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

dEdLat contribution for stress calculations is added and Universal Potentials are updated #189

Merged
merged 28 commits into from
Nov 16, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
28 commits
Select commit Hold shift + click to select a range
ccad860
Optimize the Atoms2Graph and fixed the np.meshgrid
kenko911 Aug 29, 2023
bafbc16
put unittests
kenko911 Aug 29, 2023
120a36e
Merge branch 'materialsvirtuallab:main' into main
kenko911 Aug 29, 2023
9e1a24b
improve the _three_body.py and test_M3GNetCalculator in test_ase.py
kenko911 Aug 29, 2023
1057435
Merge branch 'main' into main
shyuep Aug 29, 2023
a65b926
Merge branch 'materialsvirtuallab:main' into main
kenko911 Aug 31, 2023
83b8eb8
add cpu() in ase.py and compute.py to enable the GPU usage for MatGL-…
kenko911 Aug 31, 2023
184c0ec
Merge branch 'materialsvirtuallab:main' into main
kenko911 Aug 31, 2023
7db50e7
included the unit-test for hessian test_ase.py to improve the coverag…
kenko911 Sep 1, 2023
5b3ea43
Merge branch 'main' of https://github.com/kenko911/matgl
kenko911 Sep 1, 2023
517ba07
Merge branch 'materialsvirtuallab:main' into main
kenko911 Sep 3, 2023
8d2e6ef
Merge branch 'materialsvirtuallab:main' into main
kenko911 Sep 5, 2023
1253ba5
remove reducdant torch.unique for finding the maximum three_body inde…
kenko911 Sep 5, 2023
555a001
Merge branch 'materialsvirtuallab:main' into main
kenko911 Sep 13, 2023
ca79fab
add united test for trainer.test and description in the example
kenko911 Sep 13, 2023
28b2401
Merge branch 'materialsvirtuallab:main' into main
kenko911 Sep 18, 2023
e4171d6
add option for PES training without stresses
kenko911 Sep 19, 2023
1e693dd
Merge branch 'materialsvirtuallab:main' into main
kenko911 Sep 19, 2023
de13b22
merged the changes and fix errors
kenko911 Sep 19, 2023
15427dc
add backward compatibility for data_mean in pes.py
kenko911 Sep 20, 2023
479a4b0
Merge branch 'materialsvirtuallab:main' into main
kenko911 Sep 28, 2023
07e5b04
An Example for the simple training of M3GNet formation energy model i…
kenko911 Sep 28, 2023
7f52d3f
Merge branch 'materialsvirtuallab:main' into main
kenko911 Oct 6, 2023
d43c498
Merge branch 'materialsvirtuallab:main' into main
kenko911 Nov 4, 2023
0012f79
dEdLat for stress contributions in PES is added
kenko911 Nov 14, 2023
62650e0
Improve the coverage score for training.py
kenko911 Nov 14, 2023
8092630
improve coverage/patch for data.py
kenko911 Nov 14, 2023
233cb4d
further improve coverage/patch for training.py, datat.py and ase.py
kenko911 Nov 15, 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
1,566 changes: 8 additions & 1,558 deletions examples/Benchmarking M3GNet Predictions of Cubic Lattice Parameters.ipynb

Large diffs are not rendered by default.

Original file line number Diff line number Diff line change
Expand Up @@ -94,7 +94,7 @@
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "f05586e80c904f0c88c3098c61fe535b",
"model_id": "1827af8bbaf94a06a1d620b464e6b6a3",
"version_major": 2,
"version_minor": 0
},
Expand Down Expand Up @@ -144,17 +144,17 @@
"text": [
"Full Formula (Sr1 Ti1 O3)\n",
"Reduced Formula: SrTiO3\n",
"abc : 3.944760 3.944760 3.944760\n",
"angles: 89.999998 90.000000 90.000000\n",
"abc : 3.937988 3.937988 3.937988\n",
"angles: 90.000001 90.000000 90.000000\n",
"pbc : True True True\n",
"Sites (5)\n",
" # SP a b c\n",
"--- ---- ---- ---- ----\n",
" 0 Sr 0 0 0\n",
" 1 Ti 0.5 0.5 0.5\n",
" 2 O 0.5 -0 0.5\n",
" 3 O -0 0.5 0.5\n",
" 4 O 0.5 0.5 -0\n"
" # SP a b c\n",
"--- ---- ---- --- ----\n",
" 0 Sr 0 0 -0\n",
" 1 Ti 0.5 0.5 0.5\n",
" 2 O 0.5 0 0.5\n",
" 3 O -0 0.5 0.5\n",
" 4 O 0.5 0.5 0\n"
]
}
],
Expand Down Expand Up @@ -223,8 +223,8 @@
"name": "stdout",
"output_type": "stream",
"text": [
"The predicted formation energy for the unrelaxed SrTiO3 is -2.103 eV/atom.\n",
"The predicted formation energy for the relaxed SrTiO3 is -3.571 eV/atom.\n",
"The predicted formation energy for the unrelaxed SrTiO3 is -2.240 eV/atom.\n",
"The predicted formation energy for the relaxed SrTiO3 is -3.495 eV/atom.\n",
"The Materials Project formation energy for DFT-relaxed SrTiO3 is -3.552 eV/atom.\n"
]
}
Expand Down Expand Up @@ -270,16 +270,16 @@
"text": [
"PBE band gap\n",
"\tUnrelaxed STO = 0.16 eV.\n",
"\tRelaxed STO = 1.67 eV.\n",
"\tRelaxed STO = 1.72 eV.\n",
"GLLB-SC band gap\n",
"\tUnrelaxed STO = 2.36 eV.\n",
"\tRelaxed STO = 3.13 eV.\n",
"\tRelaxed STO = 3.22 eV.\n",
"HSE band gap\n",
"\tUnrelaxed STO = 0.53 eV.\n",
"\tRelaxed STO = 2.88 eV.\n",
"\tRelaxed STO = 3.07 eV.\n",
"SCAN band gap\n",
"\tUnrelaxed STO = 0.72 eV.\n",
"\tRelaxed STO = 2.17 eV.\n",
"\tRelaxed STO = 2.19 eV.\n",
"The PBE band gap for STO from Materials Project is 1.77 eV.\n"
]
}
Expand Down Expand Up @@ -329,7 +329,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.16"
"version": "3.10.9"
}
},
"nbformat": 4,
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -74,7 +74,15 @@
"execution_count": null,
"id": "ce4e9336",
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"The predicted formation energy for CsCl is -2.272 eV/atom.\n"
]
}
],
"source": [
"# Load the pre-trained MEGNet formation energy model.\n",
"model = matgl.load_model(\"MEGNet-MP-2018.6.1-Eform\")\n",
Expand All @@ -95,7 +103,15 @@
"execution_count": null,
"id": "4aef3fec",
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"The predicted formation energy for CsCl is -2.220 eV/atom.\n"
]
}
],
"source": [
"# Load the pre-trained M3GNet formation energy model\n",
"model = matgl.load_model(\"M3GNet-MP-2018.6.1-Eform\")\n",
Expand All @@ -119,7 +135,18 @@
"execution_count": null,
"id": "f2ec796f",
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"The predicted PBE band gap for CsCl is 4.825 eV.\n",
"The predicted GLLB-SC band gap for CsCl is 8.323 eV.\n",
"The predicted HSE band gap for CsCl is 6.317 eV.\n",
"The predicted SCAN band gap for CsCl is 5.965 eV.\n"
]
}
],
"source": [
"model = matgl.load_model(\"MEGNet-MP-2019.4.1-BandGap-mfi\")\n",
"\n",
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -77,14 +77,14 @@
"text": [
"Full Formula (Cs1 Cl1)\n",
"Reduced Formula: CsCl\n",
"abc : 4.211410 4.211410 4.211410\n",
"angles: 90.000000 90.000000 90.000000\n",
"abc : 4.212023 4.212023 4.212023\n",
"angles: 89.999999 90.000000 90.000000\n",
"pbc : True True True\n",
"Sites (2)\n",
" # SP a b c\n",
"--- ---- --- ---- ----\n",
" 0 Cs 0 -0 -0\n",
" 1 Cl 0.5 0.5 0.5\n",
" # SP a b c\n",
"--- ---- ---- ---- ----\n",
" 0 Cs -0 -0 -0\n",
" 1 Cl 0.5 0.5 0.5\n",
"The final energy is -6.543 eV.\n"
]
}
Expand Down Expand Up @@ -122,7 +122,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
"The potential energy of CsCl at 300 K after 100 steps is -6.430 eV.\n"
"The potential energy of CsCl at 300 K after 100 steps is -6.479 eV.\n"
]
}
],
Expand Down Expand Up @@ -159,7 +159,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
"The calculated potential energy is -6.430 eV.\n"
"The calculated potential energy is -6.479 eV.\n"
]
}
],
Expand Down Expand Up @@ -188,7 +188,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.16"
"version": "3.10.9"
}
},
"nbformat": 4,
Expand Down
Loading