Comments (5)
I updated the docs with some information about the training procedure, see here: https://compphysvienna.github.io/n2p2/Topics/training.html
Hope this helps for the moment, more is about to be added, please stay tuned...
from n2p2.
Hi Andreas,
That is so great you have updated that part of the manual. Thank you.
I think it would be also helpful if you can add a part for computing "normalization factors" of data set using "nnp-norm" module.
from n2p2.
Certainly, I will update the docs soon.. in the meantime I would like to direct you to the docs here and this publication, where you can find in Chapter 3.1 details about the normalization procedure.
from n2p2.
I added some documentation about the normalization.. about the tool nnp-norm and the training procedure. Please have a look and tell me if something is still unclear! Thanks!
from n2p2.
Hi Andreas,
Many thanks for keeping the documentation updated and complete. I think this part is clear, helpful, and understandable. I just think it would be appropriated if you could add a few sentences regarding scaling the mean_energy with respect to the reference atom energies. Like what is the purpose of that, what should user do, etc and maybe noting that no matter whether the atomic reference energies are defined or not, the results of training or prediction should be the same. That is just a suggestion.
Thanks again for such a great help and support.
Mostafa
from n2p2.
Related Issues (20)
- N2P2/Lammps interface for performing 4G-HDNNP MD simulations. HOT 2
- difficulty to compile interface to LAMMPS (version 3 Nov 2022) HOT 2
- Cannot declare multiple elements
- Compute Stress n2p2/lammps interface
- Include an "inner cutoff" that suppresses the symmetry function values at short distances.
- Data set normalization
- Extrapolation warning occurs when using my NNP in interface-LAMMPS. HOT 3
- n2p2, The nnp potential of three elements ( eg : Cu, S, C ), can be used in MD simulations of two elements ?(eg: Cu2S) HOT 1
- LAMMPS NNP Interface
- nnp-comp2 select
- extraction of derivative of hidden layers w.r.t symmetry function
- How to specify the test set instead of random split
- Issues in linking with the GSL CBLAS library
- Can LAMMPS run Weighted symmetry function trained MD? It is not support on CP2K.
- ASE LAMMPSrun with lammps-nnp binary HOT 7
- Regarding input.data
- Negative Memory values in the "Estimated Memory Usage For Training" section
- N2P2 Checkpointing
- Make error: multiple target patterns. Stop
- A question about the command "nnp-prune sensitivity 0.5 max" in doc. HOT 1
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 n2p2.