DeePTB
DeePTB copied to clipboard
Published
20 hours ago •
deepmodeling
deepmodeling
DeePTB: A deep learning package for tight-binding approach with ab initio accuracy.
Results
13
DeePTB issues
Sort by
recently updated
recently updated
newest added
### Describe Current Status and Possible Solution Current Status: The NEGF module now attains a constant fermi-energy input for the device and both leads. This is practical when the system...
Refactor
1. Implemented an LMDB AtomicDataset, which loads the data on the fly during the training. 2. Implemented data parsing tools from abacus single point calculation output to LMDB style dataset.
Considering the fermi level estimation method in band.py is not very accurate and might fail in the case of metal (like Au primitive cell), I add an another fermi level...
Metadata
32
Stars
12
Forks
Watchers
Owner
Metadata
DeePTB: A deep learning package for tight-binding approach with ab initio accuracy.