Comments (2)
Some more tests in 3D, since my previous comment on 0.1-1.0 is actually wrong. and is likely actually that scaled by the number of atoms (and can in principle be learned or kept as a user-input parameter. Some code:
from jax.ops import segment_sum, segment_min
import jax.numpy as jnp
import numpy as np
from matscipy.neighbours import neighbour_list
from scipy.stats.qmc import PoissonDisk
import matplotlib.pyplot as plt
np.random.seed(35280)
sampler = PoissonDisk(3)
points = sampler.fill_space()
num_points = len(points)
a = jnp.array(points)
i, j, dr = neighbour_list('ijd', cutoff=0.2, positions=np.array(a))
dr_mins = segment_min(dr, i, num_points)
repeats = jnp.bincount(i)
dr_mins = jnp.repeat(dr_mins, repeats)
for exp_denom in np.logspace(-4, -2, 3):
softmaxed_dr = jnp.exp(-(dr - dr_mins) / exp_denom)
softmax_weighted_dr = dr * softmaxed_dr / jnp.repeat(segment_sum(softmaxed_dr, i, num_points), repeats)
strict_min_dr = segment_min(dr, i, num_points)
soft_min_dr = segment_sum(softmax_weighted_dr, i, num_points)
plt.scatter(strict_min_dr, soft_min_dr, s=1, label=f"{exp_denom:0.1e}")
plt.legend()
plt.show()
from apax.
after some discussion with Anubhab, this approach seems incomplete. We'll think off something else.
from apax.
Related Issues (20)
- variable name consistency
- make atom / atoms / list of atoms more constant.
- Input pipeline fully out of core HOT 1
- Allow `apax` node with `data_file` HOT 1
- Piecewise linear MD temperature schedule HOT 2
- Rename `opt_name` to `name` HOT 2
- n_jitted_steps option buggy
- [BUG] Non-orthogonal cells do not evaluate correctly using the `batch_eval()` method HOT 2
- `nodes.Apax` retrain issues
- `nodes.Apax` metrics are wrong
- Replace matscipy nl with Vesin HOT 1
- Add uncertainties to jaxmd HOT 1
- Replace EnergyDervativeModel by function transformation
- update jax installation instructions in readme
- Batch eval bug for batch size larger 1 HOT 1
- ASE property assertion error
- Ensemble do not work with ApaxJaxMD
- Add MD termination criteria to Jaxmd
- `apax md` - show `ns/day`
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 apax.