Comments (2)
sgbaird
commented on June 3, 2024
Also, the CrabNet paper reports an even lower error for the matbench_expt_gap task (0.338 eV) than what's shown in the matbench submission (0.3463 eV). Maybe it is just that I didn't run it for enough epochs. Ran it for 100 epochs and got 0.3485 eV.
from crabnet.
sgbaird
commented on June 3, 2024
I think I was using a fresh clone of CrabNet, but this would probably need to be verified.
from crabnet.
Related Issues (20)
- Multiclass classification HOT 5
- pip or conda install HOT 6
- Is Python 3.8+ a known requirement, or are earlier versions just untested? HOT 1
- CrabNet sometimes ignores/skips certain compounds. Why? How to keep track of compound IDs? HOT 4
- fit() and predict() methods
- Does CrabNet use the validation data to improve the model? HOT 4
- Seems like an "extend_features" option for CrabNet could be useful for several people HOT 11
- CrabNet matbench results - possibly neglecting 25% of the training data it could have used HOT 2
- the classification criterion doesn't factor in the uncertainty - does this mean ignore the uncertainty for classification?
- pinned pytorch and cudatoolkit dependencies possibly defunct for GPU usage HOT 1
- attention-heads as samples from posterior distribution in a Bayesian sense
- Reproducing RooSt results, error using RooSt Colab example is higher than what's reported in CrabNet paper
- Parameter used for the results in the published work
- Add skipatom featurizer to the repository
- Facing issue while importing model (from crabnet.model import Model) HOT 1
- The order of the two hyperlinks on the "Publications / How to cite" module in the readme file seems to be reversed HOT 1
- AttributeError: 'SWA' object has no attribute '_optimizer_step_pre_hooks'. Did you mean: '_optimizer_step_code'?
- about the predictor HOT 7
- Do any of the CSV files in data/element_properties/ need citations? (e.g. in a README in the element_properties folder) 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 crabnet.