Skip to content

An optimization framework using Latin Hypercube Design and deep learning to explore high-dimensional parameter spaces.

License

Notifications You must be signed in to change notification settings

mertyigit/INDEEDopt

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

36 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

INDEEDopt: INitial DEsign Enhanced Deep learning OPTimization framework for high dimensional ReaxFF force field parameterization

INDEEDopt Workflow Scheme

Python PyTorch GitHub License

UPDATES

Due to time limitations in other projects, I won't be able to maintain this package.

A common error that users of INDEEDopt face is the generation of lousy ffield files. The reason for that is the extra spaces in ffield file that are located in the "folder". Please clean all extra spaces after each line in ffield file.

Added an example INDEEDopt folder named example_github.zip. (November 2021)

Recent updates to some subroutines due to Tensorflow Deep Learning library updates (Feb 2021)

About

An optimization framework using Latin Hypercube Design and deep learning to explore high-dimensional parameter spaces.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages