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

Basis transfer code #216

Merged
merged 9 commits into from
Jan 1, 2025
Merged

Conversation

floatingCatty
Copy link
Member

  1. Add a new loss function: EigHamLoss

  2. Add a new eigenvalue and eigenvector calculation module: I want to use the eigenvector constraint, instead of the Hamiltonian and overlap to bind the model from overfitting, but it fails. The module still works.

@floatingCatty floatingCatty requested a review from QG-phy October 23, 2024 19:55
@@ -104,6 +104,7 @@
AtomicDataDict.HAMILTONIAN_KEY, # new # should be nested
AtomicDataDict.OVERLAP_KEY, # new # should be nested
AtomicDataDict.ENERGY_EIGENVALUE_KEY, # new # should be nested
AtomicDataDict.EIGENVECTOR_KEY, # new # should be nested
Copy link
Collaborator

Choose a reason for hiding this comment

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

是想把eigenvector 加入训练标签吗?估计不行啊。求导会出问题。

Copy link
Member Author

Choose a reason for hiding this comment

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

这块是deeptb接dftio算实空间LDOS的时候用的

Copy link
Collaborator

Choose a reason for hiding this comment

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

ok

dptb/nnops/loss.py Outdated Show resolved Hide resolved
@QG-phy QG-phy merged commit 73ff3c8 into deepmodeling:main Jan 1, 2025
2 checks 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