shishaochen Sep 1, 2021
9dcc816
Fix shape mismatch when type_embedding is enabled and type_one_side i…
shishaochen Sep 1, 2021
5e96c57
Revert "get library extension suffix from built-in method (#1036)" (#…
njzjz Sep 1, 2021
d68171a
reduce `rcut` and `sel` in the example of `se_e3` (#1082)
njzjz Sep 1, 2021
da5f688
create cross-references in docstring (#1083)
njzjz Sep 1, 2021
c824ff6
add ABC for descriptors (#1081)
njzjz Sep 2, 2021
aab124f
Fix a potential slice bug in se_t descriptor (#1087)
denghuilu Sep 3, 2021
e2fc5e3
make compress work for hybrid descriptor composed of se_e2_a (#1094)
njzjz Sep 4, 2021
a5bdd14
interface for deepmd with the centroids atoms, full 3x3 "atomic-viria…
DavideTisi Sep 4, 2021
32ccbb5
Fix gradient not averaged when parallel training. (#1104)
shishaochen Sep 6, 2021
d5a0f6f
Enable init-frz-model support for the original model (#1102)
denghuilu Sep 6, 2021
8727956
merge duplicated NeighborStat.get_stat (#1103)
njzjz Sep 6, 2021
dd3c1de
Update doc for init-frz-model (#1107)
denghuilu Sep 7, 2021
904ec11
fix bug of single precision model compression (#1110)
denghuilu Sep 7, 2021
2a71494
fix bug of single precision transfer (#1111)
denghuilu Sep 7, 2021
1fbf474
fix LAMMPS_VERSION_NUMBER condition (#1116)
njzjz Sep 8, 2021
60797e0
Fix missing `std::numeric_limits` (#1113)
chazeon Sep 8, 2021
97be2f5
support init_frz_model for hybrid descriptor (#1112)
njzjz Sep 8, 2021
ed36276
fix data_modifier OOM problem when set size is too large (#1117)
amcadmus Sep 8, 2021
1526587
fix bugs of dipole charge modifier: binary str and missing frozen nod…
amcadmus Sep 10, 2021
e263aa3
fix "Call to method DeepTensor.__init__ with too many arguments" (#1125)
njzjz Sep 10, 2021
95a0340
Merge branch 'master' into devel
amcadmus Sep 10, 2021
2f6020b
Merge pull request #1126 from deepmodeling/devel
amcadmus Sep 10, 2021
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  
25 changes: 25 additions & 0 deletions .github/workflows/build_cc.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,25 @@
on:
push:
pull_request:
name: Build C++
jobs:
testpython:
name: Build C++
runs-on: ubuntu-20.04
strategy:
matrix:
include:
- variant: cpu
- variant: cuda
steps:
- uses: actions/checkout@master
with:
submodules: true
- run: sudo apt update && sudo apt install g++-7
- run: sudo apt install nvidia-cuda-toolkit
if: matrix.variant == 'cuda'
- run: source/install/build_cc.sh
env:
DP_VARIANT: ${{ matrix.variant }}
CC: gcc-7
CXX: g++-7
68 changes: 68 additions & 0 deletions .github/workflows/build_wheel.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,68 @@
name: Build and upload to PyPI

on:
push:
pull_request:

jobs:
build_wheels:
name: Build wheels on ${{ matrix.os }}
runs-on: ${{ matrix.os }}
strategy:
matrix:
os: [ubuntu-18.04] #, windows-latest, macos-latest]

steps:
- uses: actions/checkout@v2
- uses: actions/setup-python@v2
name: Install Python
with:
python-version: '3.8'

- name: Install cibuildwheel
run: |
python -m pip install cibuildwheel

- name: Build wheels
env:
CIBW_BUILD: "cp36-* cp37-* cp38-* cp39-*"
CIBW_MANYLINUX_X86_64_IMAGE: ghcr.io/deepmodeling/manylinux2010_x86_64_tensorflow
CIBW_BEFORE_BUILD: pip install tensorflow
CIBW_SKIP: "*-win32 *-manylinux_i686"
run: |
python -m cibuildwheel --output-dir wheelhouse
- uses: actions/upload-artifact@v2
with:
path: ./wheelhouse/*.whl

build_sdist:
name: Build source distribution
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v2
- uses: actions/setup-python@v2
name: Install Python
with:
python-version: '3.8'
- run: pip install -U scikit-build tensorflow setuptools_scm
- name: Build sdist
run: python setup.py sdist

- uses: actions/upload-artifact@v2
with:
path: dist/*.tar.gz

upload_pypi:
needs: [build_wheels, build_sdist]
runs-on: ubuntu-latest
if: startsWith(github.event.ref, 'refs/tags/v')
steps:
- uses: actions/download-artifact@v2
with:
name: artifact
path: dist

- uses: pypa/gh-action-pypi-publish@master
with:
user: __token__
password: ${{ secrets.pypi_password }}
33 changes: 33 additions & 0 deletions .github/workflows/lint_python.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,33 @@
on:
push:
pull_request:
name: Lint Python
jobs:
lintpython:
name: Lint Python
runs-on: ubuntu-20.04
strategy:
matrix:
python-version: [3.8]

steps:
- uses: actions/checkout@v1
- uses: actions/setup-python@v2
with:
python-version: ${{ matrix.python }}
- name: Install requirements
run: pip install -r requirements.txt
- uses: marian-code/python-lint-annotate@v2.5.0
with:
python-root-list: "./deepmd/*.py ./deepmd/*/*.py ./source/train/*.py ./source/tests/*.py ./source/op/*.py"
use-black: true
use-isort: true
use-mypy: true
use-pycodestyle: true
use-pydocstyle: true
extra-pycodestyle-options: "--max-line-length=88"
use-pylint: false
use-flake8: false
use-vulture: true
conda-python-version: "3.8"

18 changes: 18 additions & 0 deletions .github/workflows/mirror_gitee.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,18 @@
name: Mirror to Gitee Repo

on: [ push, delete, create ]

# Ensures that only one mirror task will run at a time.
concurrency:
group: git-mirror

jobs:
git-mirror:
runs-on: ubuntu-latest
steps:
- uses: wearerequired/git-mirror-action@v1
env:
SSH_PRIVATE_KEY: ${{ secrets.SYNC_GITEE_PRIVATE_KEY }}
with:
source-repo: "git@github.com:deepmodeling/deepmd-kit.git"
destination-repo: "git@gitee.com:deepmodeling/deepmd-kit.git"
11 changes: 11 additions & 0 deletions .github/workflows/test_cc.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
on:
push:
pull_request:
name: Test C++
jobs:
testpython:
name: Test C++
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@master
- run: source/install/test_cc.sh
79 changes: 79 additions & 0 deletions .github/workflows/test_python.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,79 @@
on:
push:
pull_request:
name: Test Python
jobs:
testpython:
name: Test Python
runs-on: ubuntu-18.04
strategy:
matrix:
include:
- python: 3.6
gcc: 4.8
tf: 1.8
- python: 3.6
gcc: 4.8
tf: 1.12
- python: 3.6
gcc: 4.8
tf: 1.14
- python: 3.6
gcc: 5
tf: 1.14
- python: 3.6
gcc: 8
tf: 1.14
- python: 3.7
gcc: 5
tf: 1.14
- python: 3.7
gcc: 6
tf: 1.14
- python: 3.7
gcc: 7
tf: 1.14
- python: 3.7
gcc: 8
tf: 1.14
- python: 3.7
gcc: 5
tf:
- python: 3.7
gcc: 8
tf:
- python: 3.8
gcc: 5
tf:
- python: 3.8
gcc: 8
tf:

steps:
- uses: actions/checkout@master
- uses: actions/setup-python@v2
with:
python-version: ${{ matrix.python }}
- name: pip cache
uses: actions/cache@v2
with:
path: ~/.cache/pip
key:
${{ runner.os }}-pip-${{ hashFiles('**/setup.py') }}-${{ hashFiles('**/requirements.txt') }}
restore-keys: |
${{ runner.os }}-pip-
- run: |
sudo apt update
sudo apt install gcc-${{ matrix.gcc }} g++-${{ matrix.gcc }}
- run: pip install -e .[cpu,test] codecov
env:
CC: gcc-${{ matrix.gcc }}
CXX: g++-${{ matrix.gcc }}
TENSORFLOW_VERSION: ${{ matrix.tf }}
- run: dp --version
- name: Prepare parallel runtime
if: ${{ matrix.tf == '' }}
run: |
sudo apt install libopenmpi-dev openmpi-bin
HOROVOD_WITHOUT_GLOO=1 HOROVOD_WITH_TENSORFLOW=1 pip install horovod mpi4py
- run: pytest --cov=deepmd source/tests && codecov
6 changes: 6 additions & 0 deletions .gitignore
Original file line number Diff line number Diff line change
Expand Up @@ -26,3 +26,9 @@ venv*
.vscode/**
_build
_templates
API_CC
doc/api_py/
dp/
build_lammps/
build_tests/
build_cc_tests
6 changes: 3 additions & 3 deletions .gitmodules
Original file line number Diff line number Diff line change
@@ -1,3 +1,3 @@
[submodule "source/op/cuda/cub"]
path = source/op/cuda/cub
url = git://github.com/NVlabs/cub.git
[submodule "source/lib/src/cuda/cub"]
path = source/lib/src/cuda/cub
url = git://github.com/NVIDIA/cub.git
95 changes: 0 additions & 95 deletions .travis.yml

This file was deleted.

19 changes: 19 additions & 0 deletions CITATION.cff
Original file line number Diff line number Diff line change
@@ -0,0 +1,19 @@
preferred-citation:
type: article
authors:
- family-names: "Wang"
given-names: "Han"
- family-names: "Zhang"
given-names: "Linfeng"
- family-names: "Han"
given-names: "Jiequn"
- family-names: "E"
given-names: "Weinan"
doi: "10.1016/j.cpc.2018.03.016"
journal: "Computer Physics Communications"
month: 7
start: 178 # First page number
end: 184 # Last page number
title: "DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics"
volume: 228
year: 2018
Loading