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

Excited state nodes, docs, and an example (#42) #3

Merged
merged 1 commit into from
Nov 17, 2023

Conversation

adela-habib
Copy link
Owner

  • Add nodes for NACR and phase-less loss

  • NACR node now does NACR_ij * ΔE_ij

  • dE should be E_j - E_i

  • remove parent expansion

  • Update NACR implementation

  1. Fix a bug where the charges tensor is incorrectly sliced.
  2. Add corresponding tests to NACR layers.
  • Fix a bug on calculating the phase-less loss

When the predicted vector is not in the same quadrant as the true value, the calculated loss would be smaller than the correct one. This might cause training process slower or stuck.

  • Fix a bug in new MSE implementation

  • Fix a bug in setting up custom kernels

Now "auto" will use pytorch when numba or cupy is not installed

  • Add nodes and example for excited states

  • Update changelog and rename example file

  • update example for excited states

  • move excited states into subdirectories

  • fix import order and make excited states import by default

  • update documentation

  • documentation update


* Add nodes for NACR and phase-less loss

* NACR node now does NACR_ij * ΔE_ij

* dE should be E_j - E_i

* remove parent expansion

* Update NACR implementation

1. Fix a bug where the charges tensor is incorrectly sliced.
2. Add corresponding tests to NACR layers.

* Fix a bug on calculating the phase-less loss

When the predicted vector is not in the same quadrant as the true value,
the calculated loss would be smaller than the correct one. This might
cause training process slower or stuck.

* Fix a bug in new MSE implementation

* Fix a bug in setting up custom kernels

Now "auto" will use pytorch when numba or cupy is not installed

* Add nodes and example for excited states

* Update changelog and rename example file

* update example for excited states

* move excited states into subdirectories

* fix import order and make excited states import by default

* update documentation

* documentation update

---------

Co-authored-by: Nicholas Lubbers <hippynn@lanl.gov>
@adela-habib adela-habib merged commit bfae85b into adela-habib:development Nov 17, 2023
1 check passed
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.

2 participants