Comments (2)
Looks like you defined your task incorrectly, the task should not be changed from:
task:
dataset: trajectory_lmdb
description: "Regressing to energies and forces for DFT trajectories from OCP"
type: regression
metric: mae
primary_metric: forces_mae
labels:
- potential energy
grad_input: atomic forces
tag_specific_weights:
- 0.05
- 1.0
- 1.0
dataset here doesn't refer to your particular dataset, but rather the dataset class used to load your data. You define your dataset here:
dataset = [
{'src': train_src, 'normalize_labels': False}, # train set
{'src': train_src}, # val set (optional)
{'src': train_src} # test set (optional - writes predictions to disk)
]
Where train_src
is the path to the LMDB you created, I assume sample_ReaxFF_water_10_lmdb
. Hope that helps!
from ocp.
Thank you, that fixed it!
from ocp.
Related Issues (20)
- How to get all datasets HOT 6
- E+F trajectory data for ood_* splits HOT 1
- Explanation of ODAC23 database keys HOT 1
- Request for VASP config / settings HOT 3
- OCPCalculator fails when loading checkpoints HOT 2
- Equiformer v2 PyPI release HOT 1
- Suggestions to improve changes in #639
- Balanced Sampler QOL
- Question about preprocessing relaxed trajectories HOT 3
- Does N2H4 means β*NHN2β in your paperοΌ HOT 1
- Skipping scheduler for EquiformerV2 with OC22 HOT 6
- Nan loss in Equiformer_v2 HOT 4
- Adsorption energy for OC20 mapping HOT 2
- Problem When Submitting Result Files HOT 4
- TypeError: a bytes-like object is required, not 'NoneType'
- scale file paths need to be updated for monorepo organization HOT 1
- Having troubles installing fairchem.core. when running"pip install packages/farichem-core" I get an error. HOT 8
- assert isinstance( ^^^^^^^^^^^ AssertionError when run ocptrainer.predict(ocptrainer.test_loader)
- Does ODAC use the same VASP settings as OC20? HOT 2
- How to get the totale system energy of a "fairchem.data.oc.core.Slab" or "fairchem.data.oc.core.Adsorbate" HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π 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. πππ
-
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 β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from ocp.