PyPI page
Home page
Author:
None
Summary:
DeepH-pack is a general-purpose neural network package for deep-learning electronic structure calculations. As the latest evolution of the DeepH framework, it integrates all prior methodologies into a unified, cohesive toolkit. This enhanced version has been fully rebuilt using JAX, delivering greater computational efficiency and expanded functionality.
Latest version:
1.0.6.post3
Required dependencies:
h5py
|
joblib
|
matplotlib
|
numpy
|
pyarmor
|
rocksdict
|
toml
Optional dependencies:
cython
|
docutils
|
e3nn-jax
|
flax
|
ipykernel
|
ipython_genutils
|
jax
|
juliacall
|
jupytext
|
mpi4jax
|
mpi4py
|
myst_nb
|
nbstripout
|
optax
|
orbax-checkpoint
|
recommonmark
|
sphinx
|
sphinx-autobuild
|
sphinx-book-theme
|
sphinx-design
|
torch
|
torch_geometric
Downloads last day:
11
Downloads last week:
55
Downloads last month:
73