Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Ising model #87

Merged
merged 14 commits into from
Jan 14, 2022
Merged

Ising model #87

merged 14 commits into from
Jan 14, 2022

Conversation

allaffa
Copy link
Collaborator

@allaffa allaffa commented Jan 11, 2022

No description provided.

@allaffa allaffa requested review from streeve and pzhanggit January 11, 2022 15:38
@allaffa allaffa self-assigned this Jan 11, 2022
@allaffa allaffa changed the title reformatting Ising model Jan 11, 2022
@allaffa
Copy link
Collaborator Author

allaffa commented Jan 13, 2022

This is the performance I get by training a HydraGNN model with

number_atoms_per_dimension = 5
configurational_histogram_cutoff = 100

total_energy
magnetic_moment

Copy link
Collaborator

@streeve streeve left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This looks great! I was also able to start testing locally

examples/ising_model/ising_model.json Outdated Show resolved Hide resolved
examples/ising_model/requirements.txt Show resolved Hide resolved
examples/ising_model/create_configurations.py Show resolved Hide resolved
examples/ising_model/create_configurations.py Show resolved Hide resolved
examples/ising_model/create_configurations.py Outdated Show resolved Hide resolved
examples/ising_model/create_configurations.py Outdated Show resolved Hide resolved
examples/ising_model/ising_model.json Outdated Show resolved Hide resolved
@pzhanggit
Copy link
Collaborator

pzhanggit commented Jan 13, 2022

This is the performance I get by training a HydraGNN model with

@allaffa @streeve Does it make sense to view spin prediction as a classification problem in the Ising model?

@allaffa
Copy link
Collaborator Author

allaffa commented Jan 13, 2022

@pzhanggit it does make sense, but I would like to give the idea that the Ising model naturally flows into the FePt case without changing of predictive tasks.

@allaffa allaffa merged commit 1bfb03c into ORNL:main Jan 14, 2022
@allaffa allaffa deleted the Ising_model branch January 14, 2022 14:21
RylieWeaver pushed a commit to RylieWeaver/HydraGNN that referenced this pull request Oct 17, 2024
* reformatting

* Update create_configurations.py

* json file added for Ising model

* Update ising_model.json

* change in the definition of the spin and change of data format in .json file

* requirements file for example added

* Rename ising data

* Add tqdm

* Rename spin and redefine atom_type

* removed subtraction of -1 from coordinates

* sine used to map atom features into spin

* sinusoidal spin used to calculate the energy

* setting for creation of dfataset and model changed

Co-authored-by: Massimiliano Lupo Pasini <7ml@ornl.gov>
Co-authored-by: Sam Reeve <6740307+streeve@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants