Comments (5)
Sounds like there's an issue with the training. I'm looking into this. FWIW it always works on my local computer (and runs in about 10 seconds). I can push a quick fix that makes it run faster and should avert this error and look into it more soon.
from flare.
It's actually failing every time on my machine now. Have you pulled all the updates?
from flare.
This commit should speed it up:
2622d2c
While it makes the test slightly 'weaker' by no longer training the GP, other unit tests cover the act of calling and training a GP. I will open an issue to make this unit test better.
from flare.
Also FWIW, it wasn't just you: I tried the offending unit test on Odyssey and it did indeed hang there. Things should all be up to date. We can take the difference between the above new commit and the current development branch to see what's wrong.
from flare.
Opened a PR, thanks for bringing this to my attention. Sorry I didn't catch it sooner!
from flare.
Related Issues (20)
- otf run hangs at the very first step
- Trajectory extraction HOT 7
- OTF SGP models with force_only=True, not working with OTF.from_checkpint() HOT 2
- Output file inquire HOT 3
- Is the specific coarse-grain version available? HOT 1
- seg fault when predicting local uncertainty with trained sgp calculator HOT 4
- Potential Parallelism for Hyperparameter Tuning
- Execluding some species from training HOT 1
- Bug: Python API cannot save trained model (Segmentation fault, list index out of range) HOT 3
- Adding 'Select' atomic environments to a pre-trained SGP Model using off-line training HOT 3
- Can't clone flare on windows because of tests/test_files/output_files/. Possibly OUTCAR naming not allowed on windows HOT 1
- Google Colab FLARE+LAMMPS crashing HOT 3
- About Mapped GP HOT 1
- Mapped Model in LAMMPS inaccurate compared to ASE SGP Model HOT 4
- Mapped GP Model Grid Options for SGP HOT 2
- How to accelerate training with large dataset HOT 4
- Can't access tutorial notebooks on Colab HOT 2
- Can not exclude stresses from training HOT 4
- Wrong parsing of the results which sticks numbers together.
- Supercell selection in offline training for 2 different systems
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 flare.