Comments (3)
Hi @wfreinhart thanks a lot for your message, sorry you're finding NaNs! I just opened up / ran the JAX MD cookbook and it did not give NaNs (except, curiously for once cell in the NN example because the learning rate is slightly too high). It is strange because, as you suggest, neither of us are running locally and we are both using a fresh install.
One thing I'm curious about: in the cookbook notebook I don't actually see that we use LJ anywhere, just to confirm: you also observe NaNs with the soft sphere potential?
from jax-md.
Thanks for the quick reply! Yes, I was talking about the soft sphere potential in the cookbook, sorry for the confusion.
I triple checked and realized my mistake -- I was looking at an old version of the code at https://github.com/jaxmd/jax-md and literally didn't realize until this moment that it was located at a different url than this one. My mistake!
from jax-md.
Ah yes, this is confusing; that version was an anonymized version for a conference but really it shouldn't exist anymore. I'll make a note to delete it. In case you were looking there, we have a number of new notebooks now that I think are a bit more current than the cookbook notebook!
from jax-md.
Related Issues (20)
- Cannot import 'FunctionalFullyConnectedTensorProduct' from 'e3nn_jax' HOT 1
- test_nequip_silicon in energy_test.py is broken.
- test_nve_2d_neighbor_list_multi_atom_species in rigid_body_test.py is broken HOT 1
- documentation not compiling 2
- Elasticity calculations involving rigid bodies
- Out Of Memory issue during neighbor list generation
- Inconsistence of periodic and periodic_general
- equivariant_neural_networks notebook is broken
- Question about npt simulation HOT 2
- AttributeError: module 'jax.random' has no attribute 'KeyArray' HOT 1
- Neighbor lists are broken for rigid bodies.
- PME Energies
- AttributeError: module 'jax' has no attribute 'linear_util'
- ImportError in the example notebooks HOT 1
- Run sample notebooks as of 13 April 2024. HOT 2
- Potential Definition Discrepancy with Stress Calculation
- future directions to improve jax-md's performance?
- Error when running flocking.ipynb HOT 1
- How to generate equivalent NequIP model in JAX-MD
- test_coulomb_cubeions fails
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 jax-md.