Comments (3)
Your atom type definitions look like they may be wrong: you seem to want, for example, LAMMPS atom type 4 to be Hydrogen, but are assigning it NequIP/Allegro type N
(the fourth NequIP type you list).
From the README:
The names after the model path deployed.pth indicate, in order, the names of the Allegro model's atom types to use for LAMMPS atom types 1, 2, and so on. The number of names given must be equal to the number of atom types in the LAMMPS configuration (not the Allegro model!). The given names must be consistent with the names specified in the Allegro training YAML in chemical_symbol_to_type or type_names.
I guess we could explain this more explicitly.
Given your masses/LAMMPS group labels, I think the correct line would be:
pair_coeff * * deployed.pth B C F H N
(If you find it more helpful to see the correspondance in code, consider these two lines from the unit tests:
"""
# note that ASE outputs lammps types in alphabetical order of chemical symbols
# since we use chem symbols in this test, just put the same
pair_coeff * * {deployed_model} {' '.join(sorted(set(config["chemical_symbols"])))}
{newline.join(' mass %i 1.0' % i for i in range(1, num_types + 1))}
"""
)
from pair_allegro.
I've also clarified this in the README.
from pair_allegro.
Thanks a lot! With the new atom types everything worked as expected.
from pair_allegro.
Related Issues (20)
- Configuring LAMMPS with pair_allegro HOT 2
- Virial and Lammps interface HOT 14
- Running pair_allegro with Kokkos on multiple GPUs HOT 1
- Error with the new pair_allegro-stress branch HOT 14
- 🐛 [BUG] Compilation of pair_allegro fails with `is protected within this context` HOT 2
- Problems parallelizing across more than 1 GPU HOT 11
- More trouble in LAMMPS compilation due to "LAMMPS_NS" HOT 5
- Using pair_allegro without stress on the newest version of LAMMPS HOT 2
- Mix Allegro and LJ type pair styles HOT 5
- Request for Raw Benchmark Data from Paper
- Some problems encountered when using multiple GPUs HOT 8
- Any plan of updates for newer LAMMPS? HOT 2
- Issue of running NEB with mpirun HOT 6
- Problem compiling lammps with kokkos HOT 1
- RuntimeError: CUDA error: device-side assert triggered HOT 2
- Simulated annealing calculation error using pair-allegro
- Calculating virial stress in lammps HOT 7
- allegro_pair style and empty partitions HOT 6
- Exception: expected scalar type Double but found Float HOT 1
- Error compiling pair_allegro with LAMMPS in google colab tutorial HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from pair_allegro.